{"id":21332439,"url":"https://github.com/dwctod/eccv2022-papers-with-code-demo","last_synced_at":"2026-01-27T11:02:09.906Z","repository":{"id":41807690,"uuid":"510372007","full_name":"DWCTOD/ECCV2022-Papers-with-Code-Demo","owner":"DWCTOD","description":"收集 ECCV 最新的成果，包括论文、代码和demo视频等，欢迎大家推荐！","archived":false,"fork":false,"pushed_at":"2022-11-15T13:21:56.000Z","size":174,"stargazers_count":286,"open_issues_count":0,"forks_count":23,"subscribers_count":7,"default_branch":"main","last_synced_at":"2025-03-16T01:11:12.321Z","etag":null,"topics":["ai","computer-vision","cv","dataset","diffusion","eccv","eccv2022","face-recognition","image-segmentation","multimodal-deep-learning","nerf","objection-detection","vision-transformer"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DWCTOD.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-07-04T13:32:51.000Z","updated_at":"2025-02-26T05:23:49.000Z","dependencies_parsed_at":"2023-01-21T20:35:30.167Z","dependency_job_id":null,"html_url":"https://github.com/DWCTOD/ECCV2022-Papers-with-Code-Demo","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/DWCTOD/ECCV2022-Papers-with-Code-Demo","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DWCTOD%2FECCV2022-Papers-with-Code-Demo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DWCTOD%2FECCV2022-Papers-with-Code-Demo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DWCTOD%2FECCV2022-Papers-with-Code-Demo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DWCTOD%2FECCV2022-Papers-with-Code-Demo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DWCTOD","download_url":"https://codeload.github.com/DWCTOD/ECCV2022-Papers-with-Code-Demo/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DWCTOD%2FECCV2022-Papers-with-Code-Demo/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28812367,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-27T07:41:26.337Z","status":"ssl_error","status_checked_at":"2026-01-27T07:41:08.776Z","response_time":168,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","computer-vision","cv","dataset","diffusion","eccv","eccv2022","face-recognition","image-segmentation","multimodal-deep-learning","nerf","objection-detection","vision-transformer"],"created_at":"2024-11-21T22:48:16.345Z","updated_at":"2026-01-27T11:02:09.888Z","avatar_url":"https://github.com/DWCTOD.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# ECCV2022-Papers-with-Code-Demo\n收集 ECCV 最新的成果，包括论文、代码和demo视频等，欢迎大家推荐！\n\n欢迎关注公众号：AI算法与图像处理\n\n :star_and_crescent:**福利 注册即可领取 200 块计算资源 : https://www.bkunyun.com/wap/console?source=aistudy**\n [使用说明](https://mp.weixin.qq.com/s?__biz=MzU4NTY4Mzg1Mw==\u0026amp;mid=2247521550\u0026amp;idx=1\u0026amp;sn=db4c7f609bd61ae7734b9e012a763f98\u0026amp;chksm=fd8413eccaf39afa686f69f2df2463f4a6a8233ba3b3edf698513bbee556c9f6c21e835b8eb8\u0026token=705359263\u0026lang=zh_CN#rd)\n\n\n\n:star2: [ECCV 2022](https://eccv2022.ecva.net/) 持续更新最新论文/paper和相应的开源代码/code！\n\n:car: ECCV 2022 收录列表ID：https://ailb-web.ing.unimore.it/releases/eccv2022/accepted_papers.txt\n\n:car: 官网链接：https://eccv2022.ecva.net\n\nB站demo：https://space.bilibili.com/288489574\n\n\u003e :hand: ​注：欢迎各位大佬提交issue，分享ECCV 2022论文/paper和开源项目！共同完善这个项目\n\u003e\n\u003e 往年顶会论文汇总：\n\n\u003e [CVPR2022](https://github.com/DWCTOD/CVPR2022-Papers-with-Code-Demo)\n\u003e \n\u003e [CVPR2021](https://github.com/DWCTOD/CVPR2022-Papers-with-Code-Demo/blob/main/CVPR2021.md)\n\u003e\n\u003e [ICCV2021](https://github.com/DWCTOD/ICCV2021-Papers-with-Code-Demo)\n\n### **:fireworks: 欢迎进群** | Welcome\n\nECCV 2022 论文/paper交流群已成立！已经收录的同学，可以添加微信：**nvshenj125**，请备注：**ECCV+姓名+学校/公司名称**！一定要根据格式申请，可以拉你进群。\n\n\u003ca name=\"Contents\"\u003e\u003c/a\u003e\n\n### :hammer: **目录 |Table of Contents（点击直接跳转）**\n\n\u003cdetails open\u003e\n\u003csummary\u003e 目录（右侧点击可折叠）\u003c/summary\u003e\n\n- [数据集/Dataset](#Dataset)\n- [Image Classification](#ImageClassification)\n- [GAN](#GAN)\n- [NeRF](#NeRF)\n- [Visual Transformer](#VisualTransformer)\n- [多模态/Multimodal ](#Multimodal)\n- [Vision-Language](#Vision-Language)\n- [对比学习/Contrastive Learning](#ContrastiveLearning)\n- [Domain Adaptation](#DomainAdaptation)\n- [目标检测/Object Detection](#ObjectDetection)\n- [目标跟踪/Object Tracking](#ObjectTracking)\n- [语义分割/Segmentation](#Segmentation)\n- [Video Segmentation](#VS)\n- [医学图像分割/Medical Image Segmentation](#MIS)\n- [Knowledge Distillation](#KnowledgeDistillation)\n- [Action Detection](#ActionDetection)\n- [Action Recognition](#ActionRecognition)\n- [Anomaly Detection](#AnomalyDetection)\n- [人脸识别/Face Recognition](#FaceRecognition)\n- [人脸检测/Face Detection](#FaceDetection)\n- [人脸活体检测/Face Anti-Spoofing](#FaceAnti-Spoofing)\n- [人脸年龄估计/Age Estimation](#AgeEstimation)\n- [人脸表情识别/Facial Expression Recognition](#FacialExpressionRecognition)\n- [人脸属性识别/Facial Attribute Recognition](#FacialAttributeRecognition)\n- [人脸编辑/Facial Editing](#FacialEditing)\n- [人脸相关 / Face](#Face)\n- [人体姿态估计/Human Pose Estimation](#HumanPoseEstimation)\n- [3D reconstruction](#3DReconstruction)\n- [Human Reconstruction](#HumanReconstruction)\n- [Relighting](#Relighting)\n- [DeepFake](#DeepFake)\n- [OCR](#OCR)\n- [Text Recognition](#TextRecognition)\n- [点云/Point Cloud](#PointCloud)\n- [光流估计/Flow Estimation](#FlowEstimation)\n- [深度估计/Depth Estimation](#DepthEstimation)\n- [车道线检测/Lane Detection](#LaneDetection)\n- [轨迹预测/Trajectory Prediction](#TrajectoryPrediction)\n- [超分/Super-Resolution](#Super-Resolution)\n- [图像去噪/Image Denoising](#ImageDenoising)\n- [图像去模糊/Image Deblurring](#ImageDeblurring)\n- [图像复原/Image Restoration](#ImageRestoration)\n- [图像增强/Image Enhancement](#ImageEnhancement)\n- [图像修复/Image Inpainting](#ImageInpainting)\n- [视频插帧/Video Interpolation](#VideoInterpolation)\n- [Temporal Action Segmentation](#TemporalActionSegmentation)\n- [检索/Image Retrieval](#ImageRetrieval)\n- [Diffusion](#diffusion)\n- [其他/Other](#Other)\n\n\u003c/details\u003e\n\n\u003ca name=\"Dataset\"\u003e\u003c/a\u003e \n\n## 数据集/Dataset\n\n**COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04675\n- 代码/Code: https://github.com/ku21fan/COO-Comic-Onomatopoeia\n\n**Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10664\n- 代码/Code: https://github.com/visipedia/ssw60\n\n**BRACE: The Breakdancing Competition Dataset for Dance Motion Synthesis**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10120\n- 代码/Code: https://github.com/dmoltisanti/brace\n\n**CelebV-HQ: A Large-Scale Video Facial Attributes Dataset**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12393\n- 代码/Code: https://github.com/CelebV-HQ/CelebV-HQ\n\n**Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.01166\n- 代码/Code: None\n\n**Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03826\n- 代码/Code: https://github.com/owenzlz/EgoHOS\n\n**TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.07943\n- 代码/Code: https://github.com/shubham1810/trove_toolkit\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"ImageClassification\"\u003e\u003c/a\u003e \n\n## Image Classification\n\n**Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06989\n- 代码/Code: https://github.com/remiMZ/HTS-ECCV22\n\n**Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07818\n- 代码/Code: https://github.com/zh460045050/BagCAMs\n\n**Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09519\n- 代码/Code: https://github.com/gaopengcuhk/tip-adapter\n\n**Invariant Feature Learning for Generalized Long-Tailed Classification**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09504\n- 代码/Code: https://github.com/kaihuatang/generalized-long-tailed-benchmarks.pytorch\n\n**RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11075\n- 代码/Code: https://github.com/megvii-research/RealFlow\n\n**PLMCL: Partial-Label Momentum Curriculum Learning for Multi-Label Image Classification**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09999\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"GAN\"\u003e\u003c/a\u003e \n\n## GAN\n\n**Ultra-high-resolution unpaired stain transformation via Kernelized Instance Normalization**\n\n- 论文/Paper: https://arxiv.org/pdf/2208.10730v1.pdf\n- 代码/Code: https://github.com/Kaminyou/URUST\n\n**Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling**\n\n- 论文/Paper: http://arxiv.org/abs/2207.02196\n- 代码/Code: https://github.com/fudan-zvg/pds\n\n**CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04808\n- 代码/Code: https://github.com/JarrentWu1031/CCPL\n\n**Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05049\n- 代码/Code: https://github.com/fast-vid2vid/fast-vid2vid\n\n**RepMix: Representation Mixing for Robust Attribution of Synthesized Images**\n\n- 论文/Paper: http://arxiv.org/abs/2207.02063\n- 代码/Code: https://github.com/tubui/image_attribution\n\n**VecGAN: Image-to-Image Translation with Interpretable Latent Directions**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.03411\n- 代码/Code: None\n\n**Context-Consistent Semantic Image Editing with Style-Preserved Modulation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06252\n- 代码/Code: https://github.com/wuyangluo/spmpgan\n\n**DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06124\n- 代码/Code: https://github.com/huage001/dynast\n\n**Supervised Attribute Information Removal and Reconstruction for Image Manipulation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06555\n- 代码/Code: https://github.com/nannanli999/airr\n\n**Name: Adaptive Feature Interpolation for Low-Shot Image Generation**\n\n- 论文/Paper: https://arxiv.org/abs/2112.02450\n- 代码/Code: https://github.com/dzld00/Adaptive-Feature-Interpolation-for-Low-Shot-Image-Generation\n\n**WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07288\n- 代码/Code: Link:https://github.com/kobeshegu/ECCV2022_WaveGAN\n\n**FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08630\n- 代码/Code: https://github.com/iceli1007/FakeCLR\n\n**Outpainting by Queries**\n- 论文/Paper: https://arxiv.org/abs/2207.05312\n- 代码/Code: https://github.com/Kaiseem/QueryOTR\n\n**Single Stage Virtual Try-on via Deformable Attention Flows**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09161\n- 代码/Code: https://github.com/OFA-Sys/DAFlow\n\n**Structure-aware Editable Morphable Model for 3D Facial Detail Animation and Manipulation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09019\n- 代码/Code: https://github.com/gerwang/facial-detail-manipulation\n\n**Monocular 3D Object Reconstruction with GAN Inversion**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10061\n- 代码/Code: https://github.com/junzhezhang/mesh-inversion\n\n**Generative Multiplane Images: Making a 2D GAN 3D-Aware**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10642\n- 代码/Code: https://github.com/apple/ml-gmpi\n\n**DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10271\n- 代码/Code: https://github.com/bcmi/deltagan-few-shot-image-generation\n\n**Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10257\n- 代码/Code: https://github.com/jgkwak95/surf-gan\n\n**SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10256\n- 代码/Code: None\n\n**2D GANs Meet Unsupervised Single-view 3D Reconstruction**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10183\n- 代码/Code: None\n\n**InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11148\n- 代码/Code: None\n\n**Auto-regressive Image Synthesis with Integrated Quantization**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10776\n- 代码/Code: None\n\n**Compositional Human-Scene Interaction Synthesis with Semantic Control**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12824\n- 代码/Code: https://github.com/zkf1997/coins\n\n**Generator Knows What Discriminator Should Learn in Unconditional GANs**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13320\n- 代码/Code: https://github.com/naver-ai/GGDR\n\n**StyleLight: HDR Panorama Generation for Lighting Estimation and Editing**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.14811\n- 代码/Code: https://github.com/Wanggcong/StyleLight\n\n**Cross Attention Based Style Distribution for Controllable Person Image Synthesis**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00712\n- 代码/Code: https://github.com/xyzhouo/casd\n\n**SKDCGN: Source-free Knowledge Distillation of Counterfactual Generative Networks using cGANs**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.04226\n- 代码/Code: https://github.com/ambekarsameer96/SKDCGN\n\n**Hierarchical Semantic Regularization of Latent Spaces in StyleGANs**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03764\n- 代码/Code: None\n\n**Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.07765\n- 代码/Code: https://github.com/taeu/style-your-hair\n\n**Paint2Pix: Interactive Painting based Progressive Image Synthesis and Editing**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.08092\n- 代码/Code: https://github.com/1jsingh/paint2pix\n\n**Mind the Gap in Distilling StyleGANs**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.08840\n- 代码/Code: https://github.com/xuguodong03/stylekd\n\n**ModSelect: Automatic Modality Selection for Synthetic-to-Real Domain Generalization**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09414\n- 代码/Code: None\n\n**FurryGAN: High Quality Foreground-aware Image Synthesis**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10422\n- 代码/Code: None\n\n**Improving GANs for Long-Tailed Data through Group Spectral Regularization**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09932\n- 代码/Code: None\n\n**Unrestricted Black-box Adversarial Attack Using GAN with Limited Queries**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.11613\n- 代码/Code: None\n\n**3D-FM GAN: Towards 3D-Controllable Face Manipulation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.11257\n- 代码/Code: None\n\n**High-Fidelity Image Inpainting with GAN Inversion**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.11850\n- 代码/Code: None\n\n**Bokeh-Loss GAN: Multi-Stage Adversarial Training for Realistic Edge-Aware Bokeh**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.12343\n- 代码/Code: None\n\n**Exploring Gradient-based Multi-directional Controls in GANs**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.00698\n- 代码/Code: None\n\n**Studying Bias in GANs through the Lens of Race**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.02836\n- 代码/Code: None\n\n**Improved Masked Image Generation with Token-Critic**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.04439\n- 代码/Code: None\n\n**Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.05968\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"NeRF\"\u003e\u003c/a\u003e \n\n## NeRF\n\n**Streamable Neural Fields**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09663\n- 代码/Code: https://github.com/jwcho5576/streamable_nf\n\n**Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10257\n- 代码/Code: https://github.com/jgkwak95/surf-gan\n\n**AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fields**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10312\n- 代码/Code: https://github.com/thomasneff/AdaNeRF\n\n**PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereo**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11406\n- 代码/Code: None\n\n**Neural-Sim: Learning to Generate Training Data with NeRF**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11368\n- 代码/Code: https://github.com/gyhandy/neural-sim-nerf\n\n**Neural Density-Distance Fields**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.14455\n- 代码/Code: https://github.com/ueda0319/neddf\n\n**HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.06787\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"VisualTransformer\"\u003e\u003c/a\u003e \n\n## Visual Transformer\n\n**k-means Mask Transformer**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04044\n- 代码/Code: https://github.com/google-research/deeplab2\n\n**Weakly Supervised Grounding for VQA in Vision-Language Transformers**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.02334\n- 代码/Code: https://github.com/aurooj/wsg-vqa-vltransformers\n\n**Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04978\n- 代码/Code: https://github.com/YehLi/ImageNetModel\n\n**CoMER: Modeling Coverage for Transformer-based Handwritten Mathematical Expression Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04410\n- 代码/Code: https://github.com/Green-Wood/CoMER\n\n**Towards Hard-Positive Query Mining for DETR-based Human-Object Interaction Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05293\n- 代码/Code: https://github.com/MuchHair/HQM\n\n**Hunting Group Clues with Transformers for Social Group Activity Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05254\n- 代码/Code: None\n\n**Entry-Flipped Transformer for Inference and Prediction of Participant Behavior**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06235\n- 代码/Code: None\n\n**DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06124\n- 代码/Code: https://github.com/huage001/dynast\n\n**Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06101\n- 代码/Code: https://github.com/boeun-kim/gl-transformer\n\n**TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08409\n- 代码/Code: https://github.com/Sense-X/TokenMix\n\n**TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07852\n- 代码/Code: None\n\n**Action Quality Assessment with Temporal Parsing Transformer**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09270\n- 代码/Code: None\n\n**GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09666\n- 代码/Code: https://github.com/davidnvq/grit\n\n**Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09644\n- 代码/Code: None\n\n**AiATrack: Attention in Attention for Transformer Visual Tracking**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09603\n- 代码/Code: https://github.com/Little-Podi/AiATrack\n\n**Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10040\n- 代码/Code: None\n\n**TinyViT: Fast Pretraining Distillation for Small Vision Transformers**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10666\n- 代码/Code: https://github.com/microsoft/cream\n\n**An Efficient Spatio-Temporal Pyramid Transformer for Action Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10448\n- 代码/Code: None\n\n**Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10447\n- 代码/Code: https://github.com/164140757/scm\n\n**SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10315\n- 代码/Code: https://github.com/hrzhou2/seedformer\n\n**Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10866\n- 代码/Code: None\n\n**IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12100\n- 代码/Code: None\n\n**3D Siamese Transformer Network for Single Object Tracking on Point Clouds**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11995\n- 代码/Code: None\n\n**Reference-based Image Super-Resolution with Deformable Attention Transformer**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11938\n- 代码/Code: None\n\n**SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13325\n- 代码/Code: None\n\n**Online Continual Learning with Contrastive Vision Transformer**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13516\n- 代码/Code: None\n\n**Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13820\n- 代码/Code: https://github.com/postech-ami/FastMETRO\n\n**Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00438\n- 代码/Code: https://github.com/xdxie/WordArt\n\n**TransMatting: Enhancing Transparent Objects Matting with Transformers**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03007\n- 代码/Code: https://github.com/AceCHQ/TransMatting\n\n**Ghost-free High Dynamic Range Imaging with Context-aware Transformer**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.05114\n- 代码/Code: https://github.com/megvii-research/hdr-transformer\n\n\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"Multimodal\"\u003e\u003c/a\u003e \n\n## 多模态 / Multimodal\n\n**Audio-Visual Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05042\n- 代码/Code: https://github.com/OpenNLPLab/AVSBench\n\n**Cross-modal Prototype Driven Network for Radiology Report Generation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04818\n- 代码/Code: None\n\n**Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecasting**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04624\n- 代码/Code: https://github.com/d1024choi/HLSTrajForecast\n\n**UniNet: Unified Architecture Search with Convolution, Transformer, and MLP**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05420\n- 代码/Code: https://github.com/Sense-X/UniNet\n\n**Video Graph Transformer for Video Question Answering**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05342\n- 代码/Code: https://github.com/sail-sg/VGT\n\n**Bootstrapped Masked Autoencoders for Vision BERT Pretraining**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07116\n- 代码/Code: https://github.com/lightdxy/bootmae\n\n**Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09156\n- 代码/Code: None\n\n**Exploiting Unlabeled Data with Vision and Language Models for Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08954\n- 代码/Code: https://github.com/xiaofeng94/VL-PLM\n\n**LocVTP: Video-Text Pre-training for Temporal Localization**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10362\n- 代码/Code: https://github.com/mengcaopku/locvtp\n\n**Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10785\n- 代码/Code: https://github.com/VinAIResearch/fsvc-ata\n\n**Cross-Modal 3D Shape Generation and Manipulation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11795\n- 代码/Code: None\n\n**Learning Visual Representation from Modality-Shared Contrastive Language-Image Pre-training**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12661\n- 代码/Code: https://github.com/hxyou/msclip\n\n**Frozen CLIP Models are Efficient Video Learners**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03550\n- 代码/Code: https://github.com/OpenGVLab/efficient-video-recognition\n\n**Consistency-based Self-supervised Learning for Temporal Anomaly Localization**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.05251\n- 代码/Code: None\n\n**Motion Sensitive Contrastive Learning for Self-supervised Video Representation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.06105\n- 代码/Code: None\n\n**TL;DW? Summarizing Instructional Videos with Task Relevance \u0026 Cross-Modal Saliency**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.06773\n- 代码/Code: None\n\n**See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.08608\n- 代码/Code: https://github.com/TencentYoutuResearch/PersonRetrieval-IVT.\n\n**Learning an Efficient Multimodal Depth Completion Model**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10771\n- 代码/Code: https://github.com/dwhou/emdc-pytorch\n\n**Learning from Unlabeled 3D Environments for Vision-and-Language Navigation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.11781\n- 代码/Code: None\n\n**CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.12448\n- 代码/Code: https://github.com/maoyunyao/cmd\n\n**StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.06192\n- 代码/Code: https://github.com/adymaharana/storydalle\n\n**MUST-VQA: MUltilingual Scene-text VQA**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.06730\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"Vision-Language\"\u003e\u003c/a\u003e \n\n## Vision-Language\n\n**Vision-Language Adaptive Mutual Decoder for OOV-STR**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.00859\n- 代码/Code: None\n\n\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"DomainAdaptation\"\u003e\u003c/a\u003e \n\n## Domain Adaptation\n\n**Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation**\n\n- 论文/Paper: https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136900177.pdf\n- 代码/Code: https://github.com/val-iisc/StickerDA\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"ContrastiveLearning\"\u003e\u003c/a\u003e \n\n## 对比学习/Contrastive Learning\n\n**Network Binarization via Contrastive Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.02970\n- 代码/Code: None\n\n**Contrastive Deep Supervision**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05306\n- 代码/Code: None\n\n**ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology Images**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06733\n- 代码/Code: https://github.com/tencentailabhealthcare/concl\n\n**Action-based Contrastive Learning for Trajectory Prediction**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08664\n- 代码/Code: None\n\n**FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08630\n- 代码/Code: https://github.com/iceli1007/FakeCLR.\n\n**Adversarial Contrastive Learning via Asymmetric InfoNCE**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08374\n- 代码/Code: https://github.com/yqy2001/A-InfoNCE\n\n**Fast-MoCo: Boost Momentum-based Contrastive Learning with Combinatorial Patches**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08220\n- 代码/Code: None\n\n**Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10899\n- 代码/Code: https://github.com/pantheon5100/DeACL.\n\n**Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10892\n- 代码/Code: None\n\n**Patient-level Microsatellite Stability Assessment from Whole Slide Images By Combining Momentum Contrast Learning and Group Patch Embeddings**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10429\n- 代码/Code: https://github.com/technioncomputationalmrilab/colorectal_cancer_ai\n\n**FairDisCo: Fairer AI in Dermatology via Disentanglement Contrastive Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10013\n- 代码/Code: https://github.com/siyi-wind/FairDisCo\n\n**CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09843\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"ObjectDetection\"\u003e\u003c/a\u003e \n\n## 目标检测/Object Detection\n\n**Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.02541\n- 代码/Code: None\n\n**Should All Proposals be Treated Equally in Object Detection?**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.03520\n- 代码/Code: None\n\n**HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05345\n- 代码/Code: https://github.com/LutingWang/HEAD\n\n**Adversarially-Aware Robust Object Detector**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06202\n- 代码/Code: https://github.com/7eu7d7/robustdet\n\n**ObjectBox: From Centers to Boxes for Anchor-Free Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06985\n- 代码/Code: https://github.com/mohsenzand/objectbox\n\n**Point-to-Box Network for Accurate Object Detection via Single Point Supervision**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06827\n- 代码/Code: None\n\n**DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08531\n- 代码/Code: https://github.com/SPengLiang/DID-M3D.\n\n**SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07898\n- 代码/Code: https://github.com/Hydragon516/SPSN\n\n**Rethinking IoU-based Optimization for Single-stage 3D Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09332\n- 代码/Code: https://github.com/hlsheng1/RDIoU\n\n**Densely Constrained Depth Estimator for Monocular 3D Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10047\n- 代码/Code: https://github.com/bravegroup/dcd\n\n**Robust Object Detection With Inaccurate Bounding Boxes**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09697\n- 代码/Code: https://github.com/cxliu0/OA-MIL\n\n**Unsupervised Domain Adaptation for One-stage Object Detector using Offsets to Bounding Box**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09656\n- 代码/Code: None\n\n**AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10316\n- 代码/Code: https://github.com/zehuichen123/autoalignv2\n\n**Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11169\n- 代码/Code: https://github.com/amazon-research/few-shot-object-detection-benchmark.\n\n**DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10758\n- 代码/Code: https://github.com/abhi1kumar/DEVIANT\n\n**Active Learning Strategies for Weakly-supervised Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12112\n- 代码/Code: https://github.com/huyvvo/BiB.\n\n**W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12104\n- 代码/Code: https://github.com/1170300714/w2n_wsod.\n\n**Salient Object Detection for Point Clouds**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11889\n- 代码/Code: None\n\n**UC-OWOD: Unknown-Classified Open World Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11455\n- 代码/Code: https://github.com/JohnWuzh/UC-OWOD\n\n**Monocular 3D Object Detection with Depth from Motion**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12988\n- 代码/Code: https://github.com/tai-wang/depth-from-motion\n\n**Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03062\n- 代码/Code: https://github.com/cuiziteng/ECCV_AERIS\n\n**Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03624\n- 代码/Code: https://github.com/Nightmare-n/GraphRCNN\n\n**Object Discovery via Contrastive Learning for Weakly Supervised Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.07576\n- 代码/Code: https://github.com/jinhseo/od-wscl\n\n**RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.08738\n- 代码/Code: https://github.com/chasel-tsui/mmdet-rfla\n\n**Object Detection in Aerial Images with Uncertainty-Aware Graph Network**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10781\n- 代码/Code: None\n\n**Adversarial Vulnerability of Temporal Feature Networks for Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10773\n- 代码/Code: None\n\n**Identifying Out-of-Distribution Samples in Real-Time for Safety-Critical 2D Object Detection with Margin Entropy Loss**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.00364\n- 代码/Code: None\n\n**CenterFormer: Center-based Transformer for 3D Object Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.05588\n- 代码/Code: https://github.com/tusimple/centerformer\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"ObjectTracking\"\u003e\u003c/a\u003e \n\n## 目标跟踪/Object Tracking\n\n**Tracking Objects as Pixel-wise Distributions**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05518\n- 代码/Code: None\n\n**Towards Grand Unification of Object Tracking**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07078\n- 代码/Code: https://github.com/masterbin-iiau/unicorn\n\n**The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Counting**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09295\n- 代码/Code: None\n\n**MOTCOM: The Multi-Object Tracking Dataset Complexity Metric**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10031\n- 代码/Code: None\n\n**Robust Landmark-based Stent Tracking in X-ray Fluoroscopy**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09933\n- 代码/Code: None\n\n**AiATrack: Attention in Attention for Transformer Visual Tracking**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09603\n- 代码/Code: https://github.com/Little-Podi/AiATrack\n\n**3D Siamese Transformer Network for Single Object Tracking on Point Clouds**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11995\n- 代码/Code: None\n\n**Tracking Every Thing in the Wild**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12978\n- 代码/Code: None\n\n**AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13784\n- 代码/Code: https://github.com/eth-siplab/AvatarPoser\n\n**Robust Multi-Object Tracking by Marginal Inference**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03727\n- 代码/Code: None\n\n**Towards Sequence-Level Training for Visual Tracking**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.05810\n- 代码/Code: https://github.com/byminji/SLTtrack\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"Segmentation\"\u003e\u003c/a\u003e \n\n## 语义分割/Segmentation\n\n**Domain Adaptive Video Segmentation via Temporal Pseudo Supervision**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.02372\n- 代码/Code: https://github.com/xing0047/tps\n\n**OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.02255\n- 代码/Code: https://github.com/pjlallen/osformer\n\n**PseudoClick: Interactive Image Segmentation with Click Imitation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05282\n- 代码/Code: None\n\n**XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07115\n- 代码/Code: https://github.com/hkchengrex/XMem\n\n**Tackling Background Distraction in Video Object Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06953\n- 代码/Code: https://github.com/suhwan-cho/tbd\n\n**Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08549\n- 代码/Code: None\n\n**Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08485\n- 代码/Code: https://github.com/NUST-Machine-Intelligence-Laboratory/HFAN\n\n**Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08455\n- 代码/Code: None\n\n**Learning Quality-aware Dynamic Memory for Video Object Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07922\n- 代码/Code: https://github.com/workforai/QDMN\n\n**Box-supervised Instance Segmentation with Level Set Evolution**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09055\n- 代码/Code: https://github.com/LiWentomng/boxlevelset\n\n**ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09045\n- 代码/Code: None\n\n**Self-Supervised Interactive Object Segmentation Through a Singulation-and-Grasping Approach**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09314\n- 代码/Code: None\n\n**DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09988\n- 代码/Code: https://github.com/dvlab-research/decouplenet\n\n**CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09778\n- 代码/Code: https://github.com/saltoricristiano/cosmix-uda\n\n**GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09763\n- 代码/Code: https://github.com/saltoricristiano/gipso-sfouda\n\n**Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10667\n- 代码/Code: https://github.com/theo2021/onda\n\n**In Defense of Online Models for Video Instance Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10661\n- 代码/Code: https://github.com/wjf5203/vnext\n\n**Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10436\n- 代码/Code: https://github.com/guoleisun/vss-mrcfa\n\n**Long-tailed Instance Segmentation using Gumbel Optimized Loss**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10936\n- 代码/Code: https://github.com/kostas1515/GOL\n\n**Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10892\n- 代码/Code: None\n\n**Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10866\n- 代码/Code: None\n\n**Self-Support Few-Shot Semantic Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11549\n- 代码/Code: https://github.com/fanq15/SSP\n\n**Active Pointly-Supervised Instance Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11493\n- 代码/Code: None\n\n**Video Mask Transfiner for High-Quality Video Instance Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.14012\n- 代码/Code: None\n\n**Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00306\n- 代码/Code: None\n\n**Per-Clip Video Object Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.01924\n- 代码/Code: https://github.com/pkyong95/PCVOS\n\n**Cluster-to-adapt: Few Shot Domain Adaptation for Semantic Segmentation across Disjoint Labels**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.02804\n- 代码/Code: None\n\n**Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03901\n- 代码/Code: None\n\n**Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03826\n- 代码/Code: https://github.com/owenzlz/EgoHOS\n\n**Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10169\n- 代码/Code: https://github.com/jayqine/mgd-ssss\n\n**Occlusion-Aware Instance Segmentation via BiLayer Network Architectures**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.04438\n- 代码/Code: https://github.com/lkeab/BCNet\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"VS\"\u003e\u003c/a\u003e \n\n## Video Segmentation\n\n**Video Mask Transfiner for High-Quality Video Instance Segmentation**\n\n- 论文/Paper: https://arxiv.org/abs/2207.14012\n- 代码/Code: https://github.com/SysCV/vmt\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"MIS\"\u003e\u003c/a\u003e \n\n## 医学图像分割/Medical Image Segmentation\n\n**Personalizing Federated Medical Image Segmentation via Local Calibration**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04655\n- 代码/Code: https://github.com/jcwang123/FedLC\n\n**Learning Topological Interactions for Multi-Class Medical Image Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09654\n- 代码/Code: https://github.com/topoxlab/topointeraction\n\n**qDWI-Morph: Motion-compensated quantitative Diffusion-Weighted MRI analysis for fetal lung maturity assessment**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09836\n- 代码/Code: https://github.com/TechnionComputationalMRILab/qDWI-Morph.\n\n**Self-Supervised Pretraining for 2D Medical Image Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.00314\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"KnowledgeDistillation\"\u003e\u003c/a\u003e \n\n## Knowledge Distillation\n\n**Knowledge Condensation Distillation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05409\n- 代码/Code: https://github.com/dzy3/KCD\n\n**FedX: Unsupervised Federated Learning with Cross Knowledge Distillation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09158\n- 代码/Code: https://github.com/sungwon-han/fedx\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"ActionDetection\"\u003e\u003c/a\u003e \n\n## Action Detection\n\n**ReAct: Temporal Action Detection with Relational Queries**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07097\n- 代码/Code: https://github.com/sssste/react\n\n**Semi-Supervised Temporal Action Detection with Proposal-Free Masking**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07059\n- 代码/Code: https://github.com/sauradip/SPOT\n\n**Temporal Action Detection with Global Segmentation Mask Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06580\n- 代码/Code: https://github.com/sauradip/TAGS\n\n**Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11805\n- 代码/Code: None\n\n**HaloAE: An HaloNet based Local Transformer Auto-Encoder for Anomaly Detection and Localization**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03486\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"ActionRecognition\"\u003e\u003c/a\u003e \n\n## Action Recognition\n\n**Compound Prototype Matching for Few-shot Action Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05515\n- 代码/Code: None\n\n**Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09767\n- 代码/Code: https://github.com/canbaoburen/CoDT\n\n**Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.01897\n- 代码/Code: None\n\n**PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.05775\n- 代码/Code: https://github.com/skelemoa/psumnet\n\n**Lane Change Classification and Prediction with Action Recognition Networks**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.11650\n- 代码/Code: None\n\n**Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.01425\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"AnomalyDetection\"\u003e\u003c/a\u003e \n\n## Anomaly Detection\n\n**Registration based Few-Shot Anomaly Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07361\n- 代码/Code: https://github.com/MediaBrain-SJTU/RegAD\n\n**Look at Adjacent Frames: Video Anomaly Detection without Offline Training**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13798\n- 代码/Code: None\n\n**Towards Open Set Video Anomaly Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.11113\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"FaceRecognition\"\u003e\u003c/a\u003e \n\n## 人脸识别/Face Recognition\n\n**Controllable and Guided Face Synthesis for Unconstrained Face Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10180\n- 代码/Code: None\n\n**Towards Robust Face Recognition with Comprehensive Search**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.13600\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"HumanPoseEstimation\"\u003e\u003c/a\u003e \n\n## 人体姿态估计/Human Pose Estimation\n\n**Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.02425\n- 代码/Code: None\n\n**Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05444\n- 代码/Code: https://github.com/JiehongLin/Self-DPDN\n\n**Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06101\n- 代码/Code: https://github.com/boeun-kim/gl-transformer\n\n**TransGrasp: Grasp Pose Estimation of a Category of Objects by Transferring Grasps from Only One Labeled Instance**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07861\n- 代码/Code: https://github.com/yanjh97/TransGrasp\n\n**Pose for Everything: Towards Category-Agnostic Pose Estimation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10387\n- 代码/Code: https://github.com/luminxu/Pose-for-Everything\n\n**C3P: Cross-domain Pose Prior Propagation for Weakly Supervised 3D Human Pose Estimation**\n\n- 论文/Paper: None\n- 代码/Code: https://github.com/wucunlin/C3P\n\n**3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11061\n- 代码/Code: https://github.com/MengHao666/HDR.\n\n**Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10955\n- 代码/Code: None\n\n**ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13691\n- 代码/Code: None\n\n**RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00237\n- 代码/Code: None\n\n**Neural Correspondence Field for Object Pose Estimation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00113\n- 代码/Code: None\n\n**Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00090\n- 代码/Code: None\n\n**CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00571\n- 代码/Code: https://github.com/huawei-noah/noah-research/tree/master/CLIFF\n\n**PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.07755\n- 代码/Code: None\n\n**Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09122\n- 代码/Code: None\n\n**Learning Visibility for Robust Dense Human Body Estimation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10652\n- 代码/Code: https://github.com/chhankyao/visdb\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"FaceAnti-Spoofing\"\u003e\u003c/a\u003e \n\n## 人脸活体检测/Face Anti-Spoofing\n\n**Generative Domain Adaptation for Face Anti-Spoofing**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10015\n- 代码/Code: None\n\n**Multi-domain Learning for Updating Face Anti-spoofing Models**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.11148\n- 代码/Code: None\n\n\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"FacialAttributeRecognition\"\u003e\u003c/a\u003e \n\n## 人脸属性识别/Facial Attribute Recognition\n\n**FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10888\n- 代码/Code: https://github.com/Bernardo1998/FairGRAPE\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"Face\"\u003e\u003c/a\u003e \n\n## 人脸相关 / Face\n\n**On Mitigating Hard Clusters for Face Clustering**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11895\n- 代码/Code: https://github.com/echoanran/On-Mitigating-Hard-Clusters.\n\n**Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11770\n- 代码/Code: None\n\n**Perspective Reconstruction of Human Faces by Joint Mesh and Landmark Regression**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.07142\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"3DReconstruction\"\u003e\u003c/a\u003e \n\n## 3D reconstruction\n\n**Latent Partition Implicit with Surface Codes for 3D Representation**\n\n- 论文/Paper: https://arxiv.org/abs/2207.08631\n- 代码/Code: https://github.com/chenchao15/LPI\n\n**LWA-HAND: Lightweight Attention Hand for Interacting Hand Reconstruction**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09815\n- 代码/Code: None\n\n**SimpleRecon: 3D Reconstruction Without 3D Convolutions**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.14743\n- 代码/Code: None\n\n\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"HumanReconstruction\"\u003e\u003c/a\u003e \n\n## Human Reconstruction\n\n**3D Clothed Human Reconstruction in the Wild**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10053\n- 代码/Code: https://github.com/hygenie1228/clothwild_release\n\n**UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09835\n- 代码/Code: https://github.com/ShenhanQian/UNIF\n\n**The One Where They Reconstructed 3D Humans and Environments in TV Shows**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.14279\n- 代码/Code: None\n\n**BCom-Net: Coarse-to-Fine 3D Textured Body Shape Completion Network**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.08768\n- 代码/Code: None\n\n**Neural Capture of Animatable 3D Human from Monocular Video**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.08728\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"Relighting\"\u003e\u003c/a\u003e \n\n## Relighting\n\n**Geometry-aware Single-image Full-body Human Relighting**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04750\n- 代码/Code: None\n\n**Relighting4D: Neural Relightable Human from Videos**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07104\n- 代码/Code: https://github.com/FrozenBurning/Relighting4D\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"DeepFake\"\u003e\u003c/a\u003e \n\n## DeepFake\n\n**Detecting and Recovering Sequential DeepFake Manipulation**\n\n- 论文/Paper: http://arxiv.org/abs/2207.02204\n- 代码/Code: https://github.com/rshaojimmy/seqdeepfake\n\n**An Efficient Method for Face Quality Assessment on the Edge**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09505\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"OCR\"\u003e\u003c/a\u003e\n\n## OCR\n\n**Character decomposition to resolve class imbalance problem in Hangul OCR**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.06079\n- 代码/Code: None\n\n**Shift Variance in Scene Text Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09231\n- 代码/Code: None\n\n**1st Place Solution to ECCV 2022 Challenge on Out of Vocabulary Scene Text Understanding: End-to-End Recognition of Out of Vocabulary Words**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.00224\n- 代码/Code: None\n\n**Levenshtein OCR**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.03594\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"TextRecognition\"\u003e\u003c/a\u003e\n\n## Text Recognition\n\n**Scene Text Recognition with Permuted Autoregressive Sequence Models**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06966\n- 代码/Code: https://github.com/baudm/parseq\n\n**Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06694\n- 代码/Code: https://github.com/hikopensource/davar-lab-ocr\n\n**Contextual Text Block Detection towards Scene Text Understanding**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12955\n- 代码/Code: None\n\n**GLASS: Global to Local Attention for Scene-Text Spotting**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03364\n- 代码/Code: None\n\n**Multi-Granularity Prediction for Scene Text Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.03592\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"PointCloud\"\u003e\u003c/a\u003e\n\n## 点云/Point Cloud\n\n**Open-world Semantic Segmentation for LIDAR Point Clouds**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.01452\n- 代码/Code: https://github.com/jun-cen/open_world_3d_semantic_segmentation\n\n**2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04397\n- 代码/Code: None\n\n**CPO: Change Robust Panorama to Point Cloud Localization**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05317\n- 代码/Code: None\n\n**diffConv: Analyzing Irregular Point Clouds with an Irregular View**\n\n- 论文/Paper: https://arxiv.org/abs/2111.14658\n- 代码/Code: https://github.com/mmmmimic/diffConvNet\n\n**CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08082\n- 代码/Code: None\n\n**Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09084\n- 代码/Code: None\n\n**SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10315\n- 代码/Code: https://github.com/hrzhou2/seedformer\n\n**Dynamic 3D Scene Analysis by Point Cloud Accumulation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12394\n- 代码/Code: None\n\n**3D Siamese Transformer Network for Single Object Tracking on Point Clouds**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11995\n- 代码/Code: None\n\n**Salient Object Detection for Point Clouds**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11889\n- 代码/Code: None\n\n**MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.14268\n- 代码/Code: https://github.com/MichaelRamamonjisoa/MonteBoxFinder\n\n**Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.14893\n- 代码/Code: https://github.com/514dna/llt\n\n**Learning to Generate Realistic LiDAR Point Clouds**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.03954\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\n\n\u003ca name=\"FlowEstimation\"\u003e\u003c/a\u003e\n\n## 光流估计/Flow Estimation\n\n**Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07522\n- 代码/Code: https://github.com/cwc1260/BiFlow\n\n**What Matters for 3D Scene Flow Network**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09143\n- 代码/Code: https://github.com/IRMVLab/3DFlow\n\n**Deep 360$^\\circ$ Optical Flow Estimation Based on Multi-Projection Fusion**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00776\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"DepthEstimation\"\u003e\u003c/a\u003e\n\n## 深度估计/Depth Estimation\n\n**Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04718\n- 代码/Code: None\n\n**Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04680\n- 代码/Code: https://github.com/SenZHANG-GitHub/ekf-imu-depth\n\n**RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11984\n- 代码/Code: None\n\n**Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimation**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.07088\n- 代码/Code: https://github.com/ZM-Zhou/SDFA-Net_pytorch\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"LaneDetection\"\u003e\u003c/a\u003e\n\n## 车道线检测/Lane Detection\n\n**RCLane: Relay Chain Prediction for Lane Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09399\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"TrajectoryPrediction\"\u003e\u003c/a\u003e\n\n## 轨迹预测/Trajectory Prediction\n\n**Action-based Contrastive Learning for Trajectory Prediction**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08664\n- 代码/Code: None\n\n**Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09953\n- 代码/Code: https://github.com/inhwanbae/gpgraph\n\n**Aware of the History: Trajectory Forecasting with the Local Behavior Data**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09646\n- 代码/Code: None\n\n**Human Trajectory Prediction via Neural Social Physics**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10435\n- 代码/Code: https://github.com/realcrane/human-trajectory-prediction-via-neural-social-physics\n\n**D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10398\n- 代码/Code: https://github.com/vtp-tl/d2-tpred\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"Super-Resolution\"\u003e\u003c/a\u003e\n\n## 超分/Super-Resolution\n\n**Image Super-Resolution with Deep Dictionary**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09228\n- 代码/Code: None\n\n**Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09156\n- 代码/Code: None\n\n**CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10345\n- 代码/Code: https://github.com/cheeun/cadyq\n\n**Towards Interpretable Video Super-Resolution via Alternating Optimization**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10765\n- 代码/Code: None\n\n**Reference-based Image Super-Resolution with Deformable Attention Transformer**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11938\n- 代码/Code: None\n\n**Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03012\n- 代码/Code: https://github.com/researchmm/FTVSR\n\n**HST: Hierarchical Swin Transformer for Compressed Image Super-resolution**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09885\n- 代码/Code: None\n\n**DSR: Towards Drone Image Super-Resolution**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.12327\n- 代码/Code: https://github.com/ivrl/dsr\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"ImageDenoising\"\u003e\u003c/a\u003e\n\n## 图像去噪/Image Denoising\n\n**Optimizing Image Compression via Joint Learning with Denoising**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10869\n- 代码/Code: https://github.com/felixcheng97/DenoiseCompression\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"ImageDeblurring\"\u003e\u003c/a\u003e\n\n## 图像去模糊/Image Deblurring\n\n**Spatio-Temporal Deformable Attention Network for Video Deblurring**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10852\n- 代码/Code: None\n\n**Efficient Video Deblurring Guided by Motion Magnitude**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13374\n- 代码/Code: None\n\n**Learning Degradation Representations for Image Deblurring**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.05244\n- 代码/Code: https://github.com/dasongli1/learning_degradation\n\n**Towards Real-World Video Deblurring by Exploring Blur Formation Process**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.13184\n- 代码/Code: None\n\n\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"ImageRestoration\"\u003e\u003c/a\u003e\n\n## 图像复原/Image Restoration\n\n**D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.03294\n- 代码/Code: https://github.com/zhaoyuzhi/D2HNet\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"ImageInpainting\"\u003e\u003c/a\u003e \n\n## 图像修复/Image Inpainting\n\n**Flow-Guided Transformer for Video Inpainting**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.06768\n- 代码/Code: https://github.com/hitachinsk/fgt\n\n**Unbiased Multi-Modality Guidance for Image Inpainting**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.11844\n- 代码/Code: https://github.com/yeates/MMT\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"ImageEnhancement\"\u003e\u003c/a\u003e \n\n## 图像增强/Image Enhancement\n\n**Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10564\n- 代码/Code: https://github.com/jinyeying/night-enhancement\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"VideoInterpolation\"\u003e\u003c/a\u003e \n\n## Video Interpolation\n\n**Video Interpolation by Event-driven Anisotropic Adjustment of Optical Flow**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09127\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"TemporalActionSegmentation\"\u003e\u003c/a\u003e \n\n## Temporal Action Segmentation\n\n**Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.00638\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"ImageRetrieval\"\u003e\u003c/a\u003e \n\n## 检索/Image Retrieval \n\n**Feature Representation Learning for Unsupervised Cross-domain Image Retrieval**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09721\n- 代码/Code: https://github.com/conghuihu/ucdir\n\n**A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03354\n- 代码/Code: None\n\n**CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09843\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"diffusion\"\u003e\u003c/a\u003e \n\n**Lossy Image Compression with Conditional Diffusion Models**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.06950\n- 代码/Code: None\n\n[返回目录/back](#Contents)\n\n\u003ca name=\"Other\"\u003e\u003c/a\u003e \n\n## 其他/Other\n\n**Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasets**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.01573\n- 代码/Code: None\n\n**GraphVid: It Only Takes a Few Nodes to Understand a Video**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.01375\n- 代码/Code: None\n\n**Target-absent Human Attention**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.01166\n- 代码/Code: None\n\n**Lottery Ticket Hypothesis for Spiking Neural Networks**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.01382\n- 代码/Code: None\n\n**Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality**\n\n- 论文/Paper: http://arxiv.org/abs/2207.02119\n- 代码/Code: https://github.com/kingjamessong/orthoimprovecond\n\n**AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture**\n\n- 论文/Paper: http://arxiv.org/abs/2207.02031\n- 代码/Code: https://github.com/lizhe00/AvatarCap.\n\n**DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images**\n\n- 论文/Paper: http://arxiv.org/abs/2207.02025\n- 代码/Code: None\n\n**Learning Local Implicit Fourier Representation for Image Warping**\n\n- 论文/Paper: http://arxiv.org/abs/2207.01831\n- 代码/Code: https://github.com/jaewon-lee-b/ltew\n\n**SESS: Saliency Enhancing with Scaling and Sliding**\n\n- 论文/Paper: http://arxiv.org/abs/2207.01769\n- 代码/Code: https://github.com/neouyghur/sess\n\n**TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts**\n\n- 论文/Paper: http://arxiv.org/abs/2207.01696\n- 代码/Code: None\n\n**DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.02606\n- 代码/Code: None\n\n**FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.02595\n- 代码/Code: https://github.com/timothyhtimothy/fast-vqa\n\n**Towards Realistic Semi-Supervised Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.02269\n- 代码/Code: None\n\n**OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.02261\n- 代码/Code: None\n\n**Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.02598\n- 代码/Code: None\n\n**Factorizing Knowledge in Neural Networks**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.03337\n- 代码/Code: None\n\n**SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.03677\n- 代码/Code: https://github.com/RICE-EIC/SuperTickets.\n\n**Video Dialog as Conversation about Objects Living in Space-Time**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.03656\n- 代码/Code: https://github.com/hoanganhpham1006/COST\n\n**Demystifying Unsupervised Semantic Correspondence Estimation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05054\n- 代码/Code: None\n\n**A Closer Look at Invariances in Self-supervised Pre-training for 3D Vision**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04997\n- 代码/Code: None\n\n**DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04788\n- 代码/Code: None\n\n**Batch-efficient EigenDecomposition for Small and Medium Matrices**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04228\n- 代码/Code: None\n\n**Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Space**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.04161\n- 代码/Code: None\n\n**Camera Pose Auto-Encoders for Improving Pose Regression**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05530\n- 代码/Code: https://github.com/yolish/camera-pose-auto-encoders\n\n**Synergistic Self-supervised and Quantization Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05432\n- 代码/Code: https://github.com/megvii-research/SSQL-ECCV2022\n\n**Frequency Domain Model Augmentation for Adversarial Attack**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.05382\n- 代码/Code: https://github.com/yuyang-long/ssa\n\n**Organic Priors in Non-Rigid Structure from Motion**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06262\n- 代码/Code: None\n\n**Unsupervised Visual Representation Learning by Synchronous Momentum Grouping**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06167\n- 代码/Code: None\n\n**Learning Implicit Templates for Point-Based Clothed Human Modeling**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06955\n- 代码/Code: https://github.com/jsnln/fite\n\n**BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06873\n- 代码/Code: https://github.com/explainableml/bayescap\n\n**Lipschitz Continuity Retained Binary Neural Network**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.06540\n- 代码/Code: https://github.com/42shawn/lcr_bnn\n\n**3D Instances as 1D Kernels**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07372\n- 代码/Code: https://github.com/W1zheng/DKNet\n\n**ScaleNet: Searching for the Model to Scale**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07267\n- 代码/Code: https://github.com/luminolx/ScaleNet\n\n**Rethinking Data Augmentation for Robust Visual Question Answering**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08739\n- 代码/Code: https://github.com/ItemZheng/KDDAug\n\n**Semantic Novelty Detection via Relational Reasoning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08699\n- 代码/Code: None\n\n**Label2Label: A Language Modeling Framework for Multi-Attribute Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08677\n- 代码/Code: https://github.com/Li-Wanhua/Label2Label.\n\n**Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08656\n- 代码/Code: https://github.com/UncleMEDM/InstPIFu\n\n**Class-incremental Novel Class Discovery**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08605\n- 代码/Code: https://github.com/OatmealLiu/class-iNCD\n\n**MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08403\n- 代码/Code: None\n\n**SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08351\n- 代码/Code: None\n\n**Learning with Recoverable Forgetting**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08224\n- 代码/Code: None\n\n**Zero-Shot Temporal Action Detection via Vision-Language Prompting**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08184\n- 代码/Code: https://github.com/sauradip/STALE\n\n**Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08178\n- 代码/Code: None\n\n**FashionViL: Fashion-Focused Vision-and-Language Representation Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08150\n- 代码/Code: https://github.com/BrandonHanx/mmf.\n\n**E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08132\n- 代码/Code: https://github.com/kyleleey/E-NeRV.\n\n**Neural Color Operators for Sequential Image Retouching**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08080\n- 代码/Code: https://github.com/amberwangyili/neurop\n\n**Semi-Supervised Keypoint Detector and Descriptor for Retinal Image Matching**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07932\n- 代码/Code: None\n\n**JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07895\n- 代码/Code: at~\\href{https://github.com/sunnyHelen/JPerceiver}{https://github.com/sunnyHelen/JPerceiver}.\n\n**You Should Look at All Objects**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07889\n- 代码/Code: None\n\n**NeFSAC: Neurally Filtered Minimal Samples**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07872\n- 代码/Code: https://github.com/cavalli1234/NeFSAC.\n\n**CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAS**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07868\n- 代码/Code: https://github.com/walkerning/aw_nas.\n\n**Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07826\n- 代码/Code: https://github.com/WentaoChen0813/CDCS-FSL\n\n**Self-calibrating Photometric Stereo by Neural Inverse Rendering**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07815\n- 代码/Code: https://github.com/junxuan-li/SCPS-NIR\n\n**Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.07783\n- 代码/Code: https://github.com/SRA2/SPELL\n\n**Towards Understanding The Semidefinite Relaxations of Truncated Least-Squares in Robust Rotation Search**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08350\n- 代码/Code: None\n\n**PoserNet: Refining Relative Camera Poses Exploiting Object Detections**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09445\n- 代码/Code: https://github.com/IIT-PAVIS/PoserNet\n\n**Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09425\n- 代码/Code: None\n\n**Deep Semantic Statistics Matching (D2SM) Denoising Network**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09302\n- 代码/Code: None\n\n**3D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transform**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09291\n- 代码/Code: https://github.com/Starrah/DMH-Net\n\n**NDF: Neural Deformable Fields for Dynamic Human Modelling**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09193\n- 代码/Code: None\n\n**Self-Supervision Can Be a Good Few-Shot Learner**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09176\n- 代码/Code: https://github.com/bbbdylan/unisiam\n\n**ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09137\n- 代码/Code: https://github.com/bytedance/particle-sfm.\n\n**MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09086\n- 代码/Code: None\n\n**SelectionConv: Convolutional Neural Networks for Non-rectilinear Image Data**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08979\n- 代码/Code: None\n\n**Prior-Guided Adversarial Initialization for Fast Adversarial Training**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08859\n- 代码/Code: https://github.com/jiaxiaojunQAQ/FGSM-PGI.\n\n**Prior Knowledge Guided Unsupervised Domain Adaptation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.08877\n- 代码/Code: https://github.com/tsun/KUDA\n\n**Discover and Mitigate Unknown Biases with Debiasing Alternate Networks**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10077\n- 代码/Code: https://github.com/zhihengli-UR/DebiAN\n\n**Difficulty-Aware Simulator for Open Set Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10024\n- 代码/Code: https://github.com/wjun0830/difficulty-aware-simulator\n\n**Tailoring Self-Supervision for Supervised Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10023\n- 代码/Code: https://github.com/wjun0830/localizable-rotation\n\n**Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10002\n- 代码/Code: https://github.com/boschresearch/sourcegen\n\n**Temporal and cross-modal attention for audio-visual zero-shot learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09966\n- 代码/Code: https://github.com/explainableml/tcaf-gzsl\n\n**Telepresence Video Quality Assessment**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09956\n- 代码/Code: None\n\n**Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09935\n- 代码/Code: None\n\n**Negative Samples are at Large: Leveraging Hard-distance Elastic Loss for Re-identification**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09884\n- 代码/Code: None\n\n**Discrete-Constrained Regression for Local Counting Models**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09865\n- 代码/Code: None\n\n**Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09705\n- 代码/Code: None\n\n**Efficient Meta-Tuning for Content-aware Neural Video Delivery**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09691\n- 代码/Code: https://github.com/neural-video-delivery/emt-pytorch-eccv2022\n\n**Object-Compositional Neural Implicit Surfaces**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09686\n- 代码/Code: https://github.com/qianyiwu/objsdf\n\n**Explaining Deepfake Detection by Analysing Image Matching**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09679\n- 代码/Code: https://github.com/megvii-research/fst-matching\n\n**ERA: Expert Retrieval and Assembly for Early Action Prediction**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09675\n- 代码/Code: None\n\n**Perspective Phase Angle Model for Polarimetric 3D Reconstruction**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09629\n- 代码/Code: https://github.com/gcchen97/ppa4p3d\n\n**Explicit Image Caption Editing**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09625\n- 代码/Code: https://github.com/baaaad/ece\n\n**Unsupervised Deep Multi-Shape Matching**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09610\n- 代码/Code: None\n\n**Contributions of Shape, Texture, and Color in Visual Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.09510\n- 代码/Code: https://github.com/gyhandy/humanoid-vision-engine\n\n**Novel Class Discovery without Forgetting**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10659\n- 代码/Code: None\n\n**Approximate Differentiable Rendering with Algebraic Surfaces**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10606\n- 代码/Code: None\n\n**FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10392\n- 代码/Code: None\n\n**Error Compensation Framework for Flow-Guided Video Inpainting**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10391\n- 代码/Code: None\n\n**NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10388\n- 代码/Code: None\n\n**Temporal Saliency Query Network for Efficient Video Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10379\n- 代码/Code: None\n\n**UFO: Unified Feature Optimization**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10341\n- 代码/Code: None\n\n**OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10320\n- 代码/Code: None\n\n**Towards Accurate Open-Set Recognition via Background-Class Regularization**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10287\n- 代码/Code: None\n\n**Grounding Visual Representations with Texts for Domain Generalization**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10285\n- 代码/Code: https://github.com/mswzeus/gvrt\n\n**SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10237\n- 代码/Code: https://github.com/apple/ml-spin\n\n**MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10228\n- 代码/Code: None\n\n**On Label Granularity and Object Localization**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10225\n- 代码/Code: https://github.com/visipedia/inat_loc\n\n**Spotting Temporally Precise, Fine-Grained Events in Video**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10213\n- 代码/Code: None\n\n**Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10172\n- 代码/Code: None\n\n**GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10158\n- 代码/Code: https://github.com/seleucia/goca\n\n**Visual Knowledge Tracing**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10157\n- 代码/Code: https://github.com/nkondapa/visualknowledgetracing\n\n**Tackling Long-Tailed Category Distribution Under Domain Shifts**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10150\n- 代码/Code: https://github.com/guxiao0822/lt-ds\n\n**Latent Discriminant deterministic Uncertainty**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10130\n- 代码/Code: https://github.com/ensta-u2is/ldu\n\n**Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10123\n- 代码/Code: https://github.com/zzh-tech/Animation-from-Blur.\n\n**Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10188\n- 代码/Code: None\n\n**Structural Causal 3D Reconstruction**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10156\n- 代码/Code: None\n\n**AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10141\n- 代码/Code: None\n\n**Continual Variational Autoencoder Learning via Online Cooperative Memorization**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10131\n- 代码/Code: https://github.com/dtuzi123/ovae\n\n**Panoptic Scene Graph Generation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11247\n- 代码/Code: https://github.com/Jingkang50/OpenPSG\n\n**Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11213\n- 代码/Code: None\n\n**POP: Mining POtential Performance of new fashion products via webly cross-modal query expansion**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11001\n- 代码/Code: https://github.com/HumaticsLAB/POP-Mining-POtential-Performance\n\n**Few-shot Object Counting and Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10988\n- 代码/Code: https://github.com/VinAIResearch/Counting-DETR\n\n**Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10948\n- 代码/Code: https://github.com/Beyond-Zw/DLAN-AC.\n\n**My View is the Best View: Procedure Learning from Egocentric Videos**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10883\n- 代码/Code: https://github.com/Sid2697/EgoProceL-egocentric-procedure-learning\n\n**Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10856\n- 代码/Code: https://github.com/Hongbin98/ProCA.git\n\n**MeshLoc: Mesh-Based Visual Localization**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.10762\n- 代码/Code: None\n\n**MemSAC: Memory Augmented Sample Consistency for Large Scale Domain Adaptation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12389\n- 代码/Code: None\n\n**Deforming Radiance Fields with Cages**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12298\n- 代码/Code: None\n\n**Equivariance and Invariance Inductive Bias for Learning from Insufficient Data**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12258\n- 代码/Code: https://github.com/Wangt-CN/EqInv\n\n**Black-box Few-shot Knowledge Distillation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12106\n- 代码/Code: https://github.com/nphdang/FS-BBT\n\n**Balancing Stability and Plasticity through Advanced Null Space in Continual Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12061\n- 代码/Code: None\n\n**Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11934\n- 代码/Code: None\n\n**NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11911\n- 代码/Code: None\n\n**Domain Adaptive Person Search**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11898\n- 代码/Code: https://github.com/caposerenity/DAPS.\n\n**VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairments**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11810\n- 代码/Code: None\n\n**Label-Guided Auxiliary Training Improves 3D Object Detector**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11753\n- 代码/Code: None\n\n**Combining Internal and External Constraints for Unrolling Shutter in Videos**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11725\n- 代码/Code: None\n\n**TIPS: Text-Induced Pose Synthesis**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11718\n- 代码/Code: None\n\n**Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11707\n- 代码/Code: None\n\n**Learning Graph Neural Networks for Image Style Transfer**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11681\n- 代码/Code: None\n\n**Contrastive Monotonic Pixel-Level Modulation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11517\n- 代码/Code: https://github.com/lukun199/MonoPix.\n\n**CompNVS: Novel View Synthesis with Scene Completion**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11467\n- 代码/Code: None\n\n**When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11463\n- 代码/Code: https://github.com/LBH1024/CAN.\n\n**Meta Spatio-Temporal Debiasing for Video Scene Graph Generation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.11441\n- 代码/Code: None\n\n**3D Shape Sequence of Human Comparison and Classification using Current and Varifolds**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12485\n- 代码/Code: https://github.com/cristal-3dsam/humancomparisonvarifolds\n\n**NewsStories: Illustrating articles with visual summaries**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13061\n- 代码/Code: https://github.com/newsstoriesdata/newsstories.github.io\n\n**Efficient One Pass Self-distillation with Zipf's Label Smoothing**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12980\n- 代码/Code: https://github.com/megvii-research/zipfls\n\n**AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12909\n- 代码/Code: None\n\n**Static and Dynamic Concepts for Self-supervised Video Representation Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12795\n- 代码/Code: None\n\n**Learning Hierarchy Aware Features for Reducing Mistake Severity**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12646\n- 代码/Code: https://github.com/07agarg/haf\n\n**Translating a Visual LEGO Manual to a Machine-Executable Plan**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12572\n- 代码/Code: None\n\n**Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12535\n- 代码/Code: https://github.com/xinleihe/semi-leak\n\n**Trainability Preserving Neural Structured Pruning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.12534\n- 代码/Code: https://github.com/mingsun-tse/tpp\n\n**Shift-tolerant Perceptual Similarity Metric**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13686\n- 代码/Code: http://github.com/abhijay9/ShiftTolerant-LPIPS/\n\n**Abstracting Sketches through Simple Primitives**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13543\n- 代码/Code: https://github.com/ExplainableML/sketch-primitives.\n\n**AutoTransition: Learning to Recommend Video Transition Effects**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13479\n- 代码/Code: https://github.com/acherstyx/AutoTransition\n\n**Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13417\n- 代码/Code: https://github.com/jiawangbai/HPT\n\n**Identifying Hard Noise in Long-Tailed Sample Distribution**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13378\n- 代码/Code: https://github.com/yxymessi/H2E-Framework\n\n**One-Trimap Video Matting**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13353\n- 代码/Code: https://github.com/Hongje/OTVM\n\n**PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13340\n- 代码/Code: None\n\n**End-to-end Graph-constrained Vectorized Floorplan Generation with Panoptic Refinement**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13268\n- 代码/Code: None\n\n**Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13259\n- 代码/Code: https://github.com/MartinXM/TPS\n\n**Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13247\n- 代码/Code: None\n\n**LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13129\n- 代码/Code: None\n\n**Initialization and Alignment for Adversarial Texture Optimization**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.14289\n- 代码/Code: None\n\n**Depth Field Networks for Generalizable Multi-view Scene Representation**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.14287\n- 代码/Code: None\n\n**Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.14192\n- 代码/Code: https://github.com/enlighten0707/Body-Part-Map-for-Interactiveness.\n\n**Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.14067\n- 代码/Code: None\n\n**Break and Make: Interactive Structural Understanding Using LEGO Bricks**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13738\n- 代码/Code: https://github.com/aaronwalsman/ltron.\n\n**A Repulsive Force Unit for Garment Collision Handling in Neural Networks**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.13871\n- 代码/Code: None\n\n**Minimal Neural Atlas: Parameterizing Complex Surfaces with Minimal Charts and Distortion**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.14782\n- 代码/Code: https://github.com/low5545/minimal-neural-atlas\n\n**Can Shuffling Video Benefit Temporal Bias Problem: A Novel Training Framework for Temporal Grounding**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.14698\n- 代码/Code: https://github.com/haojc/ShufflingVideosForTSG.\n\n**AlphaVC: High-Performance and Efficient Learned Video Compression**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.14678\n- 代码/Code: None\n\n**WISE: Whitebox Image Stylization by Example-based Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.14606\n- 代码/Code: None\n\n**Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels**\n\n- 论文/Paper: http://arxiv.org/pdf/2207.14476\n- 代码/Code: None\n\n**Video Question Answering with Iterative Video-Text Co-Tokenization**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00934\n- 代码/Code: None\n\n**S$^2$Contact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00874\n- 代码/Code: None\n\n**Skeleton-free Pose Transfer for Stylized 3D Characters**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00790\n- 代码/Code: None\n\n**Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00617\n- 代码/Code: https://github.com/GANPerf/SAM\n\n**SdAE: Self-distillated Masked Autoencoder**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00449\n- 代码/Code: https://github.com/AbrahamYabo/SdAE.\n\n**Out-of-Distribution Detection with Semantic Mismatch under Masking**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00446\n- 代码/Code: https://github.com/cure-lab/MOODCat\n\n**Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00368\n- 代码/Code: None\n\n**Revisiting the Critical Factors of Augmentation-Invariant Representation Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00275\n- 代码/Code: None\n\n**Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00183\n- 代码/Code: None\n\n**Few-Shot Class-Incremental Learning from an Open-Set Perspective**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00147\n- 代码/Code: None\n\n**DAS: Densely-Anchored Sampling for Deep Metric Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00119\n- 代码/Code: https://github.com/lizhaoliu-Lec/DAS\n\n**Fast Two-step Blind Optical Aberration Correction**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.00950\n- 代码/Code: None\n\n**Negative Frames Matter in Egocentric Visual Query 2D Localization**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.01949\n- 代码/Code: https://github.com/facebookresearch/vq2d_cvpr\n\n**Neighborhood Collective Estimation for Noisy Label Identification and Correction**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03207\n- 代码/Code: None\n\n**PlaneFormers: From Sparse View Planes to 3D Reconstruction**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.04307\n- 代码/Code: None\n\n**SLiDE: Self-supervised LiDAR De-snowing through Reconstruction Difficulty**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.04043\n- 代码/Code: None\n\n**Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03792\n- 代码/Code: https://github.com/PKU-EPIC/DREDS\n\n**Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03767\n- 代码/Code: None\n\n**Learning Omnidirectional Flow in 360-degree Video via Siamese Representation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03620\n- 代码/Code: None\n\n**Inpainting at Modern Camera Resolution by Guided PatchMatch with Auto-Curation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03552\n- 代码/Code: None\n\n**Contrastive Positive Mining for Unsupervised 3D Action Representation Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.03497\n- 代码/Code: None\n\n**Speaker-adaptive Lip Reading with User-dependent Padding**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.04498\n- 代码/Code: None\n\n**Contrast-Phys: Unsupervised Video-based Remote Physiological Measurement via Spatiotemporal Contrast**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.04378\n- 代码/Code: https://github.com/zhaodongsun/contrast-phys\n\n**Rethinking Robust Representation Learning Under Fine-grained Noisy Faces**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.04352\n- 代码/Code: None\n\n**RDA: Reciprocal Distribution Alignment for Robust SSL**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.04619\n- 代码/Code: https://github.com/njuyued/rda4robustssl\n\n**RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.05963\n- 代码/Code: None\n\n**PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.05962\n- 代码/Code: https://github.com/immortalco/pointtree\n\n**MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.05768\n- 代码/Code: https://github.com/winycg/self-kd-lib\n\n**PRIF: Primary Ray-based Implicit Function**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.06143\n- 代码/Code: None\n\n**Learning Semantic Correspondence with Sparse Annotations**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.06974\n- 代码/Code: None\n\n**CCRL: Contrastive Cell Representation Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.06445\n- 代码/Code: None\n\n**Pose Forecasting in Industrial Human-Robot Collaboration**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.07308\n- 代码/Code: None\n\n**Combating Label Distribution Shift for Active Domain Adaptation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.06604\n- 代码/Code: None\n\n**Matching Multiple Perspectives for Efficient Representation Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.07654\n- 代码/Code: None\n\n**Uncertainty-guided Source-free Domain Adaptation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.07591\n- 代码/Code: https://github.com/roysubhankar/uncertainty-sfda\n\n**Context-Aware Streaming Perception in Dynamic Environments**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.07479\n- 代码/Code: https://github.com/eyalsel/contextual-streaming-perception\n\n**Towards an Error-free Deep Occupancy Detector for Smart Camera Parking System**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.08220\n- 代码/Code: None\n\n**AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.08084\n- 代码/Code: None\n\n**DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.08112\n- 代码/Code: None\n\n**L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.08711\n- 代码/Code: https://github.com/snu-arc/l3\n\n**ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.08631\n- 代码/Code: https://github.com/jiwoncocoder/conmatch\n\n**Unifying Visual Perception by Dispersible Points Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.08630\n- 代码/Code: https://github.com/sense-x/unihead\n\n**Visual Cross-View Metric Localization with Dense Uncertainty Estimates**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.08519\n- 代码/Code: https://github.com/tudelft-iv/crossviewmetriclocalization\n\n**GCISG: Guided Causal Invariant Learning for Improved Syn-to-real Generalization**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10024\n- 代码/Code: None\n\n**SIM2E: Benchmarking the Group Equivariant Capability of Correspondence Matching Algorithms**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09896\n- 代码/Code: None\n\n**Artifact-Based Domain Generalization of Skin Lesion Models**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09756\n- 代码/Code: None\n\n**Fuse and Attend: Generalized Embedding Learning for Art and Sketches**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09698\n- 代码/Code: None\n\n**Effectiveness of Function Matching in Driving Scene Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.09694\n- 代码/Code: None\n\n**Consistency Regularization for Domain Adaptation**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.11084\n- 代码/Code: https://github.com/kw01sg/crda\n\n**IMPaSh: A Novel Domain-shift Resistant Representation for Colorectal Cancer Tissue Classification**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.11052\n- 代码/Code: https://github.com/trinhvg/impash\n\n**Deep Structural Causal Shape Models**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10950\n- 代码/Code: None\n\n**Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10683\n- 代码/Code: None\n\n**Anatomy-Aware Contrastive Representation Learning for Fetal Ultrasound**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10642\n- 代码/Code: None\n\n**The Value of Out-of-Distribution Data**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10967\n- 代码/Code: None\n\n**Ultra-high-resolution unpaired stain transformation via Kernelized Instance Normalization**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10730\n- 代码/Code: https://github.com/kaminyou/urust\n\n**RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.10608\n- 代码/Code: https://github.com/huyvnphan/eccv2022-ribac\n\n**Cross-Camera View-Overlap Recognition**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.11661\n- 代码/Code: None\n\n**On the Design of Privacy-Aware Cameras: a Study on Deep Neural Networks**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.11372\n- 代码/Code: https://github.com/upciti/privacy-by-design-semseg\n\n**Discovering Transferable Forensic Features for CNN-generated Images Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.11342\n- 代码/Code: None\n\n**Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.11168\n- 代码/Code: https://github.com/andreagemelli/doc2graph\n\n**Learning Continuous Implicit Representation for Near-Periodic Patterns**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.12278\n- 代码/Code: None\n\n**NeuralSI: Structural Parameter Identification in Nonlinear Dynamical Systems**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.12771\n- 代码/Code: https://github.com/human-analysis/neural-structural-identification\n\n**Take One Gram of Neural Features, Get Enhanced Group Robustness**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.12625\n- 代码/Code: None\n\n**CIRCLe: Color Invariant Representation Learning for Unbiased Classification of Skin Lesions**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.13528\n- 代码/Code: None\n\n**ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.14201\n- 代码/Code: None\n\n**Probing Contextual Diversity for Dense Out-of-Distribution Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.14195\n- 代码/Code: None\n\n**CAIR: Fast and Lightweight Multi-Scale Color Attention Network for Instagram Filter Removal**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.14039\n- 代码/Code: https://github.com/hnv-lab/cair\n\n**FUSION: Fully Unsupervised Test-Time Stain Adaptation via Fused Normalization Statistics**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.14206\n- 代码/Code: None\n\n**Style-Agnostic Reinforcement Learning**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.14863\n- 代码/Code: https://github.com/postech-cvlab/style-agnostic-rl\n\n**LiteDepth: Digging into Fast and Accurate Depth Estimation on Mobile Devices**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.00961\n- 代码/Code: https://github.com/zhyever/LiteDepth\n\n**Unpaired Image Translation via Vector Symbolic Architectures**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.02686\n- 代码/Code: None\n\n**CNSNet: A Cleanness-Navigated-Shadow Network for Shadow Removal**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.02174\n- 代码/Code: None\n\n**Semi-Supervised Domain Adaptation by Similarity based Pseudo-label Injection**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.01881\n- 代码/Code: None\n\n**Recurrent Bilinear Optimization for Binary Neural Networks**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.01542\n- 代码/Code: https://github.com/SteveTsui/RBONN\n\n**Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.01501\n- 代码/Code: None\n\n**Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.01404\n- 代码/Code: https://github.com/Sense-GVT/BCDN\n\n**Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.02869\n- 代码/Code: https://github.com/Alii-Ganjj/InterpretationsSteeredPruning\n\n**Exploring Anchor-based Detection for Ego4D Natural Language Query**\n\n- 论文/Paper: http://arxiv.org/pdf/2208.05375\n- 代码/Code: None\n\n**Detecting Driver Drowsiness as an Anomaly Using LSTM Autoencoders**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.05269\n- 代码/Code: None\n\n**Switchable Online Knowledge Distillation**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.04996\n- 代码/Code: https://github.com/hfutqian/SwitOKD\n\n**Self-supervised Human Mesh Recovery with Cross-Representation Alignment**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.04596\n- 代码/Code: None\n\n**Check and Link: Pairwise Lesion Correspondence Guides Mammogram Mass Detection**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.05809\n- 代码/Code: None\n\n**PointScatter: Point Set Representation for Tubular Structure Extraction**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.05774\n- 代码/Code: https://github.com/zhangzhao2022/pointscatter\n\n**Adversarial Coreset Selection for Efficient Robust Training**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.05785\n- 代码/Code: None\n\n**Out-of-Vocabulary Challenge Report**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.06717\n- 代码/Code: None\n\n**DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction**\n\n- 论文/Paper: http://arxiv.org/pdf/2209.06351\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdwctod%2Feccv2022-papers-with-code-demo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdwctod%2Feccv2022-papers-with-code-demo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdwctod%2Feccv2022-papers-with-code-demo/lists"}