{"id":19320152,"url":"https://github.com/52cv/wacv-2022-papers","last_synced_at":"2026-03-05T14:04:41.604Z","repository":{"id":43018923,"uuid":"445029498","full_name":"52CV/WACV-2022-Papers","owner":"52CV","description":null,"archived":false,"fork":false,"pushed_at":"2022-04-11T05:50:14.000Z","size":363,"stargazers_count":38,"open_issues_count":0,"forks_count":11,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-02-24T05:14:35.340Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/52CV.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":"2022-01-06T03:36:37.000Z","updated_at":"2023-12-23T14:34:25.000Z","dependencies_parsed_at":"2022-08-22T07:00:49.988Z","dependency_job_id":null,"html_url":"https://github.com/52CV/WACV-2022-Papers","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/52CV/WACV-2022-Papers","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/52CV%2FWACV-2022-Papers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/52CV%2FWACV-2022-Papers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/52CV%2FWACV-2022-Papers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/52CV%2FWACV-2022-Papers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/52CV","download_url":"https://codeload.github.com/52CV/WACV-2022-Papers/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/52CV%2FWACV-2022-Papers/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30130031,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-05T12:40:50.676Z","status":"ssl_error","status_checked_at":"2026-03-05T12:39:32.209Z","response_time":93,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 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":[],"created_at":"2024-11-10T01:27:19.203Z","updated_at":"2026-03-05T14:04:41.577Z","avatar_url":"https://github.com/52CV.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# 52CV-WACV-Papers\n\n## 历年综述论文分类汇总戳这里↘️[CV-Surveys](https://github.com/52CV/CV-Surveys)施工中~~~~~~~~~~\n\n## 2022 年论文分类汇总戳这里\n↘️[CVPR-2022-Papers](https://github.com/52CV/CVPR-2022-Papers)\n↘️[WACV-2022-Papers](https://github.com/52CV/WACV-2022-Papers)\n\n## 2021年论文分类汇总戳这里\n↘️[ICCV-2021-Papers](https://github.com/52CV/ICCV-2021-Papers)\n↘️[CVPR-2021-Papers](https://github.com/52CV/CVPR-2021-Papers)\n\n## 2020 年论文分类汇总戳这里\n↘️[CVPR-2020-Papers](https://github.com/52CV/CVPR-2020-Papers)\n↘️[ECCV-2020-Papers](https://github.com/52CV/ECCV-2020-Papers)\n\n# :exclamation::exclamation::exclamation::star2::star2::star2:📗📗📗WACV 2022收录论文已全部公布，下载可在【我爱计算机视觉】后台回复“paper”，即可收到。共计 406 篇。\n\n# :exclamation::exclamation::exclamation::star2::star2::star2:分类完成\n# 目录\n\n|:dog:|:mouse:|:hamster:|:tiger:|\n|---------|---------|---------|---------|\n|[53.Gaze Estimation(视线估计)](#53)|[54.Optical Flow(光流)](#54)|[55.Object Counting(物体计数)](#55)|\n|[49.Debiasing(去偏见)](#49)|[50.Sign Language Translation(手语翻译)](#50)|[51.SSC(语义场景完成)](#51)|[52.Eye Tracking(眼动跟踪)](#52)|\n|[45.Class-Incremental Learning(类增量学习)](#45)|[46.Metric Learning(度量学习)](#46)|[47.Data Augmentation(数据增强)](#47)|[48.Light Fields(光场)](#48)|\n|[41.Action Generation(动作生成)](#41)|[42.Landmark Detection(关键点检测)](#42)|[43.Active Learning(主动学习)](#43)|[44.Multi-Task Learning(多任务学习)](#44)|\n|[37.OT(目标跟踪)](#37)|[38.Sound(音频处理)](#38)|[39.Style Transfer(风格迁移)](#39)|[40.AD(异常检测)](#40)|\n|[33.View Synthesis(视图合成)](#33)|[34.SLAM\\Robots](#34)|[35.VQA(视觉问答)](#35)|[36.Soft Biometrics(软生物技术)](#36)|\n|[29.Image Classification(图像分类)](#29)|[30.RL(强化学习)](#30)|[31.Deepfake Detection(假象检测)](#31)|[32.Continual Learning(持续学习)](#32)|\n|[25.Image Captioning(图像字幕)](#25)|[26.Dataset(数据集)](#26)|[27.Defect Detection(缺陷检测)](#27)|[28.OPE(物体姿态估计)](#28)|\n|[21.PC(点云)](#21)|[22.HAR(人体动作识别与检测)](#22)|[23.AD(智能驾驶)](#23)|[24.Image Retrieval(图像检索)](#24)|\n|[17.OCR(文本检测)](#17)|[18.NAS(神经架构搜索)](#18)|[19.MC\\KD\\Pruning(模型压缩\\知识蒸馏\\剪枝)](#19)|[20.Transformer](#20)|\n|[13.Image Segmentation(图像分割)](#13)|[14.SSL(半监督学习)](#14)|[15.Image Synthesis(图像合成)](#15)|[16.SR(超分辨率)](#16)|\n|[9.RS\\Satellite Image(遥感\\卫星图像)](#9)|[10.AL(对抗学习)](#10)|[11.Face(人脸)](#11)|[12.FSL or DA\\G(小样本学习 or 域适应\\泛化)](#12)|\n|[5.OD(目标检测)](#5)|[6.Video(视频相关)](#6)|[7.Pose(人体姿态)](#7)|[8.Image Processing(图像处理)](#8)|\n|[1.其它](#1)|[2.Medical Image(医学影像)](#2)|[3.3D(三维视觉)](#3)|[4.GAN(生成对抗网络)](#4)|\n\n\n\u003ca name=\"55\"/\u003e\n\n## 55.Object Counting(物体计数)\n* [Single Image Object Counting and Localizing Using Active-Learning](https://openaccess.thecvf.com/content/WACV2022/papers/Huberman-Spiegelglas_Single_Image_Object_Counting_and_Localizing_Using_Active-Learning_WACV_2022_paper.pdf)\n\n\u003ca name=\"54\"/\u003e\n\n## 54.Optical Flow(光流)\n* [Detail Preserving Residual Feature Pyramid Modules for Optical Flow](https://arxiv.org/abs/2107.10990)\n\n\u003ca name=\"53\"/\u003e\n\n## 53.Gaze Estimation(视线估计)\n* [MTGLS: Multi-Task Gaze Estimation With Limited Supervision](https://arxiv.org/abs/2110.12100)\n\n\u003ca name=\"52\"/\u003e\n\n## 52.Eye Tracking(眼动跟踪)\n* [Event-Based Kilohertz Eye Tracking Using Coded Differential Lighting](https://openaccess.thecvf.com/content/WACV2022/papers/Stoffregen_Event-Based_Kilohertz_Eye_Tracking_Using_Coded_Differential_Lighting_WACV_2022_paper.pdf)\n\n\u003ca name=\"51\"/\u003e\n\n## 51.Semantic Scene Completion(语义场景完成SSC)\n* [Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priors](https://arxiv.org/abs/2111.13309)\n\n\u003ca name=\"50\"/\u003e\n\n## 50.Sign Language Translation(手语翻译)\n* [Sign Language Translation With Hierarchical Spatio-Temporal Graph Neural Network](https://openaccess.thecvf.com/content/WACV2022/papers/Kan_Sign_Language_Translation_With_Hierarchical_Spatio-Temporal_Graph_Neural_Network_WACV_2022_paper.pdf)\n\n\u003ca name=\"49\"/\u003e\n\n## 49.Debiasing(去偏见)\n* [An Investigation of Critical Issues in Bias Mitigation Techniques](https://arxiv.org/abs/2104.00170)\u003cbr\u003e:star:[code](https://github.com/erobic/bias-mitigators)\n\n\u003ca name=\"48\"/\u003e\n\n## 48.Light Fields(光场)\n* [Fast and Efficient Restoration of Extremely Dark Light Fields](https://openaccess.thecvf.com/content/WACV2022/papers/Lamba_Fast_and_Efficient_Restoration_of_Extremely_Dark_Light_Fields_WACV_2022_paper.pdf)\n* 相机校准\n  * [Modeling dynamic target deformation in camera calibration](https://arxiv.org/abs/2110.07322)\n* Camera Pose Estimation(相机姿势估计)\n  * [A Structure-Aware Method for Direct Pose Estimation](https://arxiv.org/abs/2012.12360)\u003cbr\u003e:star:[code](https://github.com/mvrl/structure-aware-pose-estimation)\n\n\u003ca name=\"47\"/\u003e\n\n## 47.Data Augmentation(数据增强)\n* [Meta Approach to Data Augmentation Optimization](https://arxiv.org/abs/2006.07965)\n* [Improving Model Generalization by Agreement of Learned Representations From Data Augmentation](https://arxiv.org/abs/2110.10536)\u003cbr\u003e:star:[code](https://github.com/roatienza/agmax)\n\n\u003ca name=\"46\"/\u003e\n\n## 46.Metric Learning(度量学习)\n* [Multi-Head Deep Metric Learning Using Global and Local Representations](https://arxiv.org/abs/2112.14327)\n* [Hierarchical Proxy-Based Loss for Deep Metric Learning](https://arxiv.org/abs/2103.13538)\n\n\u003ca name=\"45\"/\u003e\n\n## 45.Class-Incremental Learning(类增量学习)\n* [Dataset Knowledge Transfer for Class-Incremental Learning without Memory](https://arxiv.org/abs/2110.08421)\u003cbr\u003e:star:[code](https://github.com/HabibSlim/DKT-for-CIL)\n\n\u003ca name=\"44\"/\u003e\n\n## 44.Multi-Task Learning(多任务学习)\n* [Joint Classification and Trajectory Regression of Online Handwriting Using a Multi-Task Learning Approach](https://openaccess.thecvf.com/content/WACV2022/papers/Ott_Joint_Classification_and_Trajectory_Regression_of_Online_Handwriting_Using_a_WACV_2022_paper.pdf)\n* [Semi-Supervised Multi-Task Learning for Semantics and Depth](https://arxiv.org/abs/2110.07197)\n\n\u003ca name=\"43\"/\u003e\n\n## 43.Active Learning(主动学习)\n* [Identifying Wrongly Predicted Samples: A Method for Active Learning](https://arxiv.org/abs/2010.06890)\n\n\u003ca name=\"42\"/\u003e\n\n## 42.Landmark Detection(关键点检测)\n* [LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity](https://openaccess.thecvf.com/content/WACV2022/papers/Karmali_LEAD_Self-Supervised_Landmark_Estimation_by_Aligning_Distributions_of_Feature_Similarity_WACV_2022_paper.pdf)\n* 人体关键点检测\n  * [Registration of Human Point Set Using Automatic Key Point Detection and Region-Aware Features](https://openaccess.thecvf.com/content/WACV2022/papers/Maharjan_Registration_of_Human_Point_Set_Using_Automatic_Key_Point_Detection_WACV_2022_paper.pdf)\n\n\u003ca name=\"41\"/\u003e\n\n## 41.Action Generation(动作生成)\n* [MUGL: Large Scale Multi Person Conditional Action Generation with Locomotion](https://arxiv.org/abs/2110.11460)\u003cbr\u003e:star:[code](https://github.com/skelemoa/mugl):house:[project](https://skeleton.iiit.ac.in/mugl)\n* 基于姿势引导的动作合成\n  * [Pose-Guided Generative Adversarial Net for Novel View Action Synthesis](https://arxiv.org/abs/2110.07993)\u003cbr\u003e:star:[code](https://github.com/xhl-video/PAS-GAN)\n\n\u003ca name=\"40\"/\u003e\n\n## 40.Anomaly Detection(异常检测)\n* [CFLOW-AD: Real-Time Unsupervised Anomaly Detection With Localization via Conditional Normalizing Flows](https://openaccess.thecvf.com/content/WACV2022/papers/Gudovskiy_CFLOW-AD_Real-Time_Unsupervised_Anomaly_Detection_With_Localization_via_Conditional_Normalizing_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/gudovskiy/cflow-ad)\n* [A Semi-Supervised Generalized VAE Framework for Abnormality Detection Using One-Class Classification](https://openaccess.thecvf.com/content/WACV2022/papers/Sharma_A_Semi-Supervised_Generalized_VAE_Framework_for_Abnormality_Detection_Using_One-Class_WACV_2022_paper.pdf)\n* novelty detection(奇异值检测)\n  * [OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detection](https://arxiv.org/abs/2103.14953)\u003cbr\u003e:star:[code](https://github.com/jewelltaylor/OLED)\n\n\u003ca name=\"39\"/\u003e\n\n## 39.Style Transfer(风格迁移)\n* [PhotoWCT2: Compact Autoencoder for Photorealistic Style Transfer Resulting From Blockwise Training and Skip Connections of High-Frequency Residuals](https://openaccess.thecvf.com/content/WACV2022/papers/Chiu_PhotoWCT2_Compact_Autoencoder_for_Photorealistic_Style_Transfer_Resulting_From_Blockwise_WACV_2022_paper.pdf)\n* 3D场景风格化\n  * [Stylizing 3D Scene via Implicit Representation and HyperNetwork](https://arxiv.org/abs/2105.13016)\u003cbr\u003e:star:[code](https://github.com/ztex08010518/Stylizing-3D-Scene):house:[project](https://ztex08010518.github.io/3dstyletransfer/)\n\n\u003ca name=\"38\"/\u003e\n\n## 38.Sound(音频处理)\n* [Beyond Mono to Binaural: Generating Binaural Audio From Mono Audio With Depth and Cross Modal Attention](https://arxiv.org/abs/2111.08046)\u003cbr\u003e:house:[project](https://krantiparida.github.io/projects/bmonobinaural.html)\n* 声源定位\n  * [Unsupervised Sounding Object Localization With Bottom-Up and Top-Down Attention](https://openaccess.thecvf.com/content/WACV2022/papers/Shi_Unsupervised_Sounding_Object_Localization_With_Bottom-Up_and_Top-Down_Attention_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/VISION-SJTU/USOL)\n  * [Less Can Be More: Sound Source Localization With a Classification Model](https://openaccess.thecvf.com/content/WACV2022/papers/Senocak_Less_Can_Be_More_Sound_Source_Localization_With_a_Classification_WACV_2022_paper.pdf)\n* 声源分离\n  * [Visually Guided Sound Source Separation and Localization Using Self-Supervised Motion Representations](https://arxiv.org/abs/2104.08506)\u003cbr\u003e:house:[project](https://ly-zhu.github.io/self-supervised-motion-representations)\n  * [V-SlowFast Network for Efficient Visual Sound Separation](https://openaccess.thecvf.com/content/WACV2022/papers/Zhu_V-SlowFast_Network_for_Efficient_Visual_Sound_Separation_WACV_2022_paper.pdf)\u003cbr\u003e:house:[project](https://ly-zhu.github.io/V-SlowFast)\n\n\u003ca name=\"37\"/\u003e\n\n## 37.Object Tracking(目标跟踪)\n* [Intelligent Camera Selection Decisions for Target Tracking in a Camera Network](https://openaccess.thecvf.com/content/WACV2022/papers/Sharma_Intelligent_Camera_Selection_Decisions_for_Target_Tracking_in_a_Camera_WACV_2022_paper.pdf)\n* 多目标跟踪\n  * [Compensation Tracker: Reprocessing Lost Object for Multi-Object Tracking](https://openaccess.thecvf.com/content/WACV2022/papers/Zou_Compensation_Tracker_Reprocessing_Lost_Object_for_Multi-Object_Tracking_WACV_2022_paper.pdf)\n  * 细胞跟踪\n    * [Consistent Cell Tracking in Multi-Frames With Spatio-Temporal Context by Object-Level Warping Loss](https://openaccess.thecvf.com/content/WACV2022/papers/Hayashida_Consistent_Cell_Tracking_in_Multi-Frames_With_Spatio-Temporal_Context_by_Object-Level_WACV_2022_paper.pdf)\n\n\u003ca name=\"36\"/\u003e\n\n## 36.Soft Biometrics(软生物技术)\n* Periocular(眼周) 识别\n  * [Attribute-Based Deep Periocular Recognition: Leveraging Soft Biometrics to Improve Periocular Recognition](https://arxiv.org/abs/2111.01325)\n\n\u003ca name=\"35\"/\u003e\n\n## 35.VQA(视觉问答)\n* [InfographicVQA](https://arxiv.org/abs/2104.12756)\u003cbr\u003e:star:[code](https://docvqa.org/)\n* [Efficient Counterfactual Debiasing for Visual Question Answering](https://openaccess.thecvf.com/content/WACV2022/papers/Kolling_Efficient_Counterfactual_Debiasing_for_Visual_Question_Answering_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/hengyuan-hu/bottom-up-attention-vqa)\n* Audio video scene-aware dialog(视听场景感知对话)\n  * [QUALIFIER: Question-Guided Self-Attentive Multimodal Fusion Network for Audio Visual Scene-Aware Dialog](https://openaccess.thecvf.com/content/WACV2022/papers/Ye_QUALIFIER_Question-Guided_Self-Attentive_Multimodal_Fusion_Network_for_Audio_Visual_Scene-Aware_WACV_2022_paper.pdf)\n\n\u003ca name=\"34\"/\u003e\n\n## 34.SLAM\\Robots\n* SLAM\n  * [HybVIO: Pushing the Limits of Real-time Visual-inertial Odometry](https://arxiv.org/abs/2106.11857)\u003cbr\u003e:star:[code](https://github.com/SpectacularAI/HybVIO)\n  * [SIGNAV: Semantically-Informed GPS-Denied Navigation and Mapping in Visually-Degraded Environments](https://openaccess.thecvf.com/content/WACV2022/papers/Krasner_SIGNAV_Semantically-Informed_GPS-Denied_Navigation_and_Mapping_in_Visually-Degraded_Environments_WACV_2022_paper.pdf)\n* Try-On\n  * [C-VTON: Context-Driven Image-Based Virtual Try-On Network](https://openaccess.thecvf.com/content/WACV2022/papers/Fele_C-VTON_Context-Driven_Image-Based_Virtual_Try-On_Network_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/benquick123/C-VTON)\n  * 3D虚拟试穿\n    * [Robust 3D Garment Digitization From Monocular 2D Images for 3D Virtual Try-On Systems](https://arxiv.org/abs/2111.15140)\n  * 时尚属性编辑\n    * [Tailor Me: An Editing Network for Fashion Attribute Shape Manipulation](https://openaccess.thecvf.com/content/WACV2022/papers/Kwon_Tailor_Me_An_Editing_Network_for_Fashion_Attribute_Shape_Manipulation_WACV_2022_paper.pdf)\n* Robots\n  * 视觉导航\n    * [Self-Supervised Domain Adaptation for Visual Navigation with Global Map Consistency](https://arxiv.org/abs/2110.07184)\n    * [ForeSI: Success-Aware Visual Navigation Agent](https://openaccess.thecvf.com/content/WACV2022/papers/Moghaddam_ForeSI_Success-Aware_Visual_Navigation_Agent_WACV_2022_paper.pdf)\n\n\u003ca name=\"33\"/\u003e\n\n## 33.View Synthesis(视图合成)\n* [Revealing Disocclusions in Temporal View Synthesis Through Infilling Vector Prediction](https://arxiv.org/abs/2110.08805)\u003cbr\u003e:star:[code](https://github.com/NagabhushanSN95/IVP):house:[project](https://nagabhushansn95.github.io/publications/2021/ivp.html):tv:[video](https://youtu.be/7IYXKOqP2TA)\n* [Fast and Explicit Neural View Synthesis](https://arxiv.org/abs/2107.05775)\n* [Novel-View Synthesis of Human Tourist Photos](https://openaccess.thecvf.com/content/WACV2022/papers/Freer_Novel-View_Synthesis_of_Human_Tourist_Photos_WACV_2022_paper.pdf)\n\n\u003ca name=\"32\"/\u003e\n\n## 32.Continual Learning(持续学习)\n* [Knowledge Capture and Replay for Continual Learning](https://arxiv.org/abs/2012.06789)\n* [Online Continual Learning via Candidates Voting](https://arxiv.org/abs/2110.08855)\n\n\u003ca name=\"31\"/\u003e\n\n## 31.Deepfake Detection(假象检测)\n* [BiHPF: Bilateral High-Pass Filters for Robust Deepfake Detection](https://arxiv.org/abs/2109.00911)\u003cbr\u003e:star:[code](https://github.com/SamsungSDS-Team9/BiHPF)\n\n\u003ca name=\"30\"/\u003e\n\n## 30.Reinforcement Learning(强化学习)\n* [RLSS: A Deep Reinforcement Learning Algorithm for Sequential Scene Generation](https://openaccess.thecvf.com/content/WACV2022/papers/Ostonov_RLSS_A_Deep_Reinforcement_Learning_Algorithm_for_Sequential_Scene_Generation_WACV_2022_paper.pdf)\n\n\u003ca name=\"29\"/\u003e\n\n## 29.Image Classification(图像分类)\n* [Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactuals](https://arxiv.org/abs/2009.08270)\n* [Class-Balanced Active Learning for Image Classification](https://arxiv.org/abs/2110.04543)\u003cbr\u003e:star:[code](https://github.com/Javadzb/Class-Balanced-AL)\n* [Learnable Adaptive Cosine Estimator (LACE) for Image Classification](https://arxiv.org/abs/2110.05324)\u003cbr\u003e:star:[code](https://github.com/GatorSense/LACE)\n* [Enhancing Few-Shot Image Classification With Unlabelled Examples](https://arxiv.org/abs/2006.12245)\u003cbr\u003e:star:[code](https://github.com/plai-group/simple-cnaps)\n* 零样本分类\n  * [Trading-Off Information Modalities in Zero-Shot Classification](https://openaccess.thecvf.com/content/WACV2022/papers/Sanchez_Trading-Off_Information_Modalities_in_Zero-Shot_Classification_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/jadrs/zsl)\n* 小样本分类\n  * [Meta-Learning for Multi-Label Few-Shot Classification](https://arxiv.org/abs/2110.13494)\n* 细粒度识别\n  * [3DRefTransformer: Fine-Grained Object Identification in Real-World Scenes Using Natural Language](https://openaccess.thecvf.com/content/WACV2022/papers/Abdelreheem_3DRefTransformer_Fine-Grained_Object_Identification_in_Real-World_Scenes_Using_Natural_Language_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/Vision-CAIR/3dreftransformer):house:[project](https://vision-cair.github.io/3dreftransformer/)\n\n\u003ca name=\"28\"/\u003e\n\n## 28.Pose Estimation(姿态估计)\n* 物品姿势估计\n  * [Occlusion-Robust Object Pose Estimation with Holistic Representation](https://arxiv.org/abs/2110.11636)\u003cbr\u003e:star:[code](https://github.com/BoChenYS/ROPE)\n* Object Pose Refinement\n  * [SporeAgent: Reinforced Scene-Level Plausibility for Object Pose Refinement](https://openaccess.thecvf.com/content/WACV2022/papers/Bauer_SporeAgent_Reinforced_Scene-Level_Plausibility_for_Object_Pose_Refinement_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/dornik/sporeagent)\n* 动物姿势\n  * [Equine Pain Behavior Classification via Self-Supervised Disentangled Pose Representation](https://openaccess.thecvf.com/content/WACV2022/papers/Rashid_Equine_Pain_Behavior_Classification_via_Self-Supervised_Disentangled_Pose_Representation_WACV_2022_paper.pdf)\n\n\u003ca name=\"27\"/\u003e\n\n## 27.Defect Detection(缺陷检测)\n* [Fully Convolutional Cross-Scale-Flows for Image-Based Defect Detection](https://arxiv.org/abs/2110.02855)\u003cbr\u003e:star:[code](https://github.com/marco-rudolph/cs-flow)\n* [Automated Defect Inspection in Reverse Engineering of Integrated Circuits](https://openaccess.thecvf.com/content/WACV2022/papers/Bette_Automated_Defect_Inspection_in_Reverse_Engineering_of_Integrated_Circuits_WACV_2022_paper.pdf)\n* 下水道缺陷分类\n  * [Multi-Task Classification of Sewer Pipe Defects and Properties using a Cross-Task Graph Neural Network Decoder](https://arxiv.org/abs/2111.07846)\u003cbr\u003e:star:[code](https://bitbucket.org/aauvap/ctgnn/src/master/):house:[project](https://vap.aau.dk/ctgnn/)\n\n\u003ca name=\"26\"/\u003e\n\n## 26.Dataset\\Benchmark(数据集\\基准)\n* [MovingFashion: A Benchmark for the Video-To-Shop Challenge](https://arxiv.org/abs/2110.02627)\u003cbr\u003e:sunflower:[dataset](https://github.com/HumaticsLAB/SEAM-Match-RCNN)\n* [Challenges in Procedural Multimodal Machine Comprehension: A Novel Way To Benchmark](https://arxiv.org/abs/2110.11899)\n* 用于检测跟踪海域人类\n  * [SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water](https://arxiv.org/abs/2105.01922)\u003cbr\u003e:sunflower:[dataset](https://seadronessee.cs.uni-tuebingen.de/)\n* 图像识别\n  * [Danish Fungi 2020 - Not Just Another Image Recognition Dataset](https://openaccess.thecvf.com/content/WACV2022/papers/Picek_Danish_Fungi_2020_-_Not_Just_Another_Image_Recognition_Dataset_WACV_2022_paper.pdf)\u003cbr\u003e:sunflower:[dataset](https://sites.google.com/view/danish-fungi-dataset)\n* 自动驾驶\n  * [DG-Labeler and DGL-MOTS Dataset: Boost the Autonomous Driving Perception](https://arxiv.org/abs/2110.07790)\u003cbr\u003e:house:[project](https://goodproj13.github.io/DGL-MOTS/):tv:[video](https://youtu.be/5WVB8_TqMKQ)\n* 用于从高空鱼眼相机中检测和跟踪行人\n  * [WEPDTOF: A Dataset and Benchmark Algorithms for In-the-Wild People Detection and Tracking From Overhead Fisheye Cameras](https://openaccess.thecvf.com/content/WACV2022/papers/Tezcan_WEPDTOF_A_Dataset_and_Benchmark_Algorithms_for_In-the-Wild_People_Detection_WACV_2022_paper.pdf)\n\n\u003ca name=\"25\"/\u003e\n\n## 25.Image Captioning(图像字幕)\n* [Is an Image Worth Five Sentences? A New Look Into Semantics for Image-Text Matching](https://openaccess.thecvf.com/content/WACV2022/papers/Biten_Is_an_Image_Worth_Five_Sentences_A_New_Look_Into_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/furkanbiten/ncs_metric):star:[code](https://github.com/andrespmd/semantic_adaptive_margin)\n* [Let There Be a Clock on the Beach: Reducing Object Hallucination in Image Captioning](https://openaccess.thecvf.com/content/WACV2022/papers/Biten_Let_There_Be_a_Clock_on_the_Beach_Reducing_Object_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/furkanbiten/object-bias)\n* [Improve Image Captioning by Estimating the Gazing Patterns From the Caption](https://openaccess.thecvf.com/content/WACV2022/papers/Alahmadi_Improve_Image_Captioning_by_Estimating_the_Gazing_Patterns_From_the_WACV_2022_paper.pdf)\n\n\u003ca name=\"24\"/\u003e\n\n## 24.Image Retrieval(图像检索)\n* [All the Attention You Need: Global-Local, Spatial-Channel Attention for Image Retrieval](https://arxiv.org/abs/2107.08000)\n* [Learning With Label Noise for Image Retrieval by Selecting Interactions](https://arxiv.org/abs/2112.10453)\n* [SAC: Semantic Attention Composition for Text-Conditioned Image Retrieval](https://arxiv.org/abs/2009.01485)\n* Image-Text retrieval\n  * [GraDual: Graph-Based Dual-Modal Representation for Image-Text Matching](https://openaccess.thecvf.com/content/WACV2022/papers/Long_GraDual_Graph-Based_Dual-Modal_Representation_for_Image-Text_Matching_WACV_2022_paper.pdf)\n* 图像搜索\n  * [Generating and Controlling Diversity in Image Search](https://openaccess.thecvf.com/content/WACV2022/papers/Tanjim_Generating_and_Controlling_Diversity_in_Image_Search_WACV_2022_paper.pdf)\n* 视频文本匹配\n  * [Video and Text Matching With Conditioned Embeddings](https://arxiv.org/abs/2110.11298)\u003cbr\u003e:star:[code](https://github.com/AmeenAli/VideoMatch)\n* 绘图检索\n  * [DeepPatent: Large scale patent drawing recognition and retrieval](https://openaccess.thecvf.com/content/WACV2022/papers/Kucer_DeepPatent_Large_Scale_Patent_Drawing_Recognition_and_Retrieval_WACV_2022_paper.pdf)\n* 视频检索\n  * [Masking Modalities for Cross-Modal Video Retrieval](https://arxiv.org/abs/2111.01300)\n\n\u003ca name=\"23\"/\u003e\n\n## 23.Autonomous Driving(智能驾驶)\n* 自动驾驶\n  * [Multi-View Fusion of Sensor Data for Improved Perception and Prediction in Autonomous Driving](https://arxiv.org/abs/2008.11901)\n  * 目标检测\n    * [Adversarial Robustness of Deep Sensor Fusion Models](https://arxiv.org/abs/2006.13192)\n* 车辆定位\n  * [CoordiNet: Uncertainty-Aware Pose Regressor for Reliable Vehicle Localization](https://arxiv.org/abs/2103.10796)\n* Vehicle Detection(交通检测)\n  * 基于航空图像的交通监控\n    * [AirCamRTM: Enhancing Vehicle Detection for Efficient Aerial Camera-Based Road Traffic Monitoring](https://openaccess.thecvf.com/content/WACV2022/papers/Makrigiorgis_AirCamRTM_Enhancing_Vehicle_Detection_for_Efficient_Aerial_Camera-Based_Road_Traffic_WACV_2022_paper.pdf)\n* Lane Detection(车道线检测)\n  * [Robust Lane Detection via Expanded Self Attention](https://arxiv.org/abs/2102.07037)\n\n\n\u003ca name=\"22\"/\u003e\n\n## 22.Human Action Recognition(人体动作识别与检测)\n* [NUTA: Non-Uniform Temporal Aggregation for Action Recognition](https://arxiv.org/abs/2012.08041)\n* [MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition](https://openaccess.thecvf.com/content/WACV2022/papers/Chen_MM-ViT_Multi-Modal_Video_Transformer_for_Compressed_Video_Action_Recognition_WACV_2022_paper.pdf)\n* [Dual-Head Contrastive Domain Adaptation for Video Action Recognition](https://openaccess.thecvf.com/content/WACV2022/papers/da_Costa_Dual-Head_Contrastive_Domain_Adaptation_for_Video_Action_Recognition_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/vturrisi/CO2A)\n* [Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition](https://openaccess.thecvf.com/content/WACV2022/papers/Memmesheimer_Skeleton-DML_Deep_Metric_Learning_for_Skeleton-Based_One-Shot_Action_Recognition_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/raphaelmemmesheimer/skeleton-dml)\n* [SWAG-V: Explanations for Video Using Superpixels Weighted by Average Gradients](https://openaccess.thecvf.com/content/WACV2022/papers/Hartley_SWAG-V_Explanations_for_Video_Using_Superpixels_Weighted_by_Average_Gradients_WACV_2022_paper.pdf)\n* [Pose and Joint-Aware Action Recognition](https://arxiv.org/abs/2010.08164)\u003cbr\u003e:star:[code](https://github.com/anshulbshah/PoseAction)\n* [Domain Generalization Through Audio-Visual Relative Norm Alignment in First Person Action Recognition](https://arxiv.org/abs/2110.10101)\n* 3D动作识别\n  * [How and What To Learn: Taxonomizing Self-Supervised Learning for 3D Action Recognition](https://openaccess.thecvf.com/content/WACV2022/papers/Tanfous_How_and_What_To_Learn_Taxonomizing_Self-Supervised_Learning_for_3D_WACV_2022_paper.pdf)(https://github.com/serre-lab/ssl_actionrec)\n* 动作定位\n  * [Towards Active Vision for Action Localization With Reactive Control and Predictive Learning](https://arxiv.org/abs/2111.05448)\n  * [Contextual Proposal Network for Action Localization](https://openaccess.thecvf.com/content/WACV2022/papers/Hsieh_Contextual_Proposal_Network_for_Action_Localization_WACV_2022_paper.pdf)\n* 时序动作分割\n  * [SSCAP: Self-Supervised Co-Occurrence Action Parsing for Unsupervised Temporal Action Segmentation](https://arxiv.org/abs/2105.14158)\n  * [Leaky Gated Cross-Attention for Weakly Supervised Multi-Modal Temporal Action Localization](https://openaccess.thecvf.com/content/WACV2022/papers/Lee_Leaky_Gated_Cross-Attention_for_Weakly_Supervised_Multi-Modal_Temporal_Action_Localization_WACV_2022_paper.pdf)\n\n\u003ca name=\"21\"/\u003e\n\n## 21.Point Cloud(点云)\n* [Surrogate Model-Based Explainability Methods for Point Cloud NNs](https://arxiv.org/abs/2107.13459)\u003cbr\u003e:star:[code](https://github.com/Explain3D/LIME-3D)\n* [StickyLocalization: Robust End-to-End Relocalization on Point Clouds Using Graph Neural Networks](https://openaccess.thecvf.com/content/WACV2022/papers/Fischer_StickyLocalization_Robust_End-to-End_Relocalization_on_Point_Clouds_Using_Graph_Neural_WACV_2022_paper.pdf)\n* 3D 点云\n  * [Spatial-Temporal Transformer for 3D Point Cloud Sequences](https://arxiv.org/abs/2110.09783)\n  * [Biomass Prediction With 3D Point Clouds From LiDAR](https://openaccess.thecvf.com/content/WACV2022/papers/Pan_Biomass_Prediction_With_3D_Point_Clouds_From_LiDAR_WACV_2022_paper.pdf)\n  * 3D点云目标分类\n    * [What Makes for Effective Few-Shot Point Cloud Classification?](https://openaccess.thecvf.com/content/WACV2022/papers/Ye_What_Makes_for_Effective_Few-Shot_Point_Cloud_Classification_WACV_2022_paper.pdf)\n* 分类与分割\n  * [EllipsoidNet: Ellipsoid Representation for Point Cloud Classification and Segmentation](https://arxiv.org/abs/2103.02517)\n\n\u003ca name=\"20\"/\u003e\n\n## 20.Transformer\n* [Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations](https://arxiv.org/abs/2108.05887)\n* [Visualizing Paired Image Similarity in Transformer Networks](https://openaccess.thecvf.com/content/WACV2022/papers/Black_Visualizing_Paired_Image_Similarity_in_Transformer_Networks_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/vidarlab/xformer-paired-viz)\n* [S2-MLP: Spatial-Shift MLP Architecture for Vision](https://openaccess.thecvf.com/content/WACV2022/papers/Yu_S2-MLP_Spatial-Shift_MLP_Architecture_for_Vision_WACV_2022_paper.pdf)\n* 图像分类\n  * [Resource-Efficient Hybrid X-Formers for Vision](https://openaccess.thecvf.com/content/WACV2022/papers/Jeevan_Resource-Efficient_Hybrid_X-Formers_for_Vision_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/pranavphoenix/VisionXformer)\n* 图像超级补全\n  * [Image-Adaptive Hint Generation via Vision Transformer for Outpainting](https://openaccess.thecvf.com/content/WACV2022/papers/Kong_Image-Adaptive_Hint_Generation_via_Vision_Transformer_for_Outpainting_WACV_2022_paper.pdf)\n\n\u003ca name=\"19\"/\u003e\n\n## 19.Model Compression\\Knowledge Distillation\\Pruning(模型压缩\\知识蒸馏\\剪枝)\n* 模型压缩\n  * [Model Compression Using Optimal Transport](https://arxiv.org/abs/2012.03907)\n* 知识蒸馏\n  * [Extractive Knowledge Distillation](https://openaccess.thecvf.com/content/WACV2022/papers/Kobayashi_Extractive_Knowledge_Distillation_WACV_2022_paper.pdf)\n  * [Self-Guidance: Improve Deep Neural Network Generalization via Knowledge Distillation](https://openaccess.thecvf.com/content/WACV2022/papers/Zheng_Self-Guidance_Improve_Deep_Neural_Network_Generalization_via_Knowledge_Distillation_WACV_2022_paper.pdf)\n  * [Online Knowledge Distillation by Temporal-Spatial Boosting](https://openaccess.thecvf.com/content/WACV2022/papers/Li_Online_Knowledge_Distillation_by_Temporal-Spatial_Boosting_WACV_2022_paper.pdf)\n  * [Preventing Catastrophic Forgetting and Distribution Mismatch in Knowledge Distillation via Synthetic Data](https://arxiv.org/abs/2108.05698)\n* 剪枝\n  * [Hessian-Aware Pruning and Optimal Neural Implant](http://arxiv.org/abs/2101.08940)\u003cbr\u003e:star:[code](https://github.com/yaozhewei/HAP)\n  * [Channel Pruning via Lookahead Search Guided Reinforcement Learning](https://openaccess.thecvf.com/content/WACV2022/papers/Wang_Channel_Pruning_via_Lookahead_Search_Guided_Reinforcement_Learning_WACV_2022_paper.pdf)\n  * [EZCrop: Energy-Zoned Channels for Robust Output Pruning](https://arxiv.org/abs/2105.03679)\u003cbr\u003e:star:[code](https://github.com/ruilin0212/EZCrop)\n\n\u003ca name=\"18\"/\u003e\n\n## 18.NAS(神经架构搜索)\n* [Approximate Neural Architecture Search via Operation Distribution Learning](https://openaccess.thecvf.com/content/WACV2022/papers/Wan_Approximate_Neural_Architecture_Search_via_Operation_Distribution_Learning_WACV_2022_paper.pdf)\n* [Neural Architecture Search for Efficient Uncalibrated Deep Photometric Stereo](https://arxiv.org/abs/2110.05621)\n* [Towards a Robust Differentiable Architecture Search Under Label Noise](https://arxiv.org/abs/2110.12197)\n* [Lightweight Monocular Depth With a Novel Neural Architecture Search Method](https://arxiv.org/abs/2108.11105)\n* [Progressive Automatic Design of Search Space for One-Shot Neural Architecture Search](https://arxiv.org/abs/2005.07564)\n\n\u003ca name=\"17\"/\u003e\n\n## 17.OCR(文本检测)\n* [Post-OCR Paragraph Recognition by Graph Convolutional Networks](https://arxiv.org/abs/2101.12741)\n* 不规则场景文本识别\n  * [Robustly Recognizing Irregular Scene Text by Rectifying Principle Irregularities](https://openaccess.thecvf.com/content/WACV2022/papers/Xu_Robustly_Recognizing_Irregular_Scene_Text_by_Rectifying_Principle_Irregularities_WACV_2022_paper.pdf)\n* LOGO识别\n  * [SeeTek: Very Large-Scale Open-Set Logo Recognition With Text-Aware Metric Learning](https://openaccess.thecvf.com/content/WACV2022/papers/Li_SeeTek_Very_Large-Scale_Open-Set_Logo_Recognition_With_Text-Aware_Metric_Learning_WACV_2022_paper.pdf)\n* 手写文本识别\n  * [One-Shot Compositional Data Generation for Low Resource Handwritten Text Recognition](https://arxiv.org/abs/2105.05300)\n* 表格结构识别\n  * [Visual Understanding of Complex Table Structures from Document Images](https://arxiv.org/abs/2111.07129)\n\n\u003ca name=\"16\"/\u003e\n\n## 16.Super-Resolution(超分辨率)\n* [Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-Resolution](https://arxiv.org/abs/2111.03649)\u003cbr\u003e:star:[code](https://github.com/andreas128/AdFlow?1)\n* [Multi-Dimensional Dynamic Model Compression for Efficient Image Super-Resolution](https://openaccess.thecvf.com/content/WACV2022/papers/Hou_Multi-Dimensional_Dynamic_Model_Compression_for_Efficient_Image_Super-Resolution_WACV_2022_paper.pdf)\n* [edge-SR: Super-Resolution for the Masses](https://openaccess.thecvf.com/content/WACV2022/papers/Michelini_edge-SR_Super-Resolution_for_the_Masses_WACV_2022_paper.pdf)\n* [DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks](https://arxiv.org/abs/2012.11230)\n* [Hyperspectral Image Super-Resolution With RGB Image Super-Resolution as an Auxiliary Task](https://openaccess.thecvf.com/content/WACV2022/papers/Li_Hyperspectral_Image_Super-Resolution_With_RGB_Image_Super-Resolution_as_an_Auxiliary_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/kli8996/HSISR)\n* VSR\n  * [MEGAN: Memory Enhanced Graph Attention Network for Space-Time Video Super-Resolution](https://arxiv.org/abs/2110.15327)\n* BSR\n  * [MoESR: Blind Super-Resolution Using Kernel-Aware Mixture of Experts](https://openaccess.thecvf.com/content/WACV2022/papers/Emad_MoESR_Blind_Super-Resolution_Using_Kernel-Aware_Mixture_of_Experts_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/memad73/MoESR)\n\n\u003ca name=\"15\"/\u003e\n\n## 15.Image Synthesis(图像合成)\n* 图像生成\n  * [StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulation](https://arxiv.org/abs/2112.08493)\u003cbr\u003e:star:[code](https://github.com/catlab-team/stylemc):house:[project](https://catlab-team.github.io/stylemc/):tv:[video](https://youtu.be/ILm_5tvtzPI)\n* sketch-to-photo\n  * [Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis](https://arxiv.org/abs/2104.05703)\u003cbr\u003e:star:[code](https://github.com/Mukosame/AODA)\n* Image-to-Image Translation\n  * [Evaluation of Correctness in Unsupervised Many-to-Many Image Translation](https://arxiv.org/abs/2103.15727)\u003cbr\u003e:star:[code](https://github.com/dbash/umi2i_correctness)\n\n\u003ca name=\"14\"/\u003e\n\n## 14.Un\\Self\\Semi-Supervised Learning(无\\自\\半监督学习)\n* 半监督\n  * [HierMatch: Leveraging Label Hierarchies for Improving Semi-Supervised Learning](https://arxiv.org/abs/2111.00164)\u003cbr\u003e:star:[code](https://github.com/07Agarg/HIERMATCH)\n* 自监督\n  * [Boosting Contrastive Self-Supervised Learning with False Negative Cancellation](https://arxiv.org/abs/2011.11765)\u003cbr\u003e:star:[code](https://github.com/google-research/fnc)\n  * [Self-Supervised Shape Alignment for Sports Field Registration](https://openaccess.thecvf.com/content/WACV2022/papers/Shi_Self-Supervised_Shape_Alignment_for_Sports_Field_Registration_WACV_2022_paper.pdf)\n* 无监督\n  * [Unsupervised Learning for Human Sensing Using Radio Signals](https://openaccess.thecvf.com/content/WACV2022/papers/Li_Unsupervised_Learning_for_Human_Sensing_Using_Radio_Signals_WACV_2022_paper.pdf)\n\n\u003ca name=\"13\"/\u003e\n\n## 13.Image Segmentation(图像分割)\n* [Semantically Stealthy Adversarial Attacks Against Segmentation Models](https://arxiv.org/abs/2104.01732)\n* 视频分割\n  * [D2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos](https://openaccess.thecvf.com/content/WACV2022/papers/Schmidt_D2Conv3D_Dynamic_Dilated_Convolutions_for_Object_Segmentation_in_Videos_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/Schmiddo/d2conv3d)\n  * [Perceptual Consistency in Video Segmentation](https://arxiv.org/abs/2110.12385)\n  * [Temporally Stable Video Segmentation Without Video Annotations](https://arxiv.org/abs/2110.08893)\n* VOS(视频目标分割)\n  * [Pixel-Level Bijective Matching for Video Object Segmentation](https://arxiv.org/abs/2110.01644)\u003cbr\u003e:star:[code](https://github.com/suhwan-cho/BMVOS)\n* 动作分割\n  * [Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos](https://arxiv.org/abs/2110.05697)\u003cbr\u003e:star:[code](https://github.com/rezaghoddoosian/Hierarchical-Task-Modeling)\n* 语义分割\n  * [Plugging Self-Supervised Monocular Depth Into Unsupervised Domain Adaptation for Semantic Segmentation](https://arxiv.org/abs/2110.06685)\u003cbr\u003e:star:[code](https://github.com/CVLAB-Unibo/d4-dbst)\n  * [Adversarial Semantic Hallucination for Domain Generalized Semantic Segmentation](https://arxiv.org/abs/2106.04144)\u003cbr\u003e:star:[code](https://github.com/gabriel-tjio/ASH)\n  * [Shallow Features Guide Unsupervised Domain Adaptation for Semantic Segmentation at Class Boundaries](https://arxiv.org/abs/2110.02833)\u003cbr\u003e:star:[code](https://github.com/CVLAB-Unibo/Shallow_DA)\n  * [Evaluating the Robustness of Semantic Segmentation for Autonomous Driving Against Real-World Adversarial Patch Attacks](https://arxiv.org/abs/2108.06179)\n  * [Multi-Domain Incremental Learning for Semantic Segmentation](https://arxiv.org/abs/2110.12205)\u003cbr\u003e:star:[code](https://github.com/prachigarg23/MDIL-SS)\n  * [Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images](https://arxiv.org/abs/2110.07782)\u003cbr\u003e:star:[code](https://github.com/immuno121/ALS4GAN)\n  * [Multi-Domain Semantic Segmentation With Overlapping Labels](https://openaccess.thecvf.com/content/WACV2022/papers/Bevandic_Multi-Domain_Semantic_Segmentation_With_Overlapping_Labels_WACV_2022_paper.pdf)\n  * [Mixed-Dual-Head Meets Box Priors: A Robust Framework for Semi-Supervised Segmentation](https://openaccess.thecvf.com/content/WACV2022/papers/Chen_Mixed-Dual-Head_Meets_Box_Priors_A_Robust_Framework_for_Semi-Supervised_Segmentation_WACV_2022_paper.pdf)\n  * 视频语义分割\n    * [AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation](https://arxiv.org/abs/2110.12369)\n  * 弱监督语义分割\n    * [Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentation](https://arxiv.org/abs/2110.14309)\u003cbr\u003e:star:[code](https://github.com/weixuansun/InferCam)\n  * 无监督语义分割\n    * [Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation](https://arxiv.org/abs/2102.13002)\n  * 半监督语义分割\n    * [Semi-Supervised Semantic Segmentation of Vessel Images Using Leaking Perturbations](https://arxiv.org/abs/2110.11998)\n  * 小样本语义分割\n    * [Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation](https://arxiv.org/abs/2110.11650)\u003cbr\u003e:star:[code](https://github.com/taveraantonio/PixDA)\n    * [A Pixel-Level Meta-Learner for Weakly Supervised Few-Shot Semantic Segmentation](https://arxiv.org/abs/2111.01418)\n    * [MaskSplit: Self-Supervised Meta-Learning for Few-Shot Semantic Segmentation](https://arxiv.org/abs/2110.12207)\n* 实例分割\n  * [In-Field Phenotyping Based on Crop Leaf and Plant Instance Segmentation](https://openaccess.thecvf.com/content/WACV2022/papers/Weyler_In-Field_Phenotyping_Based_on_Crop_Leaf_and_Plant_Instance_Segmentation_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/PRBonn/leaf-plant-instance-segmentation)\n  * [FASSST: Fast Attention Based Single-Stage Segmentation Net for Real-Time Instance Segmentation](https://openaccess.thecvf.com/content/WACV2022/papers/Cheng_FASSST_Fast_Attention_Based_Single-Stage_Segmentation_Net_for_Real-Time_Instance_WACV_2022_paper.pdf)\n* 全景分割\n  * [Single-Shot Path Integrated Panoptic Segmentation](https://arxiv.org/abs/2012.01632)\n  * 视频全景分割\n    * [Time-Space Transformers for Video Panoptic Segmentation](https://openaccess.thecvf.com/content/WACV2022/papers/Petrovai_Time-Space_Transformers_for_Video_Panoptic_Segmentation_WACV_2022_paper.pdf)\n* Foreground-Background 分割\n  * [Learning Foreground-Background Segmentation from Improved Layered GANs](https://arxiv.org/abs/2104.00483)\n* 超像素分割\n  * [HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation](https://openaccess.thecvf.com/content/WACV2022/papers/Peng_HERS_Superpixels_Deep_Affinity_Learning_for_Hierarchical_Entropy_Rate_Segmentation_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/hankuipeng/DAL-HERS)\n* 道路分割\n  * [VCSeg: Virtual Camera Adaptation for Road Segmentation](https://openaccess.thecvf.com/content/WACV2022/papers/Cheng_VCSeg_Virtual_Camera_Adaptation_for_Road_Segmentation_WACV_2022_paper.pdf)\n* 抠图\n  * 视频抠图\n    * [Robust High-Resolution Video Matting with Temporal Guidance](https://arxiv.org/abs/2108.11515)\u003cbr\u003e:star:[code](https://github.com/PeterL1n/RobustVideoMatting):house:[project](https://peterl1n.github.io/RobustVideoMatting/#/):tv:[video](https://youtu.be/Ay-mGCEYEzM)\n\n\n\u003ca name=\"12\"/\u003e\n\n## 12.One\\Few-Shot Learning or Domain Adaptation\\Generalization\\Shift(单\\小样本学习 or 域适应\\泛化\\偏移)\n* 域适应\n  * [Unsupervised Robust Domain Adaptation Without Source Data](https://arxiv.org/abs/2103.14577)\n  * 半监督域适应\n    * [Semi-Supervised Domain Adaptation via Sample-to-Sample Self-Distillation](https://arxiv.org/abs/2111.14353)\n  * 无监督域适应\n    * [Cleaning Noisy Labels by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptation](https://openaccess.thecvf.com/content/WACV2022/papers/Ahmed_Cleaning_Noisy_Labels_by_Negative_Ensemble_Learning_for_Source-Free_Unsupervised_WACV_2022_paper.pdf)\n    * [Adversarial Branch Architecture Search for Unsupervised Domain Adaptation](https://arxiv.org/abs/2102.06679)\u003cbr\u003e:star:[code](https://github.com/lr94/abas)\n  * 开集域适应\n    * [Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation](https://arxiv.org/abs/2107.02067)\u003cbr\u003e:star:[code](https://github.com/silvia1993/HyMOS)\n  * 多源域适应\n    * [Mutual Learning of Joint and Separate Domain Alignments for Multi-Source Domain Adaptation](https://openaccess.thecvf.com/content/WACV2022/papers/Xu_Mutual_Learning_of_Joint_and_Separate_Domain_Alignments_for_Multi-Source_WACV_2022_paper.pdf)\n    * [Coupled Training for Multi-Source Domain Adaptation](https://openaccess.thecvf.com/content/WACV2022/papers/Amosy_Coupled_Training_for_Multi-Source_Domain_Adaptation_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/amosy3/MUST)\n  * 多目标域适应\n    * [Federated Multi-Target Domain Adaptation](https://arxiv.org/abs/2108.07792)\n* 域泛化\n  * [Learning to Weight Filter Groups for Robust Classification](https://openaccess.thecvf.com/content/WACV2022/papers/Yuan_Learning_to_Weight_Filter_Groups_for_Robust_Classification_WACV_2022_paper.pdf)\n  * 零样本域泛化\n    * [COCOA: Context-Conditional Adaptation for Recognizing Unseen Classes in Unseen Domains](https://openaccess.thecvf.com/content/WACV2022/papers/Mangla_COCOA_Context-Conditional_Adaptation_for_Recognizing_Unseen_Classes_in_Unseen_Domains_WACV_2022_paper.pdf)\n* 小样本学习\n  * [Contextual Gradient Scaling for Few-Shot Learning](https://arxiv.org/abs/2110.10353)\u003cbr\u003e:star:[code](https://github.com/shlee625/CxGrad)\n  * [Calibrating CNNs for Few-Shot Meta Learning](https://openaccess.thecvf.com/content/WACV2022/papers/Yang_Calibrating_CNNs_for_Few-Shot_Meta_Learning_WACV_2022_paper.pdf)\n  * [SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning](https://arxiv.org/abs/2111.04316)\u003cbr\u003e:star:[code](https://github.com/MartaYang/SEGA)\n  * [Tensor Feature Hallucination for Few-Shot Learning](https://arxiv.org/abs/2106.05321)\u003cbr\u003e:star:[code](https://github.com/MichalisLazarou/TFH_fewshot)\n  * [Ortho-Shot: Low Displacement Rank Regularization With Data Augmentation for Few-Shot Learning](https://openaccess.thecvf.com/content/WACV2022/papers/Osahor_Ortho-Shot_Low_Displacement_Rank_Regularization_With_Data_Augmentation_for_Few-Shot_WACV_2022_paper.pdf)\n* Domain Shift\n  *  [Learning to Generate the Unknowns as a Remedy to the Open-Set Domain Shift](https://openaccess.thecvf.com/content/WACV2022/papers/Baktashmotlagh_Learning_To_Generate_the_Unknowns_as_a_Remedy_to_the_WACV_2022_paper.pdf)\n* 单样本学习\n  * [Meta-Meta Classification for One-Shot Learning](https://arxiv.org/abs/2004.08083)\n\n\u003ca name=\"11\"/\u003e\n\n## 11.Face(人脸)\n* 3D Facial\n  * 人脸表情\n    * [Information Bottlenecked Variational Autoencoder for Disentangled 3D Facial Expression Modelling](https://openaccess.thecvf.com/content/WACV2022/papers/Sun_Information_Bottlenecked_Variational_Autoencoder_for_Disentangled_3D_Facial_Expression_Modelling_WACV_2022_paper.pdf)\n  * 3D人脸重建\n     * [Occlusion Resistant Network for 3D Face Reconstruction](https://openaccess.thecvf.com/content/WACV2022/papers/Tiwari_Occlusion_Resistant_Network_for_3D_Face_Reconstruction_WACV_2022_paper.pdf)\n* 基于皱纹的人体识别\n  * [Mobile Based Human Identification Using Forehead Creases: Application and Assessment Under COVID-19 Masked Face Scenarios](https://openaccess.thecvf.com/content/WACV2022/papers/Bharadwaj_Mobile_Based_Human_Identification_Using_Forehead_Creases_Application_and_Assessment_WACV_2022_paper.pdf)\n* 人脸活体检测\n  * [Disentangled Representation With Dual-Stage Feature Learning for Face Anti-Spoofing](https://arxiv.org/abs/2110.09157)\n* 人脸表情\n  * [Quantified Facial Expressiveness for Affective Behavior Analytics](https://arxiv.org/abs/2110.01758)\n  * [Detection and Localization of Facial Expression Manipulations](https://openaccess.thecvf.com/content/WACV2022/papers/Mazaheri_Detection_and_Localization_of_Facial_Expression_Manipulations_WACV_2022_paper.pdf)\n* 人脸检测\n  * [Measuring Representation of Race, Gender, and Age in Children's Books: Face Detection and Feature Classification in Illustrated Images](https://openaccess.thecvf.com/content/WACV2022/papers/Szasz_Measuring_Representation_of_Race_Gender_and_Age_in_Childrens_Books_WACV_2022_paper.pdf)\n* PAD人脸呈现攻击检测\n  * [Learnable Multi-Level Frequency Decomposition and Hierarchical Attention Mechanism for Generalized Face Presentation Attack Detection](https://arxiv.org/abs/2109.07950)\u003cbr\u003e:star:[code](https://github.com/meilfang/LMFD-PAD)\n  * [Digital and Physical-World Attacks on Remote Pulse Detection](https://arxiv.org/abs/2110.11525)\n* 年龄预测\n  * [Fair and Accurate Age Prediction Using Distribution Aware Data Curation and Augmentation](https://arxiv.org/abs/2009.05283)\u003cbr\u003e:star:[code](https://github.com/ForBlindRev/AIBias)\n* Face verification(人脸验证)\n  * [Face Verification With Challenging Imposters and Diversified Demographics](https://openaccess.thecvf.com/content/WACV2022/papers/Popescu_Face_Verification_With_Challenging_Imposters_and_Diversified_Demographics_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/AIMultimediaLab/FaVCI2D-Face-Verification-with-Challenging-Imposters-and-Diversified-Demographics)\n  * [On Black-Box Explanation for Face Verification](https://openaccess.thecvf.com/content/WACV2022/papers/Mery_On_Black-Box_Explanation_for_Face_Verification_WACV_2022_paper.pdf)\n* 人脸去模糊\n  * [Deep Feature Prior Guided Face Deblurring](https://openaccess.thecvf.com/content/WACV2022/papers/Jung_Deep_Feature_Prior_Guided_Face_Deblurring_WACV_2022_paper.pdf)\n* facial forgery detection\n  * [Generalized Facial Manipulation Detection With Edge Region Feature Extraction](https://arxiv.org/abs/2102.01381)\n* 人脸图像质量苹果\n  * [A Deep Insight into Measuring Face Image Utility with General and Face-specific Image Quality Metrics](https://arxiv.org/abs/2110.11111)\n* 人脸补全\n  * [3DFaceFill: An Analysis-By-Synthesis Approach to Face Completion](https://arxiv.org/abs/2110.10395)\n* 妆容迁移\n  * [Facial Attribute Transformers for Precise and Robust Makeup Transfer](https://openaccess.thecvf.com/content/WACV2022/papers/Wan_Facial_Attribute_Transformers_for_Precise_and_Robust_Makeup_Transfer_WACV_2022_paper.pdf)\n* 人脸恢复\n  * [Complete Face Recovery GAN: Unsupervised Joint Face Rotation and De-Occlusion From a Single-View Image](https://openaccess.thecvf.com/content/WACV2022/papers/Ju_Complete_Face_Recovery_GAN_Unsupervised_Joint_Face_Rotation_and_De-Occlusion_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/yeongjoonJu/CFR-GAN)\n* 人脸识别\n  * [Measuring Hidden Bias Within Face Recognition via Racial Phenotypes](https://arxiv.org/abs/2110.09839)\n  * [Geometrically Adaptive Dictionary Attack on Face Recognition](https://arxiv.org/abs/2111.04371)\n\n\u003ca name=\"10\"/\u003e\n\n## 10.Adversarial Learning(对抗学习)\n* 黑盒攻击\n  * [On the Effectiveness of Small Input Noise for Defending Against Query-Based Black-Box Attacks](https://arxiv.org/abs/2101.04829)\n* 对抗样本\n  * [Attack Agnostic Detection of Adversarial Examples via Random Subspace Analysis](https://arxiv.org/abs/2012.06405)\n* 对抗攻击\n  * [Generative Adversarial Attack on Ensemble Clustering](https://openaccess.thecvf.com/content/WACV2022/papers/Kumar_Generative_Adversarial_Attack_on_Ensemble_Clustering_WACV_2022_paper.pdf)\n\n\u003ca name=\"9\"/\u003e\n\n## 9.Remote Sensing\\Satellite Image(遥感\\卫星图像)\n* [Lane-Level Street Map Extraction From Aerial Imagery](https://openaccess.thecvf.com/content/WACV2022/papers/He_Lane-Level_Street_Map_Extraction_From_Aerial_Imagery_WACV_2022_paper.pdf)\n* [An Experimental Comparison of Multi-View Stereo Approaches on Satellite Images](https://openaccess.thecvf.com/content/WACV2022/papers/Gomez_An_Experimental_Comparison_of_Multi-View_Stereo_Approaches_on_Satellite_Images_WACV_2022_paper.pdf)\n* 小样本开放集识别\n  * [Few-Shot Open-Set Recognition of Hyperspectral Images With Outlier Calibration Network](https://openaccess.thecvf.com/content/WACV2022/papers/Pal_Few-Shot_Open-Set_Recognition_of_Hyperspectral_Images_With_Outlier_Calibration_Network_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/DebabrataPal7/OCN)\n* 检测\n  * [Physical Adversarial Attacks on an Aerial Imagery Object Detector](https://arxiv.org/abs/2108.11765)\u003cbr\u003e:tv:[video](https://www.youtube.com/watch?v=5N6JDZf3pLQ)\n  * 停车场检测\n    * [A Context-Enriched Satellite Imagery Dataset and an Approach for Parking Lot Detection](https://openaccess.thecvf.com/content/WACV2022/papers/Yin_A_Context-Enriched_Satellite_Imagery_Dataset_and_an_Approach_for_Parking_WACV_2022_paper.pdf)\n* 跟踪\n  * [Siamese Transformer Pyramid Networks for Real-Time UAV Tracking](https://arxiv.org/abs/2110.08822)\u003cbr\u003e:star:[code](https://github.com/RISCNYUAD/SiamTPNTracker)\n\n\u003ca name=\"8\"/\u003e\n\n## 8.Image Processing(图像处理)\n* [Extracting Vignetting and Grain Filter Effects From Photos](https://openaccess.thecvf.com/content/WACV2022/papers/Abdelhamed_Extracting_Vignetting_and_Grain_Filter_Effects_From_Photos_WACV_2022_paper.pdf)\n* 去噪\n  * [Weakly Supervised Learning for Joint Image Denoising and Protein Localization in Cryo-Electron Microscopy](https://openaccess.thecvf.com/content/WACV2022/papers/Huang_Weakly_Supervised_Learning_for_Joint_Image_Denoising_and_Protein_Localization_WACV_2022_paper.pdf)\n* 去雨\n  * [FLUID: Few-Shot Self-Supervised Image Deraining](https://openaccess.thecvf.com/content/WACV2022/papers/Nandan_FLUID_Few-Shot_Self-Supervised_Image_Deraining_WACV_2022_paper.pdf)\n  * [Single Image Deraining Network With Rain Embedding Consistency and Layered LSTM](https://arxiv.org/abs/2111.03615)\u003cbr\u003e:star:[code](https://github.com/Yizhou-Li-CV/ECNet)\n* 去模糊\n  * [Non-Blind Deblurring for Fluorescence: A Deformable Latent Space Approach With Kernel Parameterization](https://openaccess.thecvf.com/content/WACV2022/papers/Guan_Non-Blind_Deblurring_for_Fluorescence_A_Deformable_Latent_Space_Approach_With_WACV_2022_paper.pdf)\n  * [Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning](https://arxiv.org/abs/2108.05251)\u003cbr\u003e:star:[code](https://github.com/Abdullah-Abuolaim/multi-task-defocus-deblurring-dual-pixel-nimat)\n* 去马赛克\n  * [Forgery Detection by Internal Positional Learning of Demosaicing Traces](https://openaccess.thecvf.com/content/WACV2022/papers/Bammey_Forgery_Detection_by_Internal_Positional_Learning_of_Demosaicing_Traces_WACV_2022_paper.pdf)\n* 图像着色\n  * [Late-Resizing: A Simple but Effective Sketch Extraction Strategy for Improving Generalization of Line-Art Colorization](https://openaccess.thecvf.com/content/WACV2022/papers/Kim_Late-Resizing_A_Simple_but_Effective_Sketch_Extraction_Strategy_for_Improving_WACV_2022_paper.pdf)\n  * [Pro-CCaps: Progressively Teaching Colourisation to Capsules](https://openaccess.thecvf.com/content/WACV2022/papers/Pucci_Pro-CCaps_Progressively_Teaching_Colourisation_to_Capsules_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/Riretta/Pro_CCaps-Progressive-learning-with-capsules)\n* 图像裁剪\n  * [Auditing Saliency Cropping Algorithms](https://openaccess.thecvf.com/content/WACV2022/papers/Birhane_Auditing_Saliency_Cropping_Algorithms_WACV_2022_paper.pdf)\n  * [Re-Compose the Image by Evaluating the Crop on More Than Just a Score](https://openaccess.thecvf.com/content/WACV2022/papers/Cheng_Re-Compose_the_Image_by_Evaluating_the_Crop_on_More_Than_WACV_2022_paper.pdf)\n* 图像恢复\n  * [Training a Task-Specific Image Reconstruction Loss](https://arxiv.org/abs/2103.14616)\n  * [Image Restoration by Deep Projected GSURE](https://openaccess.thecvf.com/content/WACV2022/papers/Abu-Hussein_Image_Restoration_by_Deep_Projected_GSURE_WACV_2022_paper.pdf)\n* 图像修复\n  * [Resolution-Robust Large Mask Inpainting With Fourier Convolutions](https://arxiv.org/abs/2109.07161)\u003cbr\u003e:star:[code](https://github.com/saic-mdal/lama)\n* 图像降质\n  * [Deep Photo Scan: Semi-Supervised Learning for dealing with the real-world degradation in Smartphone Photo Scanning](https://arxiv.org/abs/2102.06120)\u003cbr\u003e:star:[code](https://github.com/minhmanho/dpscan):house:[project](https://minhmanho.github.io/dpscan/)\n* 图像增强\n  * [Learning Color Representations for Low-Light Image Enhancement](https://openaccess.thecvf.com/content/WACV2022/papers/Kim_Learning_Color_Representations_for_Low-Light_Image_Enhancement_WACV_2022_paper.pdf)\n* 图像质量评估\n  * [No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency](https://arxiv.org/abs/2108.06858)\n* Image reenactment(图像重演)\n  * [Single Source One Shot Reenactment using Weighted motion From Paired Feature Points](https://arxiv.org/abs/2104.03117)\n* Image decomposition(图像分解)\n  * [Fast Nonlinear Image Unblending](https://openaccess.thecvf.com/content/WACV2022/papers/Horita_Fast_Nonlinear_Image_Unblending_WACV_2022_paper.pdf)\n* HDR\n  * [High Dynamic Range Imaging of Dynamic Scenes With Saturation Compensation but Without Explicit Motion Compensation](https://openaccess.thecvf.com/content/WACV2022/papers/Chung_High_Dynamic_Range_Imaging_of_Dynamic_Scenes_With_Saturation_Compensation_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/haesoochung/hdri-saturation-compensation)\n  * [Single-Photon Camera Guided Extreme Dynamic Range Imaging](https://openaccess.thecvf.com/content/WACV2022/papers/Liu_Single-Photon_Camera_Guided_Extreme_Dynamic_Range_Imaging_WACV_2022_paper.pdf)\n* Auto white balance(自动白平衡)\n  * [Auto White-Balance Correction for Mixed-Illuminant Scenes](https://arxiv.org/abs/2109.08750)\u003cbr\u003e:star:[code](https://github.com/mahmoudnafifi/mixedillWB)\n\n\u003ca name=\"7\"/\u003e\n\n## 7.Human Pose(人体姿态)\n* 人体动作合成\n  * [Generative Adversarial Graph Convolutional Networks for Human Action Synthesis](https://arxiv.org/abs/2110.11191)\u003cbr\u003e:star:[code](https://github.com/DegardinBruno/Kinetic-GAN)\n* 3D人体\n  * [Matching and Recovering 3D People From Multiple Views](https://openaccess.thecvf.com/content/WACV2022/papers/Perez-Yus_Matching_and_Recovering_3D_People_From_Multiple_Views_WACV_2022_paper.pdf)\n* 人体姿态估计\n  * [Transfer Learning for Pose Estimation of Illustrated Characters](https://arxiv.org/abs/2108.01819)\n  * [PERF-Net: Pose Empowered RGB-Flow Net](https://openaccess.thecvf.com/content/WACV2022/papers/Li_PERF-Net_Pose_Empowered_RGB-Flow_Net_WACV_2022_paper.pdf)\n  * [Bayesian Uncertainty and Expected Gradient Length - Regression: Two Sides of the Same Coin?](https://openaccess.thecvf.com/content/WACV2022/papers/Shukla_Bayesian_Uncertainty_and_Expected_Gradient_Length_-_Regression_Two_Sides_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/meghshukla/ActiveLearningForHumanPose)\n  * [Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation](https://arxiv.org/abs/2110.11680)\n* 3D人体姿态估计\n  * [PoP-Net: Pose Over Parts Network for Multi-Person 3D Pose Estimation From a Depth Image](https://openaccess.thecvf.com/content/WACV2022/papers/Guo_PoP-Net_Pose_Over_Parts_Network_for_Multi-Person_3D_Pose_Estimation_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/oppo-us-research/PoP-Net)\n* 3D手部姿势估计\n  * [Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation](https://arxiv.org/abs/2111.06500)\n* 头部姿势估计\n  * [LwPosr: Lightweight Efficient Fine Grained Head Pose Estimation](https://openaccess.thecvf.com/content/WACV2022/papers/Dhingra_LwPosr_Lightweight_Efficient_Fine_Grained_Head_Pose_Estimation_WACV_2022_paper.pdf)\n  * [HHP-Net: A Light Heteroscedastic Neural Network for Head Pose Estimation With Uncertainty](https://openaccess.thecvf.com/content/WACV2022/papers/Cantarini_HHP-Net_A_Light_Heteroscedastic_Neural_Network_for_Head_Pose_Estimation_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/cantarinigiorgio/HHP-Net)\n* 三维人体模型\n  * [Creating and Reenacting Controllable 3D Humans with Differentiable Rendering](https://arxiv.org/abs/2110.11746)\n* 人体形状\n  * [A Riemannian Framework for Analysis of Human Body Surface](https://arxiv.org/abs/2108.11449)\n\n\u003ca name=\"6\"/\u003e\n\n## 6.Video(视频相关)\n* 无监督视频域适应\n  * [Multi-Level Attentive Adversarial Learning With Temporal Dilation for Unsupervised Video Domain Adaptation](https://openaccess.thecvf.com/content/WACV2022/papers/Chen_Multi-Level_Attentive_Adversarial_Learning_With_Temporal_Dilation_for_Unsupervised_Video_WACV_2022_paper.pdf)\n* Partial Video Copy Detection(局部视频拷贝检测)\n  * [A Fast Partial Video Copy Detection Using KNN and Global Feature Database](https://arxiv.org/abs/2105.01713)\n* 异常检测\n  * [Discrete Neural Representations for Explainable Anomaly Detection](https://arxiv.org/abs/2112.05585)\u003cbr\u003e:house:[project](http://jjcvision.com/projects/vqunet_anomally_detection.html):tv:[video](https://youtu.be/3KLRi0biQvY)\n  * [Rethinking Video Anomaly Detection - A Continual Learning Approach](https://openaccess.thecvf.com/content/WACV2022/papers/Doshi_Rethinking_Video_Anomaly_Detection_-_A_Continual_Learning_Approach_WACV_2022_paper.pdf)\n  * [A Modular and Unified Framework for Detecting and Localizing Video Anomalies](https://arxiv.org/abs/2103.11299)\n  * [FastAno: Fast Anomaly Detection via Spatio-Temporal Patch Transformation](https://arxiv.org/abs/2106.08613)\n  * [Multi-Branch Neural Networks for Video Anomaly Detection in Adverse Lighting and Weather Conditions](https://openaccess.thecvf.com/content/WACV2022/papers/Leroux_Multi-Branch_Neural_Networks_for_Video_Anomaly_Detection_in_Adverse_Lighting_WACV_2022_paper.pdf)\n* sarcasm and humor detection(讽刺与幽默检测)\n  * [Multimodal Learning using Optimal Transport for Sarcasm and Humor Detection](https://arxiv.org/abs/2110.10949)\n* 视频表征学习\n  * [Hierarchically Decoupled Spatial-Temporal Contrast for Self-Supervised Video Representation Learning](https://arxiv.org/abs/2011.11261)\n  * [Self-Supervised Video Representation Learning With Cross-Stream Prototypical Contrasting](https://arxiv.org/abs/2106.10137)\u003cbr\u003e:star:[code](https://github.com/martinetoering/ViCC)\n* 视频字幕\n  * [Co-Segmentation Aided Two-Stream Architecture for Video Captioning](https://openaccess.thecvf.com/content/WACV2022/papers/Vaidya_Co-Segmentation_Aided_Two-Stream_Architecture_for_Video_Captioning_WACV_2022_paper.pdf)\n  * [Variational Stacked Local Attention Networks for Diverse Video Captioning](https://openaccess.thecvf.com/content/WACV2022/papers/Deb_Variational_Stacked_Local_Attention_Networks_for_Diverse_Video_Captioning_WACV_2022_paper.pdf)\n* 视频人物定位\n  * [Extraction of Positional Player Data From Broadcast Soccer Videos](https://openaccess.thecvf.com/content/WACV2022/papers/Theiner_Extraction_of_Positional_Player_Data_From_Broadcast_Soccer_Videos_WACV_2022_paper.pdf)\n* 视频稳定\n  * [Deep Online Fused Video Stabilization](https://arxiv.org/abs/2102.01279)\u003cbr\u003e:star:[code](https://github.com/googleinterns/deep-stabilization):house:[project](https://zhmeishi.github.io/dvs/):tv:[video](https://youtu.be/LF_JVdUFIw8)\n* 视频理解\n  * [Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search](https://openaccess.thecvf.com/content/WACV2022/papers/Jiang_Auto-X3D_Ultra-Efficient_Video_Understanding_via_Finer-Grained_Neural_Architecture_Search_WACV_2022_paper.pdf)\n* 视频分类\n  * [Busy-Quiet Video Disentangling for Video Classification](https://arxiv.org/abs/2103.15584)\u003cbr\u003e:star:[code](https://github.com/guoxih/busy-quiet-net)\n* 视频摘要\n  * [Multi-Stream Dynamic Video Summarization](https://arxiv.org/abs/1812.00108)\n* 有声视频合成\n  * [Strumming to the Beat: Audio-Conditioned Contrastive Video Textures](https://arxiv.org/abs/2104.02687)\u003cbr\u003e:star:[code](https://github.com/medhini/audio-video-textures):house:[project](https://medhini.github.io/audio_video_textures/):tv:[video](https://youtu.be/JCuEbSF4kxU)\n* 视频帧插值\n  * [Enhanced Correlation Matching Based Video Frame Interpolation](https://arxiv.org/abs/2111.08869)\n* 视频时刻定位\n  * [Natural Language Video Moment Localization Through Query-Controlled Temporal Convolution](https://openaccess.thecvf.com/content/WACV2022/papers/Zhang_Natural_Language_Video_Moment_Localization_Through_Query-Controlled_Temporal_Convolution_WACV_2022_paper.pdf)\n* Temporal Video Segmentation(时序视频分割)\n  * [Learning Temporal Video Procedure Segmentation From an Automatically Collected Large Dataset](https://openaccess.thecvf.com/content/WACV2022/papers/Ji_Learning_Temporal_Video_Procedure_Segmentation_From_an_Automatically_Collected_Large_WACV_2022_paper.pdf)\n\n\u003ca name=\"5\"/\u003e\n\n## 5.Object Detection(目标检测)\n* [Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection Using Meta-Learning](https://openaccess.thecvf.com/content/WACV2022/papers/VS_Meta-UDA_Unsupervised_Domain_Adaptive_Thermal_Object_Detection_Using_Meta-Learning_WACV_2022_paper.pdf)\n* [ADC: Adversarial Attacks Against Object Detection That Evade Context Consistency Checks](https://arxiv.org/abs/2110.12321)\n* [TricubeNet: 2D Kernel-Based Object Representation for Weakly-Occluded Oriented Object Detection](https://arxiv.org/abs/2104.11435)\u003cbr\u003e:star:[code](https://github.com/qjadud1994/TricubeNet)\n* [Detecting Tear Gas Canisters With Limited Training Data](https://openaccess.thecvf.com/content/WACV2022/papers/DCruz_Detecting_Tear_Gas_Canisters_With_Limited_Training_Data_WACV_2022_paper.pdf)\n* [Learned Event-Based Visual Perception for Improved Space Object Detection](https://openaccess.thecvf.com/content/WACV2022/papers/Salvatore_Learned_Event-Based_Visual_Perception_for_Improved_Space_Object_Detection_WACV_2022_paper.pdf)\n* [Densely-Packed Object Detection via Hard Negative-Aware Anchor Attention](https://openaccess.thecvf.com/content/WACV2022/papers/Cho_Densely-Packed_Object_Detection_via_Hard_Negative-Aware_Anchor_Attention_WACV_2022_paper.pdf)\n* [PICA: Point-Wise Instance and Centroid Alignment Based Few-Shot Domain Adaptive Object Detection With Loose Annotations](https://openaccess.thecvf.com/content/WACV2022/papers/Zhong_PICA_Point-Wise_Instance_and_Centroid_Alignment_Based_Few-Shot_Domain_Adaptive_WACV_2022_paper.pdf)\n* [Improving Object Detection by Label Assignment Distillation](https://arxiv.org/abs/2108.10520)\u003cbr\u003e:star:[code](https://github.com/cybercore-co-ltd/CoLAD)\n* [Fusion Point Pruning for Optimized 2D Object Detection With Radar-Camera Fusion](https://openaccess.thecvf.com/content/WACV2022/papers/Stacker_Fusion_Point_Pruning_for_Optimized_2D_Object_Detection_With_Radar-Camera_WACV_2022_paper.pdf)\n* [YOLO-ReT: Towards High Accuracy Real-Time Object Detection on Edge GPUs](https://openaccess.thecvf.com/content/WACV2022/papers/Ganesh_YOLO-ReT_Towards_High_Accuracy_Real-Time_Object_Detection_on_Edge_GPUs_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/prakharg24/yoloret)\n* [SC-UDA: Style and Content Gaps Aware Unsupervised Domain Adaptation for Object Detection](https://openaccess.thecvf.com/content/WACV2022/papers/Yu_SC-UDA_Style_and_Content_Gaps_Aware_Unsupervised_Domain_Adaptation_for_WACV_2022_paper.pdf)\n* [To Miss-Attend Is to Misalign! Residual Self-Attentive Feature Alignment for Adapting Object Detectors](https://openaccess.thecvf.com/content/WACV2022/papers/Khindkar_To_Miss-Attend_Is_to_Misalign_Residual_Self-Attentive_Feature_Alignment_for_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/Vaishnvi/ILLUME)\n* 目标定位\n  * 无监督目标定位\n    * [F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling](https://openaccess.thecvf.com/content/WACV2022/papers/Belharbi_F-CAM_Full_Resolution_Class_Activation_Maps_via_Guided_Parametric_Upscaling_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/sbelharbi/fcam-wsol)\n* MOD(移动目标检测)\n  * [Multi-Motion and Appearance Self-Supervised Moving Object Detection](https://openaccess.thecvf.com/content/WACV2022/papers/Yang_Multi-Motion_and_Appearance_Self-Supervised_Moving_Object_Detection_WACV_2022_paper.pdf)\n* 路标检测\n  * [CeyMo: See More on Roads - A Novel Benchmark Dataset for Road Marking Detection](https://openaccess.thecvf.com/content/WACV2022/papers/Jayasinghe_CeyMo_See_More_on_Roads_-_A_Novel_Benchmark_Dataset_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/oshadajay/CeyMo)\n* 零样本检测\n  * [From Node To Graph: Joint Reasoning on Visual-Semantic Relational Graph for Zero-Shot Detection](https://openaccess.thecvf.com/content/WACV2022/papers/Nie_From_Node_To_Graph_Joint_Reasoning_on_Visual-Semantic_Relational_Graph_WACV_2022_paper.pdf)\n* 小样本目标检测\n  * [Few-Shot Object Detection by Attending to Per-Sample-Prototype](https://arxiv.org/abs/2109.07734)\n* 图像异常检测\n  * [Multi-Scale Patch-Based Representation Learning for Image Anomaly Detection and Segmentation](https://openaccess.thecvf.com/content/WACV2022/papers/Tsai_Multi-Scale_Patch-Based_Representation_Learning_for_Image_Anomaly_Detection_and_Segmentation_WACV_2022_paper.pdf)\n* 弱监督目标检测\n * [Few-Shot Weakly-Supervised Object Detection via Directional Statistics](https://arxiv.org/abs/2103.14162)\n* 海上障碍物检测\n  * [Learning Maritime Obstacle Detection From Weak Annotations by Scaffolding](https://openaccess.thecvf.com/content/WACV2022/papers/Zust_Learning_Maritime_Obstacle_Detection_From_Weak_Annotations_by_Scaffolding_WACV_2022_paper.pdf)\n* 人造卫星识别\n  * [SpectraNet: Learned Recognition of Artificial Satellites From High Contrast Spectroscopic Imagery](https://openaccess.thecvf.com/content/WACV2022/papers/Gazak_SpectraNet_Learned_Recognition_of_Artificial_Satellites_From_High_Contrast_Spectroscopic_WACV_2022_paper.pdf)\n* Object Anti-Spoofing\n  * [MToFNet: Object Anti-Spoofing with Mobile Time-of-Flight Data](https://arxiv.org/abs/2110.04066)\u003cbr\u003e:star:[code](https://github.com/SamsungSDS-Team9/mToFNet)\n* 3D目标检测\n  * [ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection](https://arxiv.org/abs/2106.01178)\u003cbr\u003e:star:[code](https://github.com/saic-vul/imvoxelnet)\n  * [Fast-CLOCs: Fast Camera-LiDAR Object Candidates Fusion for 3D Object Detection](https://openaccess.thecvf.com/content/WACV2022/papers/Pang_Fast-CLOCs_Fast_Camera-LiDAR_Object_Candidates_Fusion_for_3D_Object_Detection_WACV_2022_paper.pdf)\n  * [M3DETR: Multi-Representation, Multi-Scale, Mutual-Relation 3D Object Detection With Transformers](https://arxiv.org/abs/2104.11896)\u003cbr\u003e:star:[code](https://github.com/rayguan97/M3DETR)\n* 显著目标检测\n  * [Video Salient Object Detection via Contrastive Features and Attention Modules](https://arxiv.org/abs/2111.02368)\n  * [Recursive Contour-Saliency Blending Network for Accurate Salient Object Detection](https://arxiv.org/abs/2105.13865)\u003cbr\u003e:star:[code](https://github.com/BarCodeReader/RCSB-PyTorch)\n* 伪装目标检测\n  * [Modeling Aleatoric Uncertainty for Camouflaged Object Detection](https://openaccess.thecvf.com/content/WACV2022/papers/Liu_Modeling_Aleatoric_Uncertainty_for_Camouflaged_Object_Detection_WACV_2022_paper.pdf)\n* 球员检测\n  * [Transductive Weakly-Supervised Player Detection Using Soccer Broadcast Videos](https://openaccess.thecvf.com/content/WACV2022/papers/Gadde_Transductive_Weakly-Supervised_Player_Detection_Using_Soccer_Broadcast_Videos_WACV_2022_paper.pdf)\n* Wireframe Detection(线框检测)\n  * [Hole-robust Wireframe Detection](https://arxiv.org/abs/2111.15064)\n\n\u003ca name=\"4\"/\u003e\n\n## 4.GAN(生成对抗网络)\n* [GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks](https://openaccess.thecvf.com/content/WACV2022/papers/Bhaskara_GraN-GAN_Piecewise_Gradient_Normalization_for_Generative_Adversarial_Networks_WACV_2022_paper.pdf)\n* [Latent to Latent: A Learned Mapper for Identity Preserving Editing of Multiple Face Attributes in StyleGAN-Generated Images](https://openaccess.thecvf.com/content/WACV2022/papers/Khodadadeh_Latent_to_Latent_A_Learned_Mapper_for_Identity_Preserving_Editing_WACV_2022_paper.pdf)\n* [AE-StyleGAN: Improved Training of Style-Based Auto-Encoders](https://openaccess.thecvf.com/content/WACV2022/papers/Han_AE-StyleGAN_Improved_Training_of_Style-Based_Auto-Encoders_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/phymhan/stylegan2-pytorch)\n* [GANs Spatial Control via Inference-Time Adaptive Normalization](https://openaccess.thecvf.com/content/WACV2022/papers/Jakoel_GANs_Spatial_Control_via_Inference-Time_Adaptive_Normalization_WACV_2022_paper.pdf)\n* [Latent Reweighting, an Almost Free Improvement for GANs](https://arxiv.org/abs/2110.09803)\n* [PPCD-GAN: Progressive Pruning and Class-Aware Distillation for Large-Scale Conditional GANs Compression](https://openaccess.thecvf.com/content/WACV2022/papers/Vo_PPCD-GAN_Progressive_Pruning_and_Class-Aware_Distillation_for_Large-Scale_Conditional_GANs_WACV_2022_paper.pdf)\n* [Controlled GAN-Based Creature Synthesis via a Challenging Game Art Dataset - Addressing the Noise-Latent Trade-Off](https://openaccess.thecvf.com/content/WACV2022/papers/Vavilala_Controlled_GAN-Based_Creature_Synthesis_via_a_Challenging_Game_Art_Dataset_WACV_2022_paper.pdf)\n* [Data InStance Prior (DISP) in Generative Adversarial Networks](https://arxiv.org/abs/2012.04256)\n* Sketch-To-Face草图到人脸图像翻译\n  * [S2FGAN: Semantically Aware Interactive Sketch-To-Face Translation](https://arxiv.org/abs/2011.14785)\u003cbr\u003e:star:[code](https://github.com/Yan98/S2FGAN)\n* 基于关键点重新合成新姿势\n  * [CharacterGAN: Few-Shot Keypoint Character Animation and Reposing](https://arxiv.org/abs/2102.03141)\u003cbr\u003e:star:[code](https://github.com/tohinz/CharacterGAN)\n* MRI重建\n  * [Compressed Sensing MRI Reconstruction With Co-VeGAN: Complex-Valued Generative Adversarial Network](https://openaccess.thecvf.com/content/WACV2022/papers/Vasudeva_Compressed_Sensing_MRI_Reconstruction_With_Co-VeGAN_Complex-Valued_Generative_Adversarial_Network_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/estija/Co-VeGAN)\n\n\u003ca name=\"3\"/\u003e\n\n## 3.3D(三维视觉)\n* 深度估计\n  * [SIDE: Center-Based Stereo 3D Detector With Structure-Aware Instance Depth Estimation](https://arxiv.org/abs/2108.09663)\n  * [Estimating Image Depth in the Comics Domain](https://arxiv.org/abs/2110.03575)\n  * [Self-Supervised Learning of Domain Invariant Features for Depth Estimation](https://arxiv.org/abs/2106.02594)\n  * 单目深度估计\n    * [Monocular Depth Estimation With Adaptive Geometric Attention](https://openaccess.thecvf.com/content/WACV2022/papers/Naderi_Monocular_Depth_Estimation_With_Adaptive_Geometric_Attention_WACV_2022_paper.pdf)\n    * [EdgeConv With Attention Module for Monocular Depth Estimation](https://arxiv.org/abs/2106.08615)\n* stereo images\n  * [SBEVNet: End-to-End Deep Stereo Layout Estimation](https://arxiv.org/abs/2105.11705)\u003cbr\u003e:star:[code](https://github.com/divamgupta/sbevnet-stereo-layout-estimation)\n  * [MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching](https://arxiv.org/abs/2108.09770)\u003cbr\u003e:star:[code](https://github.com/cogsys-tuebingen/mobilestereonet)\n* 三维重建\n  * [Single-Shot Dense Active Stereo With Pixel-Wise Phase Estimation Based on Grid-Structure Using CNN and Correspondence Estimation Using GCN](https://openaccess.thecvf.com/content/WACV2022/papers/Furukawa_Single-Shot_Dense_Active_Stereo_With_Pixel-Wise_Phase_Estimation_Based_on_WACV_2022_paper.pdf)\n  * [Style Agnostic 3D Reconstruction via Adversarial Style Transfer](https://arxiv.org/abs/2110.10784)\u003cbr\u003e:star:[code](https://github.com/Felix-Petersen/style-agnostic-3d-reconstruction)\n  * [3D Modeling Beneath Ground: Plant Root Detection and Reconstruction Based on Ground-Penetrating Radar](https://openaccess.thecvf.com/content/WACV2022/papers/Lu_3D_Modeling_Beneath_Ground_Plant_Root_Detection_and_Reconstruction_Based_WACV_2022_paper.pdf)\n  * [Mending Neural Implicit Modeling for 3D Vehicle Reconstruction in the Wild](https://arxiv.org/abs/2101.06860)\n  * [Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image](https://arxiv.org/abs/2104.07986)\u003cbr\u003e:star:[code](https://github.com/Cyang0515/NonCuboidRoom)\n  * [Tensor-Based Non-Rigid Structure From Motion](https://openaccess.thecvf.com/content/WACV2022/papers/Grasshof_Tensor-Based_Non-Rigid_Structure_From_Motion_WACV_2022_paper.pdf)\n* stereo vision(立体视觉)\n  * [PredStereo: An Accurate Real-Time Stereo Vision System](https://openaccess.thecvf.com/content/WACV2022/papers/Moolchandani_PredStereo_An_Accurate_Real-Time_Stereo_Vision_System_WACV_2022_paper.pdf)\n* 网格重建\n  * [AttWalk: Attentive Cross-Walks for Deep Mesh Analysis](https://arxiv.org/abs/2104.11571)\n\n\u003ca name=\"2\"/\u003e\n\n## 2.Medical Image(医学影像)\n* 分割\n  * [UNETR: Transformers for 3D Medical Image Segmentation](https://arxiv.org/abs/2103.10504)\u003cbr\u003e:star:[code](https://github.com/Project-MONAI/research-contributions/tree/master/UNETR)\n  * [Self-Supervised Generative Style Transfer for One-Shot Medical Image Segmentation](https://arxiv.org/abs/2110.02117)\u003cbr\u003e:star:[code](https://github.com/devavratTomar/SST)\n  * [AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentation](https://openaccess.thecvf.com/content/WACV2022/papers/Yan_AFTer-UNet_Axial_Fusion_Transformer_UNet_for_Medical_Image_Segmentation_WACV_2022_paper.pdf)\n  * [Co-Net: A Collaborative Region-Contour-Driven Network for Fine-to-Finer Medical Image Segmentation](https://openaccess.thecvf.com/content/WACV2022/papers/Liu_Co-Net_A_Collaborative_Region-Contour-Driven_Network_for_Fine-to-Finer_Medical_Image_Segmentation_WACV_2022_paper.pdf)\n  * [T-Net: A Resource-Constrained Tiny Convolutional Neural Network for Medical Image Segmentation](https://openaccess.thecvf.com/content/WACV2022/papers/Khan_T-Net_A_Resource-Constrained_Tiny_Convolutional_Neural_Network_for_Medical_Image_WACV_2022_paper.pdf)\n  * [Hyper-Convolution Networks for Biomedical Image Segmentation](https://arxiv.org/abs/2105.10559)\u003cbr\u003e:star:[code](https://github.com/tym002/Hyper-Convolution)\n  * 血管分割\n    * [Weakly-Supervised Convolutional Neural Networks for Vessel Segmentation in Cerebral Angiography](https://openaccess.thecvf.com/content/WACV2022/papers/Vepa_Weakly-Supervised_Convolutional_Neural_Networks_for_Vessel_Segmentation_in_Cerebral_Angiography_WACV_2022_paper.pdf)\n  * 腺体分割\n    * [TA-Net: Topology-Aware Network for Gland Segmentation](https://openaccess.thecvf.com/content/WACV2022/papers/Wang_TA-Net_Topology-Aware_Network_for_Gland_Segmentation_WACV_2022_paper.pdf)\n* 检索\n  * [X-MIR: EXplainable Medical Image Retrieval](https://openaccess.thecvf.com/content/WACV2022/papers/Hu_X-MIR_EXplainable_Medical_Image_Retrieval_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://gitlab.kitware.com/brianhhu/x-mir)\n* 配准\n  * [Uncertainty Learning Towards Unsupervised Deformable Medical Image Registration](https://openaccess.thecvf.com/content/WACV2022/papers/Gong_Uncertainty_Learning_Towards_Unsupervised_Deformable_Medical_Image_Registration_WACV_2022_paper.pdf)\n* 分类\n  * [Weakly Supervised Branch Network With Template Mask for Classifying Masses in 3D Automated Breast Ultrasound](https://openaccess.thecvf.com/content/WACV2022/papers/Kim_Weakly_Supervised_Branch_Network_With_Template_Mask_for_Classifying_Masses_WACV_2022_paper.pdf)\n* 自动生成医学报告\n  * [Non-Local Attention Improves Description Generation for Retinal Images](https://openaccess.thecvf.com/content/WACV2022/papers/Huang_Non-Local_Attention_Improves_Description_Generation_for_Retinal_Images_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/Jhhuangkay/Non-local-Attention-Improves-Description-Generation-for-Retinal-Images)\n* 手术器械定位\n  * [Dynamic CNNs Using Uncertainty To Overcome Domain Generalization for Surgical Instrument Localization](https://openaccess.thecvf.com/content/WACV2022/papers/Philipp_Dynamic_CNNs_Using_Uncertainty_To_Overcome_Domain_Generalization_for_Surgical_WACV_2022_paper.pdf)\n* 胸部X光片的异常分类和定位\n  * [Knowledge-Augmented Contrastive Learning for Abnormality Classification and Localization in Chest X-Rays With Radiomics Using a Feedback Loop](https://openaccess.thecvf.com/content/WACV2022/papers/Han_Knowledge-Augmented_Contrastive_Learning_for_Abnormality_Classification_and_Localization_in_Chest_WACV_2022_paper.pdf)\n\n\u003ca name=\"1\"/\u003e\n\n## 1.其它\n* [Does Data Repair Lead to Fair Models? Curating Contextually Fair Data To Reduce Model Bias](https://arxiv.org/abs/2110.10389)\u003cbr\u003e:star:[code](https://github.com/sumanyumuku98/contextual-bias)\n* [The Untapped Potential of Off-the-Shelf Convolutional Neural Networks](https://arxiv.org/abs/2103.09891)\n* [Unveiling Real-Life Effects of Online Photo Sharing](https://openaccess.thecvf.com/content/WACV2022/papers/Nguyen_Unveiling_Real-Life_Effects_of_Online_Photo_Sharing_WACV_2022_paper.pdf)\n* [Shadow Art Revisited: A Differentiable Rendering Based Approach](https://arxiv.org/abs/2107.14539)\n* [Towards Class-Oriented Poisoning Attacks Against Neural Networks](https://arxiv.org/abs/2008.00047)\n* [Predicting Levels of Household Electricity Consumption in Low-Access Settings](https://arxiv.org/abs/2112.08497)\n* [Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo](https://arxiv.org/abs/2110.05594)\n* [PRECODE - A Generic Model Extension To Prevent Deep Gradient Leakage](https://openaccess.thecvf.com/content/WACV2022/papers/Scheliga_PRECODE_-_A_Generic_Model_Extension_To_Prevent_Deep_Gradient_WACV_2022_paper.pdf)\n* [Discovering Underground Maps From Fashion](https://arxiv.org/abs/2012.02897)\n* [On the Maximum Radius of Polynomial Lens Distortion](https://openaccess.thecvf.com/content/WACV2022/papers/Leotta_On_the_Maximum_Radius_of_Polynomial_Lens_Distortion_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/Kitware/max-lens-radius)\n* [The Hitchhiker's Guide to Prior-Shift Adaptation](https://openaccess.thecvf.com/content/WACV2022/papers/Sipka_The_Hitchhikers_Guide_to_Prior-Shift_Adaptation_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/sipkatom/The-Hitchhiker-s-Guide-to-Prior-Shift-Adaptation)\n* [FalCon: Fine-Grained Feature Map Sparsity Computing With Decomposed Convolutions for Inference Optimization](https://openaccess.thecvf.com/content/WACV2022/papers/Xu_FalCon_Fine-Grained_Feature_Map_Sparsity_Computing_With_Decomposed_Convolutions_for_WACV_2022_paper.pdf)\n* [METGAN: Generative Tumour Inpainting and Modality Synthesis in Light Sheet Microscopy](https://arxiv.org/abs/2104.10993)\n* [Agree To Disagree: When Deep Learning Models With Identical Architectures Produce Distinct Explanations](https://arxiv.org/abs/2105.06791)\u003cbr\u003e:star:[code](https://github.com/mattswatson/agree-to-disagree)\n* [REFICS: A Step Towards Linking Vision With Hardware Assurance](https://openaccess.thecvf.com/content/WACV2022/papers/Wilson_REFICS_A_Step_Towards_Linking_Vision_With_Hardware_Assurance_WACV_2022_paper.pdf)\n* [Deep Optimization Prior for THz Model Parameter Estimation](https://openaccess.thecvf.com/content/WACV2022/papers/Wong_Deep_Optimization_Prior_for_THz_Model_Parameter_Estimation_WACV_2022_paper.pdf)\n* [Sharing Decoders: Network Fission for Multi-Task Pixel Prediction](https://openaccess.thecvf.com/content/WACV2022/papers/Hickson_Sharing_Decoders_Network_Fission_for_Multi-Task_Pixel_Prediction_WACV_2022_paper.pdf)\n* [Fair Visual Recognition in Limited Data Regime using Self-Supervision and Self-Distillation](https://arxiv.org/abs/2107.00067)\n* [Low-Cost Multispectral Scene Analysis With Modality Distillation](https://openaccess.thecvf.com/content/WACV2022/papers/Zhang_Low-Cost_Multispectral_Scene_Analysis_With_Modality_Distillation_WACV_2022_paper.pdf)\n* [Self-Supervised Pretraining Improves Self-Supervised Pretraining](https://arxiv.org/abs/2103.12718)\n* [PROVES: Establishing Image Provenance Using Semantic Signatures](https://arxiv.org/abs/2110.11411)\n* [Addressing Out-of-Distribution Label Noise in Webly-Labelled Data](https://arxiv.org/abs/2110.13699)\u003cbr\u003e:star:[code](https://github.com/PaulAlbert31/DSOS)\n* [Towards Durability Estimation of Bioprosthetic Heart Valves via Motion Symmetry Analysis](https://openaccess.thecvf.com/content/WACV2022/papers/Alizadeh_Towards_Durability_Estimation_of_Bioprosthetic_Heart_Valves_via_Motion_Symmetry_WACV_2022_paper.pdf)\n* [Network Generalization Prediction for Safety Critical Tasks in Novel Operating Domains](https://arxiv.org/abs/2108.07399)\n* [Generalized Clustering and Multi-Manifold Learning With Geometric Structure Preservation](https://arxiv.org/abs/2009.09590)\u003cbr\u003e:star:[code](https://github.com/LirongWu/GCML)\n* [Batch Normalization Tells You Which Filter Is Important](https://arxiv.org/abs/2112.01155)\n* [Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity](https://arxiv.org/abs/2102.11382)\u003cbr\u003e:star:[code](https://github.com/VITA-Group/Sandwich-Batch-Normalizationhttps://arxiv.org/abs/2102.11382)\n* [Parsing Line Chart Images Using Linear Programming](https://openaccess.thecvf.com/content/WACV2022/papers/Kato_Parsing_Line_Chart_Images_Using_Linear_Programming_WACV_2022_paper.pdf)\n* [CrossLocate: Cross-Modal Large-Scale Visual Geo-Localization in Natural Environments Using Rendered Modalities](https://openaccess.thecvf.com/content/WACV2022/papers/Tomesek_CrossLocate_Cross-Modal_Large-Scale_Visual_Geo-Localization_in_Natural_Environments_Using_Rendered_WACV_2022_paper.pdf)\u003cbr\u003e:house:[project](http://cphoto.fit.vutbr.cz/crosslocate/)\n* [Symmetric-Light Photometric Stereo](https://openaccess.thecvf.com/content/WACV2022/papers/Minami_Symmetric-Light_Photometric_Stereo_WACV_2022_paper.pdf)\n* [REGroup: Rank-Aggregating Ensemble of Generative Classifiers for Robust Predictions](https://arxiv.org/abs/2006.10679)\u003cbr\u003e:house:[project](https://lokender.github.io/REGroup.html):star:[code](https://github.com/lokender/REGroup)\n* [Leveraging Test-Time Consensus Prediction for Robustness Against Unseen Noise](https://openaccess.thecvf.com/content/WACV2022/papers/Sarkar_Leveraging_Test-Time_Consensus_Prediction_for_Robustness_Against_Unseen_Noise_WACV_2022_paper.pdf)\n* [Supervised Compression for Resource-Constrained Edge Computing Systems](https://arxiv.org/abs/2108.11898)\u003cbr\u003e:star:[code](https://github.com/yoshitomo-matsubara/supervised-compression)\n* [Action Anticipation Using Latent Goal Learning](https://openaccess.thecvf.com/content/WACV2022/papers/Roy_Action_Anticipation_Using_Latent_Goal_Learning_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/debadityaroy/LatentGoal)\n* [Non-Semantic Evaluation of Image Forensics Tools: Methodology and Database](https://arxiv.org/abs/2105.02700)\n* [Inpaint2Learn: A Self-Supervised Framework for Affordance Learning](https://openaccess.thecvf.com/content/WACV2022/papers/Zhang_Inpaint2Learn_A_Self-Supervised_Framework_for_Affordance_Learning_WACV_2022_paper.pdf)\n* [RGL-NET: A Recurrent Graph Learning Framework for Progressive Part Assembly](https://openaccess.thecvf.com/content/WACV2022/papers/Narayan_RGL-NET_A_Recurrent_Graph_Learning_Framework_for_Progressive_Part_Assembly_WACV_2022_paper.pdf)\n* [Self-Supervised Knowledge Transfer via Loosely Supervised Auxiliary Tasks](https://arxiv.org/abs/2110.12696)\u003cbr\u003e:star:[code](https://github.com/generation21/Self-Supervised-Knowledge-Transfer-via-Loosely-Supervised-Auxiliary-Tasks)\n* [Novel Ensemble Diversification Methods for Open-Set Scenarios](https://openaccess.thecvf.com/content/WACV2022/papers/Farber_Novel_Ensemble_Diversification_Methods_for_Open-Set_Scenarios_WACV_2022_paper.pdf)\n* [Contrast To Divide: Self-Supervised Pre-Training for Learning With Noisy Labels](https://arxiv.org/abs/2103.13646)\u003cbr\u003e:star:[code](https://github.com/ContrastToDivide/C2D)\n* [Typenet: Towards Camera Enabled Touch Typing on Flat Surfaces Through Self-Refinement](https://openaccess.thecvf.com/content/WACV2022/papers/Maman_Typenet_Towards_Camera_Enabled_Touch_Typing_on_Flat_Surfaces_Through_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/benadar293/typeNet)\n* [Nonnegative Low-Rank Tensor Completion via Dual Formulation With Applications to Image and Video Completion](https://openaccess.thecvf.com/content/WACV2022/papers/Sinha_Nonnegative_Low-Rank_Tensor_Completion_via_Dual_Formulation_With_Applications_to_WACV_2022_paper.pdf)\n* [MisConv: Convolutional Neural Networks for Missing Data](https://openaccess.thecvf.com/content/WACV2022/papers/Przewiezlikowski_MisConv_Convolutional_Neural_Networks_for_Missing_Data_WACV_2022_paper.pdf)\n* [MAPS: Multimodal Attention for Product Similarity](https://openaccess.thecvf.com/content/WACV2022/papers/Das_MAPS_Multimodal_Attention_for_Product_Similarity_WACV_2022_paper.pdf)\n* [Global Assists Local: Effective Aerial Representations for Field of View Constrained Image Geo-Localization](https://openaccess.thecvf.com/content/WACV2022/papers/Rodrigues_Global_Assists_Local_Effective_Aerial_Representations_for_Field_of_View_WACV_2022_paper.pdf)\n* [Self-Supervised Test-Time Adaptation on Video Data](https://openaccess.thecvf.com/content/WACV2022/papers/Azimi_Self-Supervised_Test-Time_Adaptation_on_Video_Data_WACV_2022_paper.pdf)\n* [FT-DeepNets: Fault-Tolerant Convolutional Neural Networks With Kernel-Based Duplication](https://openaccess.thecvf.com/content/WACV2022/papers/Baek_FT-DeepNets_Fault-Tolerant_Convolutional_Neural_Networks_With_Kernel-Based_Duplication_WACV_2022_paper.pdf)\n* [Short-Term Solar Irradiance Prediction From Sky Images With a Clear Sky Model](https://openaccess.thecvf.com/content/WACV2022/papers/Gao_Short-Term_Solar_Irradiance_Prediction_From_Sky_Images_With_a_Clear_WACV_2022_paper.pdf)\n* [Reconstructing Training Data From Diverse ML Models by Ensemble Inversion](https://arxiv.org/abs/2111.03702)\n* [How Good Is Your Explanation? Algorithmic Stability Measures To Assess the Quality of Explanations for Deep Neural Networks](https://openaccess.thecvf.com/content/WACV2022/papers/Fel_How_Good_Is_Your_Explanation_Algorithmic_Stability_Measures_To_Assess_WACV_2022_paper.pdf)\n* [Seeing Implicit Neural Representations As Fourier Series](https://openaccess.thecvf.com/content/WACV2022/papers/Benbarka_Seeing_Implicit_Neural_Representations_As_Fourier_Series_WACV_2022_paper.pdf)\n* [Human-Aided Saliency Maps Improve Generalization of Deep Learning](https://arxiv.org/abs/2105.03492)\n* [Cross-Modal Adversarial Reprogramming](https://arxiv.org/abs/2102.07325)\n* [Learning From the CNN-Based Compressed Domain](https://openaccess.thecvf.com/content/WACV2022/papers/Wang_Learning_From_the_CNN-Based_Compressed_Domain_WACV_2022_paper.pdf)\n* [Spatiotemporal Initialization for 3D CNNs With Generated Motion Patterns](https://openaccess.thecvf.com/content/WACV2022/papers/Kataoka_Spatiotemporal_Initialization_for_3D_CNNs_With_Generated_Motion_Patterns_WACV_2022_paper.pdf)\u003cbr\u003e:house:[project](https://hirokatsukataoka16.github.io/Spatiotemporal-Initialization-for-3DCNNs/)\n* [DAD: Data-Free Adversarial Defense at Test Time](https://openaccess.thecvf.com/content/WACV2022/papers/Nayak_DAD_Data-Free_Adversarial_Defense_at_Test_Time_WACV_2022_paper.pdf)\n* [Geometry-Inspired Top-K Adversarial Perturbations](https://openaccess.thecvf.com/content/WACV2022/papers/Tursynbek_Geometry-Inspired_Top-K_Adversarial_Perturbations_WACV_2022_paper.pdf)\n* [Shape-Coded ArUco: Fiducial Marker for Bridging 2D and 3D Modalities](https://openaccess.thecvf.com/content/WACV2022/papers/Makabe_Shape-Coded_ArUco_Fiducial_Marker_for_Bridging_2D_and_3D_Modalities_WACV_2022_paper.pdf)\n* [Interpretable Semantic Photo Geolocation](https://openaccess.thecvf.com/content/WACV2022/papers/Theiner_Interpretable_Semantic_Photo_Geolocation_WACV_2022_paper.pdf)\u003cbr\u003e:star:[code](https://github.com/jtheiner/semantic_geo_partitioning)\n* [Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes](https://arxiv.org/abs/2110.09401)\u003cbr\u003e:star:[code](https://github.com/Fraunhofer-SCAI/conv_sr_mesh_autoencoder)\n* [Geometry-Aware Hierarchical Bayesian Learning on Manifolds](https://arxiv.org/abs/2111.00184)\n* [Transferable 3D Adversarial Textures Using End-to-End Optimization](https://openaccess.thecvf.com/content/WACV2022/papers/Pestana_Transferable_3D_Adversarial_Textures_Using_End-to-End_Optimization_WACV_2022_paper.pdf)\n* [Improving Fractal Pre-Training](https://arxiv.org/abs/2110.03091)\u003cbr\u003e:star:[code](https://github.com/catalys1/fractal-pretraining):house:[project](https://catalys1.github.io/fractal-pretraining/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F52cv%2Fwacv-2022-papers","html_url":"https://awesome.ecosyste.ms/projects/github.com%2F52cv%2Fwacv-2022-papers","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F52cv%2Fwacv-2022-papers/lists"}