Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/alisure-ml/awesome-visual-relationship-detection

A curated list of visual relationship detection and related area resources
https://github.com/alisure-ml/awesome-visual-relationship-detection

List: awesome-visual-relationship-detection

object-detection object-recognition scene-graph visual-relationship-detection vrd

Last synced: 3 months ago
JSON representation

A curated list of visual relationship detection and related area resources

Awesome Lists containing this project

README 

        
# Awesome Visual Relationship Detection: ![Awesome](https://img.shields.io/david/peer/https://github.com/alisure-ml/awesome-visual-relationship-detection/ww.svg?colorB=green&label=VRD&logo=ww&logoColor=yellow)



A curated list of visual relationship detection and related area (e.g. object detection, scene graph) resources, inspired by [awesome-computer-vision](https://github.com/jbhuang0604/awesome-computer-vision).



## Contents

 - [Visual Relationship Detection](#visual-relationship-detection)

 - [Object Recognition](#object-recognition)



## Visual Relationship Detection



### Visual Relationship Detection

* `NIPS 2017` - [Pixels to Graphs by Associative Embedding ](https://arxiv.org/pdf/1706.07365.pdf) Alejandro -et al.[[offical code]](https://github.com/princeton-vl/px2graph)



* `2018` - [Attentive Relational Networks for Mapping Images to Scene Graphs](https://arxiv.org/abs/1811.10696v1) Mengshi Qi et al.



* `AAAI 2019` - [Large-Scale Visual Relationship Understanding](https://arxiv.org/abs/1804.10660) - Ji Zhang et al, AAAI 2019.



* `2018` - [Improving Visual Relationship Detection using Semantic Modeling of Scene Descriptions](https://arxiv.org/abs/1809.00204) - Stephan Baier et al.



* `AAAI 2018` - [Visual Relationship Detection with Deep Structural Ranking](http://vipl.ict.ac.cn/uploadfile/upload/2018030615400539.pdf) - Kongming Liang et al, AAAI 2018, [[official pytorch=0.2.0 code]](https://github.com/GriffinLiang/vrd-dsr).



* `ECCV 2018` - [Visual Relationship Prediction via Label Clustering and Incorporation of Depth Information](https://arxiv.org/abs/1809.02945) - Hsuan-Kung Yang et al, ECCV 2018 workshop.



* `ECCV 2018` - [Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features](https://arxiv.org/abs/1808.00171) - Xu Yang et al, ECCV 2018, [[tensorflow]](https://github.com/yangxuntu/vrd)



* `CVPR 2018` - [Relation Networks for Object Detection](https://arxiv.org/abs/1711.11575) - Han Hu et al, CVPR 2018 oral paper, [[official MXNet code]](https://github.com/msracver/Relation-Networks-for-Object-Detection), [[pytorch]](https://github.com/heefe92/Relation_Networks-pytorch).



* `CVPR 2018` - [Tensorize, Factorize and Regularize: Robust Visual Relationship Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Hwang_Tensorize_Factorize_and_CVPR_2018_paper.pdf) - Seong Jae Hwang et al, CVPR 2018.



* `CVPR 2018` - [Referring Relationships](https://github.com/StanfordVL/ReferringRelationships) - Ranjay Krishna et al, , [[official keras code]](https://github.com/StanfordVL/ReferringRelationships).



* `ICME 2018` - [Visual Relationship Detection Based on Guided Proposals and Semantic Knowledge Distillation](https://arxiv.org/abs/1805.10802) - François Plesse et al, ICME 2018.



* `2018` - [Natural Language Guided Visual Relationship Detection](https://arxiv.org/abs/1711.06032) - Wentong Liao et al.



* `ACM MM 2018` - [Context-Dependent Diffusion Network for Visual Relationship Detection](https://arxiv.org/abs/1809.06213) - Zhen Cui et al, 2018 ACM Multimedia Conference.



* `ICCV 2017` - [PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN](https://arxiv.org/abs/1708.01956) - Hanwang Zhang et al, ICCV 2017. [[official Matlab code]](https://github.com/yjy941124/PPR-FCN)



* `ICCV 2017` - [Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues](https://arxiv.org/abs/1611.06641) - Bryan A. Plummer et al, ICCV 2017, [[official Matlab code]](https://github.com/BryanPlummer/pl-clc).



* `ICCV 2017` - [Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation](https://arxiv.org/abs/1707.09423) - Ruichi Yu et al, ICCV 2017.



* `ICCV 2017` - [Weakly-supervised learning of visual relations](https://arxiv.org/abs/1707.09472) - Julia Peyre et al, ICCV 2017, [[official Matlab code]](https://github.com/jpeyre/unrel).



* `CVPR 2017` - [Detecting Visual Relationships with Deep Relational Networks](https://arxiv.org/abs/1704.03114) - Bo Dai et al, CVPR 2017 oral, [[official caffe code]](https://github.com/doubledaibo/drnet_cvpr2017)



* `CVPR 2017` - [ViP-CNN: Visual Phrase Guided Convolutional Neural Network](https://arxiv.org/abs/1702.07191) - Yikang Li et al, CVPR 2017.



* `CVPR 2017` - [Scene Graph Generation by Iterative Message Passing](https://arxiv.org/abs/1701.02426) - Danfei Xu et al, CVPR 2017.



* `CVPR 2017` - [Deep Variation-Structured Reinforcement Learning for Visual Relationship and Attribute Detection](https://arxiv.org/abs/1703.03054) - Xiaodan Liang et al, CVPR 2017, [[pytorch]](https://github.com/nexusapoorvacus/DeepVariationStructuredRL).



* `CVPR 2017` - [Relationship Proposal Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Zhang_Relationship_Proposal_Networks_CVPR_2017_paper.html) - Ji Zhang et al, CVPR 2017.



* `CVPR 2017` - [Visual Translation Embedding Network for Visual Relation Detection](https://arxiv.org/abs/1702.08319) - Hanwang Zhang et al, CVPR 2017.



* `ECCV 2016` - [Visual Relationship Detection with Language Priors](https://cs.stanford.edu/people/ranjaykrishna/vrd/vrd.pdf) - Lu et al, ECCV 2016 Oral, [[official Matlab code]](https://github.com/Prof-Lu-Cewu/Visual-Relationship-Detection).



### Scene Graph

* `CVPR 2018` - [Neural Motifs: Scene Graph Parsing with Global Context](https://arxiv.org/abs/1711.06640) - Rowan Zellers et al, CVPR 2018, [[official pytorch=0.3.0 code]](https://github.com/rowanz/neural-motifs).



* `IJCAI 2018` - [Representation Learning for Scene Graph Completion via Jointly Structural and Visual Embedding](https://www.ijcai.org/proceedings/2018/0132.pdf) - Hai Wan et al, IJCAI-18.



* `ICCV 2017` - [Scene Graph Generation From Objects, Phrases and Region Captions](http://openaccess.thecvf.com/content_iccv_2017/html/Li_Scene_Graph_Generation_ICCV_2017_paper.html) - Yikang Li et al, ICCV 2017.

* `CVPR 2017` - [Scene Graph Generation by Iterative Message Passing](https://arxiv.org/pdf/1701.02426.pdf) - Danfei Xu et al, CVPR 2017.



### Video Visual Relation Detection



* `ACM MM 2017` - [Video Visual Relation Detection](http://lms.comp.nus.edu.sg/research/VidVRD/VidVRD-MM17.pdf) - Xindi Shang et al, 2017 ACM Multimedia Conference, [Video Visual Relation Detection](http://software.nju.edu.cn/rentw/publication/mm17-shangxd_pot.pdf)



### Dataset



* `The Open Images Dataset V4`, `IJCV 2018` - [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://arxiv.org/abs/1811.00982) - Alina Kuznetsova et al, IJCV 2018.



* `Visual Genome`, `2016` - [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://visualgenome.org/static/paper/Visual_Genome.pdf) - Ranjay Krishna et al, [official web] (https://visualgenome.org/).



* `VRD`, `ECCV 2016` - [Visual Relationship Detection with Language Priors](https://cs.stanford.edu/people/ranjaykrishna/vrd/) - Lu et al, ECCV 2016 Oral.



* `VidVRD`, `ACM MM 2017` - [Video Visual Relation Dataset](https://lms.comp.nus.edu.sg/research/VidVRD.html) - Xindi Shang et al, 2018 ACM Multimedia Conference, [VidVRD-helper](https://github.com/xdshang/VidVRD-helper).



## Object Recognition



### Object Detection

* `ICCV 2017` - [Deformable Convolutional Networks](http://openaccess.thecvf.com/content_ICCV_2017/papers/Dai_Deformable_Convolutional_Networks_ICCV_2017_paper.pdf) - J. Dai et al., ICCV 2017. [[official code]](https://github.com/msracver/Deformable-ConvNets)



* `FacebookResearch` - [Detectron](https://github.com/facebookresearch/Detectron) - Open Source Object Detection Framework from Facebook AI Research. Includes Mask R-CNN, FPN, and etc. Caffe2 implementation.



* `ICCV 2017` - [Mask R-CNN](https://arxiv.org/abs/1703.06870) - K. He et al, [[Detectron]](https://github.com/facebookresearch/Detectron), [[TensorFlow + Keras]](https://github.com/matterport/Mask_RCNN), [[MXNet]](https://github.com/TuSimple/mx-maskrcnn), [[TensorFlow]](https://github.com/CharlesShang/FastMaskRCNN), [[PyTorch]](https://github.com/felixgwu/mask_rcnn_pytorch) - State-of-the-art object detection/instance segmentation algorithm.



* `NIPS 2015` - [Faster R-CNN](https://arxiv.org/abs/1506.01497) - S. Ren et al, NIPS2015. [[official MatCaffe code]](https://github.com/ShaoqingRen/faster_rcnn), [[PyCaffe]](https://github.com/rbgirshick/py-faster-rcnn), [[TensorFlow]](https://github.com/smallcorgi/Faster-RCNN_TF), [[Another TF implementation]](https://github.com/CharlesShang/TFFRCNN) [[Keras]](https://github.com/yhenon/keras-frcnn) - State-of-the-art object detector.



* `CVPR 2016` - [YOLO](https://pjreddie.com/media/files/papers/yolo.pdf) - J. Redmon et al, CVPR2016. [[official code]](https://github.com/pjreddie/darknet.git), [[TensorFLow]](https://github.com/gliese581gg/YOLO_tensorflow) - Fast object detector.



* `CVPR 2017` - [YOLO9000](https://arxiv.org/abs/1612.08242) - J. Redmon and A. Farhadi, CVPR2017. [[official code]](https://pjreddie.com/darknet/yolo/) - State-of-the-art object detector which can detect 9000 objects in realtime.



* `ECCV 2016` - [SSD](https://arxiv.org/abs/1512.02325) - W. Liu et al, ECCV2016. [[official PyCaffe code]](https://github.com/weiliu89/caffe/tree/ssd), [[TensorFlow]](https://github.com/balancap/SSD-Tensorflow), [[Keras]](https://github.com/rykov8/ssd_keras) - State-of-the-art object detector with realtime processing speed.



* `ICCV 2017` - [RetinaNet](https://arxiv.org/abs/1708.02002) - Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He and Piotr Dollár, Facebook AI Research FAIR & ICCV 2017.[[Keras]](https://github.com/fizyr/keras-retinanet) - State-of-the-art object detector with realtime processing speed.



### Video Object Detection

* `ICCV 2017` - [Detect to Track and Track to Detect] - C. Feichtenhofer et al., ICCV2017. [[code]](https://github.com/feichtenhofer/detect-track), [[project web]](http://www.robots.ox.ac.uk/~vgg/research/detect-track/)



* `ICCV 2017` - [Flow-Guided Feature Aggregation for Video Object Detection] - X. Zhu et al., ICCV2017. [[code]](https://github.com/msracver/Flow-Guided-Feature-Aggregation), aka FGFA



### Video Object Detection Datasets

* [ImageNet VID](http://image-net.org/challenges/LSVRC/2017/download-images-1p39.php)



* [YouTube-8M](https://research.google.com/youtube8m/), [technical report](https://arxiv.org/abs/1609.08675)



* [YouTube-BB](https://research.google.com/youtube-bb/), [technical report](https://arxiv.org/pdf/1702.00824.pdf)



## Licenses

License



[![CC0](http://i.creativecommons.org/p/zero/1.0/88x31.png)](http://creativecommons.org/publicdomain/zero/1.0/)



To the extent possible under law, [ALISURE](https://github.com/alisure-ml/) has waived all copyright and related or neighboring rights to this work.



## Contributing

Please feel free to send me [pull requests](https://github.com/alisure-ml/awesome-visual-relationship-detection/pulls) or email ([email protected]) to add links.