https://github.com/shi-labs/human-object-interaction-detection
https://github.com/shi-labs/human-object-interaction-detection
Last synced: 8 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/shi-labs/human-object-interaction-detection
- Owner: SHI-Labs
- Created: 2020-09-12T16:24:35.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2020-10-11T21:00:53.000Z (almost 5 years ago)
- Last Synced: 2024-12-30T02:51:42.075Z (9 months ago)
- Size: 7.81 KB
- Stars: 27
- Watchers: 3
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Human-Object Interaction Detection: A Quick Survey and Examination of Methods
Our survey & examination paper[[ArXiv](https://arxiv.org/abs/2009.12950)]
```BibTex
@article{bergstrom20human,
title={Human-Object Interaction Detection: A Quick Survey and Examination of Methods},
author={Bergstrom, Trevor and Shi, Humphrey},
journal={The 1st International Workshop on Human-Centric Multimedia Analysis at ACM Multimedia Conference},
year={2020}
}
```
## Datasets
* HICO (Humans Interacting with Common Objects) [[paper](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Chao_HICO_A_Benchmark_ICCV_2015_paper.pdf)][[download](http://www-personal.umich.edu/~ywchao/hico/)]
* HICO-DET (Humans Interacting with Common Objects + Detection) [[paper](https://arxiv.org/pdf/1702.05448.pdf)][[download](http://www-personal.umich.edu/~ywchao/hico/)]
* COCO (Verbs in Coco) [[paper](https://arxiv.org/pdf/1505.04474.pdf)][[download](https://github.com/s-gupta/v-coco)]
* HCVRD (Human Centric Visual Relationship Detection) [[paper](https://arxiv.org/pdf/1705.09892.pdf)][[download](https://github.com/bohanzhuang/HCVRD-a-benchmark-for-large-scale-Human-Centered-Visual-Relationship-Detection)]
## Evaluation Metrics
To be updated soon.
## Papers
### Models:
* HORCNN (Learning to Detect Human-Object Interactions) - Chao, Yu-Wei and Liu, Yunfan and Liu, Xieyang and Zeng, Huayi and Deng, Jia [[paper](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Chao_HICO_A_Benchmark_ICCV_2015_paper.pdf)]
* InteractNet (Detecting and Recognizing Human-Object Interactions) - Gkioxari, Georgia and Girshick, Ross and Doll'ar, Piotr and He, Kaiming [[paper](https://arxiv.org/pdf/1704.07333.pdf)]
* iCAN (iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection) - Gao, Chen and Zou, Yuliang and Huang, Jia-Bin [[paper](https://arxiv.org/pdf/1808.10437.pdf)]
* GPNN (Learning Human-Object Interactions by Graph Parsing Neural Networks) - Qi, Siyuan and Wang, Wenguan and Jia, Baoxiong and Shen, Jianbing and Zhu, Song-Chun [[paper](https://arxiv.org/pdf/1808.07962.pdf)]
* Transferable Interactiveness Network (Transferable Interactiveness Prior for Human-Object Interaction Detection) - Li, Yong-Lu and Zhou, Siyuan and Huang, Xijie and Xu, Liang and Ma, Ze and Fang, Hao-Shu and Wang, Yan-Feng and Lu, Cewu [[paper](https://arxiv.org/pdf/1811.08264.pdf)]
* iHOI (Interact as you intend: Intention-driven human-object interaction detection) - Xu, Bingjie and Li, Junnan and Wong, Yongkang and Zhao, Qi and Kankanhalli, Mohan S [[paper](https://arxiv.org/pdf/1808.09796.pdf)]
* VS-GAT (Visual-Semantic Graph Attention Network for Human-Object Interaction Detection) - Liang, Zhijun and Guan, Yisheng and Rojas, Juan [[paper](https://arxiv.org/pdf/2001.02302.pdf)]
* VCL (Visual Compositional Learning for Human-Object Interaction Detection) - Hou, Zhi and Peng, Xiaojiang and Qiao, Yu and Tao, Dacheng [[paper](https://arxiv.org/pdf/2007.12407.pdf)]
* RPNN (Relation Parsing Neural Network for Human-Object Interaction Detection) - Zhou, Penghao and Chi, Mingmin [[paper](https://openaccess.thecvf.com/content_ICCV_2019/papers/Zhou_Relation_Parsing_Neural_Network_for_Human-Object_Interaction_Detection_ICCV_2019_paper.pdf)]
* Cascaded HOI Detection (Cascaded Human-Object Interaction Recognition) - Zhou, Tianfei and Wang, Wenguan and Qi, Siyuan and Ling, Haibin and Shen, Jianbing [[paper](https://arxiv.org/pdf/2003.04262.pdf)]
* SIGN (Skeleton-Based Interactive Graph Network For Human Object Interaction Detection) - Zheng, Sipeng and Chen, Shizhe and Jin, Qin [[paper](https://ieeexplore.ieee.org/document/9102755)]
* PPDM (PPDM: Parallel Point Detection and Matching for Real-Time Human-Object Interaction Detection) - Liao, Yue and Liu, Si and Wang, Fei and Chen, Yanjie and Qian, Chen and Feng, Jiashi [[paper](https://arxiv.org/pdf/1912.12898.pdf)]
* PMN (Pose-based Modular Network for Human-Object Interaction Detection) - Liang, Zhijun and Liu, Junfa and Guan, Yisheng and Rojas, Juan [[paper](https://arxiv.org/pdf/2008.02042.pdf)]
* Compositional Learning (Compositional Learning for Human Object Interaction) - Kato, Keizo and Li, Yin and Gupta, Abhinav [[paper](https://openaccess.thecvf.com/content_ECCV_2018/papers/Keizo_Kato_Compositional_Learning_of_ECCV_2018_paper.pdf)]
* (Learning to Detect Human-Object Interactions with Knowledge) - Xu, Bingjie and Wong, Yongkang and Li, Junnan and Zhao, Qi and Kankanhalli, Mohan S [[paper](https://www-users.cs.umn.edu/~qzhao/publications/pdf/xu2019cvpr.pdf)]
* (Modeling Mutual Context of Object and Human Pose in Human-Object Interaction Activities) - Yao, Bangpeng and Fei-Fei, Li [[paper](http://vision.stanford.edu/pdf/YaoFei-Fei_CVPR2010b.pdf)]
To be updated soon.
## Code
Code can be found here for now: https://github.com/trevorbergstrom/HOI-Toolkit
Will be added to this repo soon.