CVPR2019 | Papers on Behavior/Action Recognition, Gesture Recognition, Timing Action Detection and Video Related

CVPR2019 | Papers on Behavior/Action Recognition, Gesture Recognition, Timing Action Detection and Video Related

Behavior/action recognition, gesture recognition

1. An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based
Action
Recognition Tan
paper link: https://arxiv.org/abs/1902.09130

2. Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training
Chinese: Multimodal training improves the performance of single-modal dynamic gesture recognition
Authors: Mahdi Abavisani, Hamid Reza Vaezi Joze, Vishal M. PatelLink
: https://arxiv .org/abs/1812.06145

3. Collaborative Spatio-temporal Feature Learning for Video Action Recognition
Chinese: Application of Collaborative Spatio-temporal Feature Learning in Video Action Recognition
Authors: Chao Li, Qiaoyong Zhong, Di Xie, Shiliang Pu
Paper link: https://arxiv.org/abs /1903.01197

4. Peeking into the Future: Predicting Future Person Activities and Locations in Videos
Authors
: Junwei Liang, Lu Jiang, Juan Carlos Niebles, Alexander Hauptmann, Li Fei-Fei
paper link: https://arxiv.org/abs/1902.03748

5. Neural Scene Decomposition for Multi-Person Motion Capture
Chinese: Neural Scene Decomposition for Multi-Person Motion Capture
Authors: Helge Rhodin, Victor Constantin, Isinsu Katircioglu, Mathieu Salzmann, Pascal Fua
Paper link: https://arxiv.org/abs/ 1903.05684

6. Action Recognition from Single Timestamp Supervision in Untrimmed Videos (action recognition)
Chinese: Untrimmed Video Action Recognition Based on Single Timestamp Supervision
Authors: Davide Moltisanti, Sanja Fidler, Dima Damen
Paper link: https://arxiv.org/abs /1904.04689

7. Pushing the Envelope for RGB-based Dense 3D Hand Pose
Estimation via
Neural
Rendering arxiv.org/abs/1904.04196

8. Relational Action Forecasting (oral)
Chinese: Relational Action Prediction
Authors: Chen Sun, Abhinav Shrivastava, Carl Vondrick, Rahul Sukthankar, Kevin Murphy, Cordelia Schmid
Paper link: https://arxiv.org/abs/1904.04231

9. H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions
(
Oral
) : https://arxiv.org/abs/1904.05349

10. Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition
Chinese: Out-of-distribution detection for generalized zero-shot action recognition
Authors: Devraj Mandal, Sanath Narayan, Saikumar Dwivedi, Vikram Gupta, Shuaib Ahmed, Fahad Shahbaz Khan, Ling Shao
paper Link: https://arxiv.org/abs/1904.08703

11. Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
Chinese: Action Structure Graph Convolutional Network Based on Skeleton Action Recognition
Authors: Maosen Li, Siheng Chen, Xu Chen, Ya Zhang, Yanfeng Wang, and Qi Tian
Paper link: https://arxiv.org/pdf/1904.12659

12. A neural network based on SPD manifold learning for skeleton-based hand gesture recognition
Chinese: Application of neural network based on SPD manifold learning for skeleton-based hand gesture recognition
Authors: Xuan Son Nguyen, Luc Brun, Olivier Lézoray, Sébastien Bougleux
Paper link: https://arxiv.org/abs/1904.12970

13. DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition (
Facebook
) Kalantidis, Laura Sevilla-Lara, Marcus Rohrbach, Shih-Fu Chang, Zhicheng Yan
paper link: https://arxiv.org/abs/1901.03460

Timing motion detection and video correlation

1. Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning
Chinese: Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video
Captioning Authors: Nayyer Aafaq, Naveed Akhtar, Wei Liu, Syed Zulqarnain Gilani, Ajmal Mian
Paper link: https: //arxiv.org/abs/1902.10322
Source: https://mp.weixin.qq.com/s/61C-k3Ijy_7ry5B5lRML6Q

2. Single-frame Regularization for Temporally Stable CNNs (Video Processing)
Chinese: Single-frame regularization method for temporally stable CNNs
Authors: Gabriel Eilertsen, Rafał K. Mantiuk, Jonas Unger
Paper link: https://arxiv.org/abs/ 1902.10424
Source: https://mp.weixin.qq.com/s/61C-k3Ijy_7ry5B5lRML6Q

3. Neural RGB-D Sensing: Depth estimation from a video Camera
Chinese: Neural RGB-D Sensing: Camera Depth Estimation
Authors: Chao Liu, Jinwei Gu, Kihwan Kim, Srinivasa Narasimhan, Jan Kautz
Paper link: https://arxiv .org/abs/1901.02571
project link: https://research.nvidia.com/publication/2019-06_Neural-RGBD

4. Competitive Collaboration: Joint Unsupervised Learning of Depth, CameraMotion, Optical Flow and
Motion
Segmentation Sun, Jonas Wulff, Michael J. Black
paper link: https://arxiv.org/abs/1805.09806

5. Representation Flow for Action Recognition
Chinese: Representation Flow for Action Recognition
Authors: AJ Piergiovanni, Michael S. Ryoo
Paper link: https://arxiv.org/abs/1810.01455
Project link: https://piergiaj.github.io/ rep-flow-site/
code link: https://github.com/piergiaj/representation-flow-cvpr19

6. Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos
Chinese: Learning Regularity of Skeleton Trajectories in Video Anomaly Detection
Authors: Romero Morais, Vuong Le, Truyen Tran, Budhaditya Saha, Moussa Mansour, Svetha Venkatesh
Paper link: https://arxiv .org/abs/1903.03295

7. Video Generation from Single Semantic Label Map
Chinese: Generate video from a single semantic label map
Authors: Junting Pan, Chengyu Wang, Xu Jia, Jing Shao, Lu Sheng, Junjie Yan, Xiaogang Wang
Paper link: https://arxiv.org /abs/1903.04480
Source link: https://github.com/junting/seg2vid/tree/master

8. Inserting Videos into Videos
Chinese: Inserting videos into videos
Authors: Donghoon Lee, Tomas Pfister, Ming-Hsuan Yang
Paper link: https://arxiv.org/abs/1903.06571

9. Recurrent Back-Projection Network for Video Super-Resolution
Chinese: Recurrent Back-Projection Network for Video Super-Resolution
Author: Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita
Paper Link: https://arxiv.org/abs/1903.10128
Code Link: https://github.com/alterzero/RBPN-PyTorch
project link: https://alterzero.github.io/projects/RBPN.html

10. Depth-Aware Video Frame Interpolation
Chinese:
Authors: Wenbo Bao Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang
Paper link: https://sites.google.com/view/wenbobao/ dain
     https://arxiv.org/abs/1904.00830
code link: https://github.com/baowenbo/DAIN

11. Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph
Chinese: Video Relationship Reasoning Using Gated Spatio-Temporal Energy Graph
Authors: Yao-Hung Hubert Tsai, Santosh Divvala, Louis-Philippe Morency, Ruslan Salakhutdinov, Ali Farhadi
Paper link: https: https://arxiv.org/abs/1903.10547

12. Dual Encoding for Zero-Example Video Retrieval
Chinese: Dual Encoding Realizes Zero-Sample Video Retrieval
Authors: Jianfeng Dong, Xirong Li, Chaoxi Xu, Shouling Ji, Yuan He, Gang Yang and Xun Wang
Paper link: https://arxiv. org/abs/1809.06181
code link: https://github.com/danieljf24/dual_encoding

13. Rethinking the Evaluation of Video Summaries
Chinese: Rethinking the Evaluation of Video Summaries
Authors: Jacques Manderscheid, Amos Sironi, Nicolas Bourdis, Davide Migliore, Vincent Lepetit
Paper link: https://arxiv.org/abs/1903.11328

14. End-to-End Time-Lapse Video Synthesis from a Single Outdoor Image
Chinese: End-to-end time-lapse video synthesis from a single outdoor image
Authors: Seonghyeon Nam, Chongyang Ma, Menglei Chai, William Brendel, Ning Xu, Seon Joo Link to Kim's
paper: https://arxiv.org/abs/1904.00680

15. GolfDB: A Video Database for Golf Swing Sequencing
Chinese: GolfDB: A Video Database for Golf Swing Sequencing
Authors: William McNally, Kanav Vats, Tyler Pinto, Chris Dulhanty, John McPhee, Alexander Wong
Paper link: https:/ /arxiv.org/abs/1903.06528v1

16. VORNet: Spatio-temporally Consistent Video Inpainting for Object Removal
Chinese: VORNet: Spatio-temporally Consistent Video Inpainting for Object Removal
Authors: Ya-Liang Chang, Zhe Yu Liu, Winston Hsu
Paper link: https://arxiv. org/abs/1904.06726

17. STEP: Spatio-Temporal Progressive Learning for Video Action Detection (Oral)
Chinese: Step: Spatio-Temporal Progressive Learning for Video Action Detection
Authors: Xitong Yang, Xiaodong Yang, Ming-Yu Liu, Fanyi Xiao, Larry Davis, Jan Kautz
Paper link: https://arxiv.org/abs/1904.09288

18. UnOS: Unified Unsupervised Optical-flow and Stereo-depth Estimation by
Watching
Videos Yang, and Wei Xu
paper link: https://arxiv.org/abs/1810.03654

19. Memory-Attended Recurrent Network for Video Captioning
Chinese: Memory-specific recurrent network for video subtitles
Authors: Wenjie Pei, Jiyuan Zhang, Xiangrong Wang, Lei Ke, Xiaoyong Shen, Yu-Wing Tai
Paper link: https://arxiv .org/abs/1905.03966