STD-TR: End-to-End Spatio-Temporal Action Detection with Transformers-Reference-Cited by-同舟云学术

STD-TR: End-to-End Spatio-Temporal Action Detection with Transformers

Author:

Li Zexian¹,Wang Tian²,Zhu Aichun³,Liu Kexin⁴,Shi Peng⁵,Snoussi Hichem⁶

Affiliation:

1. Beihang University,School of Automation Science and Electrical Engineering,Beijing,China

2. Nanjing University of Science and Technology,Jiangsu Key Laboratory of Image and Video Understanding for Social Safety,Nanjing,China

3. Beihang University,Institute of Artificial Intelligence,Beijing,China

4. Nanjing Tech University,School of Computer Science and Technology,Nanjing,China

5. Fujian Normal University,School of Mathematics and Computer Science,Fujian,China

6. University of Technology of Troyes,Institute Charles Delaunay-LM2S,Troyes,France

Funder

Research and Development

National Natural Science Foundation of China

Fundamental Research Funds for the Central Universities

Publisher

IEEE

Link

Reference17 articles.

1. Yolov3: An incremental improvement;redmon;arXiv preprint arXiv 1804 02767,2018

2. End-to-end object detection with transformers;carion;European Conference on Computer Vision,2020

3. The kinetics human action video dataset;kay;arXiv preprint arXiv 1705 06950,2017

5. Fixing weight decay regularization in adam;loshchilov,2018

Cited by 4 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

2. Self-Feedback DETR for Temporal Action Detection;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01

3. Human Action Detection Based on Multimodal Feature Fusion for Human-Robot Collaborative Assembly;2023 IEEE 19th International Conference on Automation Science and Engineering (CASE);2023-08-26