Attention in Attention: Modeling Context Correlation for Efficient Video Classification-Reference-Cited by-同舟云学术

Attention in Attention: Modeling Context Correlation for Efficient Video Classification

Published:2022-10 Issue:10 Volume:32 Page:7120-7132
ISSN:1051-8215
Container-title:IEEE Transactions on Circuits and Systems for Video Technology
language:
Short-container-title:IEEE Trans. Circuits Syst. Video Technol.

Author:

Hao Yanbin¹^ORCID,Wang Shuo¹^ORCID,Cao Pei²^ORCID,Gao Xinjian³^ORCID,Xu Tong⁴^ORCID,Wu Jinmeng⁵,He Xiangnan¹^ORCID

Affiliation:

1. CCCD Key Laboratory of Ministry of Culture and Tourism, School of Data Science and School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China

2. Wuhan Research Institute of Posts and Telecommunications, Wuhan, Hubei, China

3. School of Computer Science and Information Engineering and the School of Artificial Intelligence, Hefei University of Technology, Hefei Anhui, China

4. School of Data Science and the School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China

5. Hubei Key Laboratory of Optical Information and Pattern Recognition, Wuhan Institute of Technology, Wuhan, Hubei, China

Funder

National Key Research and Development Program of China

National Natural Science Foundation of China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Media Technology

Link

http://xplorestaging.ieee.org/ielx7/76/9910246/09762292.pdf?arnumber=9762292

Reference58 articles.

1. RESOUND: Towards Action Recognition Without Representation Bias

2. On the effectiveness of task granularity for transfer learning;mahdisoltani;arXiv 1804 09235,2018

3. Recurrent prediction with spatio-temporal attention for crowd attribute recognition;li;IEEE Trans Circuits Syst Video Technol,2020

4. stagNet: An Attentive Semantic RNN for Group Activity and Individual Action Recognition

5. Two-Stream Collaborative Learning With Spatial-Temporal Attention for Video Classification

Cited by 32 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

1. A dual-prototype network combining query-specific and class-specific attentive learning for few-shot action recognition;Neurocomputing;2024-09

2. FineTea: A Novel Fine-Grained Action Recognition Video Dataset for Tea Ceremony Actions;Journal of Imaging;2024-08-31

3. Enhanced Pseudo-Label Generation With Self-Supervised Training for Weakly- Supervised Semantic Segmentation;IEEE Transactions on Circuits and Systems for Video Technology;2024-08

4. PosMLP-Video: Spatial and Temporal Relative Position Encoding for Efficient Video Recognition;International Journal of Computer Vision;2024-06-27

5. Channel-Blind Joint Source–Channel Coding for Wireless Image Transmission;Sensors;2024-06-20