Efficient Video Transformers with Spatial-Temporal Token Selection
- 4 November 2022
- book chapter
- Published by Springer Nature
- p. 69-86
Abstract
No abstract availableKeywords
All Related Versions
This publication has 47 references indexed in Scilit:
- ECO: Efficient Convolutional Network for Online Video Understanding2018
- A Closer Look at Spatiotemporal Convolutions for Action Recognition2018
- Large-Scale Content-Only Video Recommendation2017
- The “Something Something” Video Database for Learning and Evaluating Visual Common Sense2017
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- Real-time Video Recommendation Exploration2016
- End-to-End Learning of Action Detection from Frame Glimpses in Videos2016
- Convolutional Two-Stream Network Fusion for Video Action Recognition2016
- Contextual Video Recommendation by Multimodal Relevance and User FeedbackACM Transactions on Information Systems, 2011
- The YouTube video recommendation system2010