AR-Net: Adaptive Frame Resolution for Efficient Action Recognition
Authors:
- 9 November 2020
- book chapter
- Published by Springer Nature
- p. 86-104
Abstract
No abstract availableKeywords
All Related Versions
This publication has 45 references indexed in Scilit:
- SlowFast Networks for Video Recognition2019
- Training Compact Deep Learning Models for Video Classification Using Circulant Matrices2019
- Watching a Small Portion could be as Good as Watching All: Towards Efficient Video Classification2018
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- More is Less: A More Complicated Network with Less Inference Complexity2017
- A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection2016
- P-CNN: Pose-Based CNN Features for Action Recognition2015
- Long-term recurrent convolutional networks for visual recognition and description2015
- ActivityNet: A large-scale video benchmark for human activity understanding2015
- ImageNet: A large-scale hierarchical image database2009