Multi-cue based four-stream 3D ResNets for video-based action recognition
Authors:
- Lei WangLWLei Wang
- Xiaoguang YuanXYXiaoguang Yuan
- Ming ZongMZMing Zong
- Yujun MaYMYujun Ma
- Wanting JiWJWanting Ji
- Mingzhe LiuMLMingzhe Liu
- Ruili WangRWRuili Wang
- 1 October 2021
- journal article
- research article
- Published by Elsevier in Information Sciences
- Vol. 575, 654-665
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (U19A2086)
- China Scholarship Council
This publication has 27 references indexed in Scilit:
- Stochastic configuration networks ensemble with heterogeneous features for large-scale data analyticsInformation Sciences, 2017
- Three-stream CNNs for action recognitionPattern Recognition Letters, 2017
- Beyond Frame-level CNN: Saliency-Aware 3-D CNN With LSTM for Video Action RecognitionIEEE Signal Processing Letters, 2016
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition2016
- Saliency-context two-stream convnets for action recognition2016
- Group-Based Alternating Direction Method of Multipliers for Distributed Linear ClassificationIEEE Transactions on Cybernetics, 2016
- Saliency guided local and global descriptors for effective action recognitionComputational Visual Media, 2016
- Human action recognition via multi-task learning base on spatial–temporal featureInformation Sciences, 2015
- Feature selection for least squares projection twin support vector machineNeurocomputing, 2014
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998