BDTSNet: A novel bidirectional two-stream network for video-based human action recognition
Authors:
- Chuanjiang LengCLChuanjiang Leng
- Chengdong WuCWChengdong Wu
- Ange ChenACAnge Chen
- Hexiao LiHLHexiao Li
- Hao WuHWHao Wu
- 15 April 2026
- journal article
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 146
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (61973065)
- National Natural Science Foundation of China (U20A20197)
This publication has 59 references indexed in Scilit:
- BDNet: a method based on forward and backward convolutional networks for action recognition in videosThe Visual Computer, 2023
- Multiple temporal scale aggregation graph convolutional network for skeleton-based action recognitionComputers and Electrical Engineering, 2023
- Human action recognition in complex live videos using graph convolutional networkComputers and Electrical Engineering, 2023
- A review of video action recognition based on 3D convolutionComputers and Electrical Engineering, 2023
- Adaptive 2D skeleton deformation based on view agnostic network for action recognitionComputers and Electrical Engineering, 2022
- A Coarse-to-Fine Framework for Resource Efficient Video RecognitionInternational Journal of Computer Vision, 2021
- Human action recognition method based on historical point cloud trajectory characteristicsThe Visual Computer, 2021
- VDARN: Video Disentangling Attentive Relation Network for Few-Shot and Zero-Shot Action RecognitionAd Hoc Networks, 2021
- Temporal Relational Reasoning in Videos2018
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition2016