BiCTM: lightweight video recognition via convolutional tube masking and bidirectional motion features
- 11 July 2026
- journal article
- research article
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (6) , 402
Abstract
No abstract availableKeywords
Funding Information
- Sichuan Provincial Science and Technology Support Program (2025NSFSC2017)
- National Natural Science Foundation of China (62576295)
- Scientic Research Funds project of Science and Technology Department of Sichuan Province (2023YFG0354)
This publication has 61 references indexed in Scilit:
- VideoMamba: State Space Model for Efficient Video Understanding2024
- Spatio-temporal adaptive convolution and bidirectional motion difference fusion for video action recognitionExpert Systems with Applications, 2024
- Frozen CLIP Models are Efficient Video Learners2022
- EAN: Event Adaptive Network for Enhanced Action RecognitionInternational Journal of Computer Vision, 2022
- AR-Net: Adaptive Frame Resolution for Efficient Action Recognition2020
- MotionSqueeze: Neural Motion Feature Learning for Video Understanding2020
- ECO: Efficient Convolutional Network for Online Video Understanding2018
- Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification2018
- Videos as Space-Time Region Graphs2018
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition2016