Motion-driven Visual Tempo Learning for Video-based Action Recognition

The proposed Temporal Correlation Module (TCM) to deal with the variation of action visual tempo in videos, which includes a Multi-scale Temporal Dynamics Module (MTDM) and a Temporal Attention Module (TAM).

Data and Resources

Cite this as

Yuanzhong Liu, Junsong Yuan, Zhigang Tu (2024). Dataset: Motion-driven Visual Tempo Learning for Video-based Action Recognition. https://doi.org/10.57702/95g100ad

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Yuanzhong Liu
More Authors
Junsong Yuan
Zhigang Tu
Homepage https://github.com/yzfly/TCM