English

Entity-aware and Motion-aware Transformers for Language-driven Action Localization in Videos

Computer Vision and Pattern Recognition 2022-05-13 v1 Multimedia

Abstract

Language-driven action localization in videos is a challenging task that involves not only visual-linguistic matching but also action boundary prediction. Recent progress has been achieved through aligning language query to video segments, but estimating precise boundaries is still under-explored. In this paper, we propose entity-aware and motion-aware Transformers that progressively localizes actions in videos by first coarsely locating clips with entity queries and then finely predicting exact boundaries in a shrunken temporal region with motion queries. The entity-aware Transformer incorporates the textual entities into visual representation learning via cross-modal and cross-frame attentions to facilitate attending action-related video clips. The motion-aware Transformer captures fine-grained motion changes at multiple temporal scales via integrating long short-term memory into the self-attention module to further improve the precision of action boundary prediction. Extensive experiments on the Charades-STA and TACoS datasets demonstrate that our method achieves better performance than existing methods.

Keywords

Cite

@article{arxiv.2205.05854,
  title  = {Entity-aware and Motion-aware Transformers for Language-driven Action Localization in Videos},
  author = {Shuo Yang and Xinxiao Wu},
  journal= {arXiv preprint arXiv:2205.05854},
  year   = {2022}
}

Comments

accepted by IJCAI-22, Codes are available at https://github.com/shuoyang129/EAMAT

R2 v1 2026-06-24T11:14:59.611Z