English

Localizing the Common Action Among a Few Videos

Computer Vision and Pattern Recognition 2020-08-26 v2 Machine Learning Image and Video Processing

Abstract

This paper strives to localize the temporal extent of an action in a long untrimmed video. Where existing work leverages many examples with their start, their ending, and/or the class of the action during training time, we propose few-shot common action localization. The start and end of an action in a long untrimmed video is determined based on just a hand-full of trimmed video examples containing the same action, without knowing their common class label. To address this task, we introduce a new 3D convolutional network architecture able to align representations from the support videos with the relevant query video segments. The network contains: (\textit{i}) a mutual enhancement module to simultaneously complement the representation of the few trimmed support videos and the untrimmed query video; (\textit{ii}) a progressive alignment module that iteratively fuses the support videos into the query branch; and (\textit{iii}) a pairwise matching module to weigh the importance of different support videos. Evaluation of few-shot common action localization in untrimmed videos containing a single or multiple action instances demonstrates the effectiveness and general applicability of our proposal.

Keywords

Cite

@article{arxiv.2008.05826,
  title  = {Localizing the Common Action Among a Few Videos},
  author = {Pengwan Yang and Vincent Tao Hu and Pascal Mettes and Cees G. M. Snoek},
  journal= {arXiv preprint arXiv:2008.05826},
  year   = {2020}
}

Comments

ECCV 2020

R2 v1 2026-06-23T17:49:57.086Z