SVIP: Sequence VerIfication for Procedures in Videos

Yicheng Qian, Weixin Luo, Dongze Lian, Xu Tang, Peilin Zhao, Shenghua Gao

Abstract

In this paper, we propose a novel sequence verification task that aims to distinguish positive video pairs performing the same action sequence from negative ones with step-level transformations but still conducting the same task. Such a challenging task resides in an open-set setting without prior action detection or segmentation that requires event-level or even frame-level annotations. To that end, we carefully reorganize two publicly available action-related datasets with step-procedure-task structure. To fully investigate the effectiveness of any method, we collect a scripted video dataset enumerating all kinds of step-level transformations in chemical experiments. Besides, a novel evaluation metric Weighted Distance Ratio is introduced to ensure equivalence for different step-level transformations during evaluation. In the end, a simple but effective baseline based on the transformer encoder with a novel sequence alignment loss is introduced to better characterize long-term dependency between steps, which outperforms other action recognition methods. Codes and data will be released.
BibTeX
@inproceedings{qian2021svip,
  author = {Yicheng Qian and Weixin Luo and Dongze Lian and Xu Tang and Peilin Zhao and Shenghua Gao},
  title = {{SVIP: Sequence VerIfication for Procedures in Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2021},
  doi = {10.1109/cvpr52688.2022.01927},
}
Figure