English

Open-Vocabulary Video Relation Extraction

Computer Vision and Pattern Recognition 2023-12-27 v1

Abstract

A comprehensive understanding of videos is inseparable from describing the action with its contextual action-object interactions. However, many current video understanding tasks prioritize general action classification and overlook the actors and relationships that shape the nature of the action, resulting in a superficial understanding of the action. Motivated by this, we introduce Open-vocabulary Video Relation Extraction (OVRE), a novel task that views action understanding through the lens of action-centric relation triplets. OVRE focuses on pairwise relations that take part in the action and describes these relation triplets with natural languages. Moreover, we curate the Moments-OVRE dataset, which comprises 180K videos with action-centric relation triplets, sourced from a multi-label action classification dataset. With Moments-OVRE, we further propose a crossmodal mapping model to generate relation triplets as a sequence. Finally, we benchmark existing cross-modal generation models on the new task of OVRE.

Keywords

Cite

@article{arxiv.2312.15670,
  title  = {Open-Vocabulary Video Relation Extraction},
  author = {Wentao Tian and Zheng Wang and Yuqian Fu and Jingjing Chen and Lechao Cheng},
  journal= {arXiv preprint arXiv:2312.15670},
  year   = {2023}
}

Comments

accpeted by AAAI 2024

R2 v1 2026-06-28T14:01:26.848Z