English

Retrieval-Augmented Egocentric Video Captioning

Computer Vision and Pattern Recognition 2024-06-21 v4

Abstract

Understanding human actions from videos of first-person view poses significant challenges. Most prior approaches explore representation learning on egocentric videos only, while overlooking the potential benefit of exploiting existing large-scale third-person videos. In this paper, (1) we develop EgoInstructor, a retrieval-augmented multimodal captioning model that automatically retrieves semantically relevant third-person instructional videos to enhance the video captioning of egocentric videos. (2) For training the cross-view retrieval module, we devise an automatic pipeline to discover ego-exo video pairs from distinct large-scale egocentric and exocentric datasets. (3) We train the cross-view retrieval module with a novel EgoExoNCE loss that pulls egocentric and exocentric video features closer by aligning them to shared text features that describe similar actions. (4) Through extensive experiments, our cross-view retrieval module demonstrates superior performance across seven benchmarks. Regarding egocentric video captioning, EgoInstructor exhibits significant improvements by leveraging third-person videos as references. Project page is available at: https://jazzcharles.github.io/Egoinstructor/

Keywords

Cite

@article{arxiv.2401.00789,
  title  = {Retrieval-Augmented Egocentric Video Captioning},
  author = {Jilan Xu and Yifei Huang and Junlin Hou and Guo Chen and Yuejie Zhang and Rui Feng and Weidi Xie},
  journal= {arXiv preprint arXiv:2401.00789},
  year   = {2024}
}

Comments

CVPR 2024. Project page is available at: https://jazzcharles.github.io/Egoinstructor/

R2 v1 2026-06-28T14:06:02.621Z