English

HierVL: Learning Hierarchical Video-Language Embeddings

Computer Vision and Pattern Recognition 2023-06-09 v2

Abstract

Video-language embeddings are a promising avenue for injecting semantics into visual representations, but existing methods capture only short-term associations between seconds-long video clips and their accompanying text. We propose HierVL, a novel hierarchical video-language embedding that simultaneously accounts for both long-term and short-term associations. As training data, we take videos accompanied by timestamped text descriptions of human actions, together with a high-level text summary of the activity throughout the long video (as are available in Ego4D). We introduce a hierarchical contrastive training objective that encourages text-visual alignment at both the clip level and video level. While the clip-level constraints use the step-by-step descriptions to capture what is happening in that instant, the video-level constraints use the summary text to capture why it is happening, i.e., the broader context for the activity and the intent of the actor. Our hierarchical scheme yields a clip representation that outperforms its single-level counterpart as well as a long-term video representation that achieves SotA results on tasks requiring long-term video modeling. HierVL successfully transfers to multiple challenging downstream tasks (in EPIC-KITCHENS-100, Charades-Ego, HowTo100M) in both zero-shot and fine-tuned settings.

Keywords

Cite

@article{arxiv.2301.02311,
  title  = {HierVL: Learning Hierarchical Video-Language Embeddings},
  author = {Kumar Ashutosh and Rohit Girdhar and Lorenzo Torresani and Kristen Grauman},
  journal= {arXiv preprint arXiv:2301.02311},
  year   = {2023}
}

Comments

CVPR 2023

R2 v1 2026-06-28T08:04:28.289Z