English

Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding

Computer Vision and Pattern Recognition 2024-09-10 v3

Abstract

Existing video-language pre-training methods primarily focus on instance-level alignment between video clips and captions via global contrastive learning but neglect rich fine-grained local information in both videos and text, which is of importance to downstream tasks requiring temporal localization and semantic reasoning. A powerful model is expected to be capable of capturing region-object correspondences and recognizing scene changes in a video clip, reflecting spatial and temporal granularity, respectively. To strengthen model's understanding into such fine-grained details, we propose a simple yet effective video-language modeling framework, S-ViLM, by exploiting the intrinsic structures of these two modalities. It includes two novel designs, inter-clip spatial grounding and intra-clip temporal grouping, to promote learning region-object alignment and temporal-aware features, simultaneously. Comprehensive evaluations demonstrate that S-ViLM performs favorably against existing approaches in learning more expressive representations. Specifically, S-ViLM surpasses the state-of-the-art methods substantially on four representative downstream tasks, covering text-video retrieval, video question answering, video action recognition, and temporal action localization.

Keywords

Cite

@article{arxiv.2303.16341,
  title  = {Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding},
  author = {Yuanhao Xiong and Long Zhao and Boqing Gong and Ming-Hsuan Yang and Florian Schroff and Ting Liu and Cho-Jui Hsieh and Liangzhe Yuan},
  journal= {arXiv preprint arXiv:2303.16341},
  year   = {2024}
}

Comments

Accepted to ICLR2024, see https://openreview.net/forum?id=5dlfiJIXoh for more details

R2 v1 2026-06-28T09:38:56.205Z