Dynamic Group Detection using VLM-augmented Temporal Groupness Graph

Kaname Yokoyama1, Chihiro Nakatani1, Norimichi Ukita1
1Toyota Technological Institute, Japan
Paper Supplementary Code arXiv

Abstract

This paper proposes dynamic human group detection in videos. For detecting complex groups, not only the local appearance features of in-group members but also the global context of the scene are important. Such local and global appearance features in each frame are extracted using a Vision-Language Model (VLM) augmented for group detection in our method. For further improvement, the group structure should be consistent over time. While previous methods are stabilized on the assumption that groups are not changed in a video, our method detects dynamically changing groups by global optimization using a graph with all frames' groupness probabilities estimated by our groupness-augmented CLIP features. Our experimental results demonstrate that our method outperforms state-of-the-art group detection methods on public datasets. Code: https://github.com/ PJAE.

Poster

BibTeX

@InProceedings{Yokoyama_2025_ICCV,
        author    = {Yokoyama, Kaname and Nakatani, Chihiro and Ukita, Norimichi},
        title     = {Dynamic Group Detection using VLM-augmented Temporal Groupness Graph},
        booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
        month     = {October},
        year      = {2025},
        pages     = {-}
        }