Dynamic Group Detection using VLM-augmented Temporal Groupness Graph

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yokoyama, Kaname, Nakatani, Chihiro, Ukita, Norimichi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911138963259392
author Yokoyama, Kaname
Nakatani, Chihiro
Ukita, Norimichi
author_facet Yokoyama, Kaname
Nakatani, Chihiro
Ukita, Norimichi
contents 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/irajisamurai/VLM-GroupDetection.git
format Preprint
id arxiv_https___arxiv_org_abs_2509_04758
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dynamic Group Detection using VLM-augmented Temporal Groupness Graph
Yokoyama, Kaname
Nakatani, Chihiro
Ukita, Norimichi
Computer Vision and Pattern Recognition
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/irajisamurai/VLM-GroupDetection.git
title Dynamic Group Detection using VLM-augmented Temporal Groupness Graph
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.04758