Group-DINOmics: Incorporating People Dynamics into DINO for Self-supervised Group Activity Feature Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tezuka, Ryuki, Nakatani, Chihiro, Ukita, Norimichi
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915917728841728
author Tezuka, Ryuki
Nakatani, Chihiro
Ukita, Norimichi
author_facet Tezuka, Ryuki
Nakatani, Chihiro
Ukita, Norimichi
contents This paper proposes Group Activity Feature (GAF) learning without group activity annotations. Unlike prior work, which uses low-level static local features to learn GAFs, we propose leveraging dynamics-aware and group-aware pretext tasks, along with local and global features provided by DINO, for group-dynamics-aware GAF learning. To adapt DINO and GAF learning to local dynamics and global group features, our pretext tasks use person flow estimation and group-relevant object location estimation, respectively. Person flow estimation is used to represent the local motion of each person, which is an important cue for understanding group activities. In contrast, group-relevant object location estimation encourages GAFs to learn scene context (e.g., spatial relations of people and objects) as global features. Comprehensive experiments on public datasets demonstrate the state-of-the-art performance of our method in group activity retrieval and recognition. Our ablation studies verify the effectiveness of each component in our method. Code: https://github.com/tezuka0001/Group-DINOmics.
format Preprint
id arxiv_https___arxiv_org_abs_2604_04467
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Group-DINOmics: Incorporating People Dynamics into DINO for Self-supervised Group Activity Feature Learning
Tezuka, Ryuki
Nakatani, Chihiro
Ukita, Norimichi
Computer Vision and Pattern Recognition
This paper proposes Group Activity Feature (GAF) learning without group activity annotations. Unlike prior work, which uses low-level static local features to learn GAFs, we propose leveraging dynamics-aware and group-aware pretext tasks, along with local and global features provided by DINO, for group-dynamics-aware GAF learning. To adapt DINO and GAF learning to local dynamics and global group features, our pretext tasks use person flow estimation and group-relevant object location estimation, respectively. Person flow estimation is used to represent the local motion of each person, which is an important cue for understanding group activities. In contrast, group-relevant object location estimation encourages GAFs to learn scene context (e.g., spatial relations of people and objects) as global features. Comprehensive experiments on public datasets demonstrate the state-of-the-art performance of our method in group activity retrieval and recognition. Our ablation studies verify the effectiveness of each component in our method. Code: https://github.com/tezuka0001/Group-DINOmics.
title Group-DINOmics: Incorporating People Dynamics into DINO for Self-supervised Group Activity Feature Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.04467