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

• URL: http://arxiv.org/abs/2604.04467v1
• Date: Mon, 06 Apr 2026 06:38:33 GMT
• Title: Group-DINOmics: Incorporating People Dynamics into DINO for Self-supervised Group Activity Feature Learning
• Abstract summary: We propose leveraging dynamics-aware and group-aware pretext, along with local and global features provided by DINO, for group-dynamics-aware learning.<n>To adapt DINO and learning to local dynamics and global group features, our pretext tasks use person flow estimation and group-relevant object location estimation.<n>Experiments on public datasets demonstrate the state-of-the-art performance of our method in group activity retrieval and recognition.
• Score: 15.39227972929495
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Simulating Organized Group Behavior: New Framework, Benchmark, and Analysis [49.796228341744076]
  We propose a task that models organized groups as collective entities from a practical perspective.<n>We present GROVE, a benchmark covering 44 entities with 8,052 real-world context-decision pairs.<n>We also propose a structured analytical framework that converts collective decision-making events into an interpretable, adaptive, and traceable behavioral model.
  arXiv  Detail & Related papers  (2026-04-10T20:04:33Z)
• Learning Human-Object Interaction as Groups [52.28258599873394]
  GroupHOI is a framework that propagates contextual information in terms of geometric proximity and semantic similarity.<n>It exhibits leading performance on the more challenging Nonverbal Interaction Detection task.
  arXiv  Detail & Related papers  (2025-10-21T07:25:10Z)
• Dynamic Group Detection using VLM-augmented Temporal Groupness Graph [15.43013474885794]
  This paper proposes dynamic human group detection in videos.<n>For detecting complex groups, not only the local appearance features of in-group members but also the global context of the scene are important.<n>Our method outperforms state-of-the-art group detection methods on public datasets.
  arXiv  Detail & Related papers  (2025-09-05T02:37:01Z)
• Towards Open-World Human Action Segmentation Using Graph Convolutional Networks [6.167678490008973]
  Most existing learning-based methods excel in closed-world action segmentation.<n>We propose a structured framework for detecting and segmenting unseen actions.<n>We evaluate our framework on two challenging human-object recognition datasets.
  arXiv  Detail & Related papers  (2025-07-01T14:00:39Z)
• GRA: Detecting Oriented Objects through Group-wise Rotating and Attention [64.21917568525764]
  Group-wise Rotating and Attention (GRA) module is proposed to replace the convolution operations in backbone networks for oriented object detection. GRA can adaptively capture fine-grained features of objects with diverse orientations, comprising two key components: Group-wise Rotating and Group-wise Attention. GRA achieves a new state-of-the-art (SOTA) on the DOTA-v2.0 benchmark, while saving the parameters by nearly 50% compared to the previous SOTA method.
  arXiv  Detail & Related papers  (2024-03-17T07:29:32Z)
• Learning Group Activity Features Through Person Attribute Prediction [13.964739198311001]
  Group Activity Feature (GAF) learning is proposed. By learning the whole network in an end-to-end manner, the attributes of people in a group are trained.
  arXiv  Detail & Related papers  (2024-03-05T08:19:44Z)
• Towards More Practical Group Activity Detection: A New Benchmark and Model [61.39427407758131]
  Group activity detection (GAD) is the task of identifying members of each group and classifying the activity of the group at the same time in a video. We present a new dataset, dubbed Caf'e, which presents more practical scenarios and metrics. We also propose a new GAD model that deals with an unknown number of groups and latent group members efficiently and effectively.
  arXiv  Detail & Related papers  (2023-12-05T16:48:17Z)
• Hunting Group Clues with Transformers for Social Group Activity Recognition [3.1061678033205635]
  Social group activity recognition requires recognizing multiple sub-group activities and identifying group members. Most existing methods tackle both tasks by refining region features and then summarizing them into activity features. We propose to leverage attention modules in transformers to generate effective social group features. Our method is designed in such a way that the attention modules identify and then aggregate features relevant to social group activities.
  arXiv  Detail & Related papers  (2022-07-12T01:46:46Z)
• Pose is all you need: The pose only group activity recognition system (POGARS) [7.876115370275732]
  We introduce a novel deep learning based group activity recognition approach called Pose Only Group Activity Recognition System (POGARS) POGARS uses 1D CNNs to learn dynamics of individuals involved in group activity and forgo learning from pixel data. Experimental results confirm that POGARS achieves highly competitive results compared to state-of-the-art methods on a widely used public volleyball dataset.
  arXiv  Detail & Related papers  (2021-08-09T17:16:04Z)
• Learning Multi-Attention Context Graph for Group-Based Re-Identification [214.84551361855443]
  Learning to re-identify or retrieve a group of people across non-overlapped camera systems has important applications in video surveillance. In this work, we consider employing context information for identifying groups of people, i.e., group re-id. We propose a novel unified framework based on graph neural networks to simultaneously address the group-based re-id tasks.
  arXiv  Detail & Related papers  (2021-04-29T09:57:47Z)
• Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data [85.43008636875345]
  We show that diverse representation in training data is key to increasing subgroup performances and achieving population level objectives. Our analysis and experiments describe how dataset compositions influence performance and provide constructive results for using trends in existing data, alongside domain knowledge, to help guide intentional, objective-aware dataset design.
  arXiv  Detail & Related papers  (2021-03-05T00:27:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.