# Structured Relational Reasoning for Group Activity Assessment

arXiv: https://arxiv.org/abs/2508.07996 · HTML: https://mlsanity.com/paper/2508.07996/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [AIM: Adapting Image Models for Efficient Video Action Recognition](https://mlsanity.com/paper/2302.03024/) (2023)
- [Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting](https://mlsanity.com/paper/2304.03307/) (2023)
- [Learning Actor Relation Graphs for Group Activity Recognition](https://mlsanity.com/paper/1904.10117/) (2019)
- [Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos](https://mlsanity.com/paper/2007.02632/) (2020)
- [JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detection](https://mlsanity.com/paper/2106.08827/) (2021)
- [Visual Fourier Prompt Tuning](https://mlsanity.com/paper/2411.01327/) (2024)
- [Hunting Group Clues with Transformers for Social Group Activity Recognition](https://mlsanity.com/paper/2207.05254/) (2022)
- [COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality](https://mlsanity.com/paper/2112.05892/) (2021)
- [DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers](https://mlsanity.com/paper/2505.23694/) (2025)
- [Panoramic Human Activity Recognition](https://mlsanity.com/paper/2203.03806/) (2022)
- [Towards More Practical Group Activity Detection: A New Benchmark and Model](https://mlsanity.com/paper/2312.02878/) (2023)

## Built on by (most cited first, 1 of 1)

- [Why Relational Graphs Will Save the Next Generation of Vision Foundation Models?](https://mlsanity.com/paper/2508.18421/) (2025)

## Abstract (arXiv)

Group Activity Detection (GAD) involves recognizing social groups and their collective behaviors in videos. Vision Foundation Models (VFMs), like DINOv2, offer excellent features but are pretrained on object-centric data. We find that naively substituting them into existing GAD pipelines actually degrades performance, exposing structured group-aware decoding as the true bottleneck. We introduce ProGraD, a structured relational-reasoning framework for GAD built on top of frozen VFMs. At its core is a lightweight two-layer GroupContext Transformer that explicitly models actor-group associations and aggregates global context to infer collective behavior. Learnable group prompts serve as a minimal conditioning mechanism to guide the frozen backbone toward socially relevant representations, while the relational decoder performs the core reasoning over actors and groups. This design jointly infers group locations, memberships, and activities in a single pass using only 10M trainable parameters - less than half of prior methods. On the Cafe benchmark with multiple concurrent social groups, ProGraD improves the state-of-the-art by 6.5% Group mAP@1.0 and 8.2% Group mAP@0.5. On Social-CAD, it achieves state-of-the-art social and membership accuracy. ProGraD further produces interpretable attention maps that provide insights into actor-group reasoning.