# Group-CLIP Uncertainty Modeling for Group Re-Identification

arXiv: https://arxiv.org/abs/2502.06460 · HTML: https://mlsanity.com/paper/2502.06460/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 10 Feb 2025.

## Builds on (most cited first, 10 of 10)

- [EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought](https://mlsanity.com/paper/2305.15021/) (2023)
- [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022)
- [Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias](https://mlsanity.com/paper/2305.19894/) (2023)
- [Bootstrapping Vision-Language Learning with Decoupled Language Pre-training](https://mlsanity.com/paper/2307.07063/) (2023)
- [Enhancing Vision-Language Pre-training with Rich Supervisions](https://mlsanity.com/paper/2403.03346/) (2024)
- [Learning Multi-Attention Context Graph for Group-Based Re-Identification](https://mlsanity.com/paper/2104.14236/) (2021)
- [Group Re-Identification with Multi-grained Matching and Integration](https://mlsanity.com/paper/1905.07108/) (2019)
- [Group Re-Identification via Unsupervised Transfer of Sparse Features Encoding](https://mlsanity.com/paper/1707.09173/) (2017)
- [Parallel Augmentation and Dual Enhancement for Occluded Person Re-identification](https://mlsanity.com/paper/2210.05438/) (2022)
- [Vision Transformer based Random Walk for Group Re-Identification](https://mlsanity.com/paper/2410.05808/) (2024)

## Abstract (arXiv)

Group Re-Identification (Group ReID) aims matching groups of pedestrians across non-overlapping cameras. Unlike single-person ReID, Group ReID focuses more on the changes in group structure, emphasizing the number of members and their spatial arrangement. However, most methods rely on certainty-based models, which consider only the specific group structures in the group images, often failing to match unseen group configurations. To this end, we propose a novel Group-CLIP UncertaintyModeling (GCUM) approach that adapts group text descriptions to undetermined accommodate member and layout variations. Specifically, we design a Member Variant Simulation (MVS)module that simulates member exclusions using a Bernoulli distribution and a Group Layout Adaptation (GLA) module that generates uncertain group text descriptions with identity-specific tokens. In addition, we design a Group RelationshipConstruction Encoder (GRCE) that uses group features to refine individual features, and employ cross-modal contrastive loss to obtain generalizable knowledge from group text descriptions. It is worth noting that we are the first to employ CLIP to GroupReID, and extensive experiments show that GCUM significantly outperforms state-of-the-art Group ReID methods.