UniPAR: A Unified Framework for Pedestrian Attribute Recognition
Year: 2026
Type: article
Abstract: ABSTRACT Pedestrian Attribute Recognition is a foundational computer vision task that provides essential support for downstream applications, including person retrieval in video surveillance and intelligent retail analytics. However, existing research is frequently constrained by the “one‐model‐per‐dataset” paradigm and struggles to handle significant discrepancies across domains in terms of modalities, attribute definitions, and environmental scenarios. To address these challenges, we propose UniPAR, a unified Transformer‐based framework for PAR. By incorporating a unified data scheduling strategy and a dynamic classification head, UniPAR enables a single model to jointly learn from diverse pedestrian attribute datasets spanning RGB images, video sequences, and event streams through a unified optimization framework. We also introduce an innovative phased fusion encoder that incorporates textual attribute queries as semantic guidance through a late deep fusion strategy, enabling more discriminative visual feature learning. Experimental results on the widely used benchmark datasets, including MSP60K, DukeMTMC, and EventPAR, demonstrate that UniPAR achieves performance comparable to specialised SOTA methods. Furthermore, multi‐dataset joint training enables positive knowledge transfer across heterogeneous datasets, leading to improved generalisation ability and more robust pedestrian attribute recognition under challenging conditions such as low‐light and motion‐blurred environments. The source code of this paper will be released on https://github.com/Event‐AHU/OpenPAR .
Source: IET Computer Vision
DOI: 10.1049/cvi2.70081
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,510
OpenAlex ID: W7202046652