UniPAR: A Unified Framework for Pedestrian Attribute Recognition
#UniPAR #pedestrian attribute recognition #unified framework #computer vision #artificial intelligence
📌 Key Takeaways
- UniPAR introduces a unified framework for pedestrian attribute recognition.
- The framework aims to improve accuracy and efficiency in identifying pedestrian attributes.
- It addresses challenges in diverse real-world scenarios like varying lighting and occlusion.
- UniPAR integrates multiple data sources and techniques for robust performance.
📖 Full Retelling
arXiv:2603.05114v1 Announce Type: cross
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
🏷️ Themes
Computer Vision, AI Research
📚 Related People & Topics
Unified framework
Unified framework is a general formulation which yields nth - order expressions giving mode shapes and natural frequencies for damaged elastic structures such as rods, beams, plates, and shells. The formulation is applicable to structures with any shape of damage or those having more than one area o...
Entity Intersection Graph
No entity connections available yet for this article.
Mentioned Entities
Original Source
--> Computer Science > Computer Vision and Pattern Recognition arXiv:2603.05114 [Submitted on 5 Mar 2026] Title: UniPAR: A Unified Framework for Pedestrian Attribute Recognition Authors: Minghe Xu , Rouying Wu , Jiarui Xu , Minhao Sun , Zikang Yan , Xiao Wang , ChiaWei Chu , Yu Li View a PDF of the paper titled UniPAR: A Unified Framework for Pedestrian Attribute Recognition, by Minghe Xu and 7 other authors View PDF HTML 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 simultaneously process diverse datasets from heterogeneous modalities, including RGB images, video sequences, and event streams. We also introduce an innovative phased fusion encoder that explicitly aligns visual features with textual attribute queries through a late deep fusion strategy. Experimental results on the widely used benchmark datasets, including MSP60K, DukeMTMC, and EventPAR, demonstrate that UniPAR achieves performance comparable to specialized SOTA methods. Furthermore, multi-dataset joint training significantly enhances the model's cross-domain generalization and recognition robustness in extreme environments characterized by low light and motion blur. The source code of this paper will be released on this https URL Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2603.05114 [cs.CV] (or arXiv:2603.05114v1 [cs.CV]...
Read full article at source