Conference proceeding
SapiensID: Foundation for Human Recognition
Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online), pp 13937-13947
10 Jun 2025
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
Existing human recognition systems often rely on separate, specialized models for face and body analysis, limiting their effectiveness in real-world scenarios where pose, visibility, and context vary widely. This paper introduces SapiensID, a unified model that bridges this gap, achieving robust performance across diverse settings. SapiensID introduces (i) Retina Patch (RP), a dynamic patch generation scheme that adapts to subject scale and ensures consistent tokenization of regions of interest, (ii) a masked recognition model (MRM) that learns from variable token length, and (iii) Semantic Attention Head (SAH), an module that learns pose-invariant representations by pooling features around key body parts. To facilitate training, we introduce WebBody4M, a large-scale dataset capturing diverse poses and scale variations. Extensive experiments demonstrate that SapiensID achieves state-of-the-art results on various body ReID benchmarks, outperforming specialized models in both short-term and long-term scenarios while remaining competitive with dedicated face recognition systems. Furthermore, SapiensID establishes a strong baseline for the newly introduced challenge of Cross Pose-Scale ReID, demonstrating its ability to generalize to complex, real-world conditions. Project Link
Metrics
1 Record Views
Details
- Title
- SapiensID: Foundation for Human Recognition
- Creators
- Minchul Kim - Michigan State UniversityDingqiang Ye - Michigan State UniversityYiyang Su - Michigan State UniversityFeng Liu - Drexel University, Computer ScienceXiaoming Liu - Michigan State University
- Publication Details
- Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online), pp 13937-13947
- Publisher
- IEEE
- Number of pages
- 11
- Grant note
- Office of the Director (10.13039/100000179) Intelligence Advanced Research Projects Activity (10.13039/100011039)
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science
- Web of Science ID
- WOS:001601141700181
- Scopus ID
- 2-s2.0-105017096848
- Other Identifier
- 991022197330704721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
Source: SDGs in the Output
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Interdisciplinary Applications
- Computer Science, Theory & Methods