GaitMspT: A Novel Multi-Scale and Multi-Perspective Temporal Learning Network for Gait Recognition in the Wild

Hanlin Li, Wanquan Liu, Chenqiang Gao, Ping Wang, Huafeng Wang

Abstract: Gait recognition, a promising biometric technique, faces significant challenges in unconstrained in-the-wild scenarios. While spatial modeling has progressed, existing state-of-the-art methods fundamentally struggle with temporal variations due to their reliance on strategies developed for constrained environments, limiting their effectiveness in diverse real-world conditions. To overcome this critical bottleneck, we propose GaitMspT, a novel Multi-scale and Multi-perspective Temporal Learning Network engineered for robust unconstrained gait recognition. GaitMspT introduces two key modules: a Multi-scale Temporal Extraction (MsTE) module that captures diverse temporal features across three distinct scales, effectively mitigating issues like gait contour occlusion, and a Multi-perspective Spatial-Temporal Extraction (MpSTE) module that extracts nuanced horizontal and vertical gait variations, emphasizing salient components. Their synergistic integration endows our network with significantly enhanced temporal modeling capabilities. Extensive experiments on four prominent in-the-wild gait datasets (Gait3D, GREW, CCPG, and SUSTech1K) unequivocally demonstrate that GaitMspT substantially outperforms existing state-of-the-art methods, achieving superior recognition accuracy while maintaining an excellent balance between performance and computational complexity.

External IDs:doi:10.1109/tbiom.2025.3613586