Search papers, labs, and topics across Lattice.
This paper introduces SapiensID 2.0, a human recognition framework that enhances traditional geometric feature extraction by integrating semantic and temporal awareness to better align with human perception. By leveraging zero-shot semantic knowledge from Multimodal Large Language Models and employing techniques like Invariant Trait Alignment and Transient Noise Disentanglement, the framework effectively captures invariant soft biometrics and decouples noise artifacts. Extensive experiments show that SapiensID 2.0 outperforms existing methods in person re-identification and gait recognition while maintaining strong face recognition capabilities.
SapiensID 2.0 achieves state-of-the-art recognition performance by aligning human perception with advanced semantic and temporal modeling techniques.
While foundation models have significantly advanced human recognition across diverse modalities, they predominantly rely on static, geometric feature extraction. This approach fundamentally diverges from human perception. Consequently, current models often suffer from"semantic blindness,"overfitting to transient noise while failing to leverage invariant soft biometrics, and struggle to capture temporal motion signatures. To bridge this gap, we propose SapiensID 2.0, a human recognition framework enriched with both semantic and temporal awareness. To overcome the lack of soft-biometric annotations, we transfer zero-shot semantic knowledge from Multimodal Large Language Models (MLLMs) into a discriminative embedding space. We resolve the dimensional mismatch between these spaces using Invariant Trait Alignment (ITA) to distill core persistent traits, and Transient Noise Disentanglement (TND) to decouple artifacts like clothing. Furthermore, we design a Kinematic Semantic Attention Head (K-SAH) that extends spatial attention across temporal windows. By tracking semantic patches over time, K-SAH captures rich kinematic signatures without requiring large-scale video datasets. Extensive experiments demonstrate that SapiensID 2.0 achieves state-of-the-art performance across image- and video-based person re-identification and gait recognition, while maintaining robust face recognition capabilities.
