A single model for face, person, and gait recognition that aligns its embedding space with semantic soft biometrics and models motion via a temporal attention head, achieving state-of-the-art zero-shot results.
Qwen2. 5-VL Technical Report
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SapiensID 2.0: Aligning Human Recognition Foundation Models with Human Perception
A single model for face, person, and gait recognition that aligns its embedding space with semantic soft biometrics and models motion via a temporal attention head, achieving state-of-the-art zero-shot results.