Preprint
Aug 2026
Illuminating Visual Identity in Universal Multimodal Embeddings
This work proposes a unified formulation for visual identity discrimination~(VisID) and introduces a simple yet effective learning framework that jointly optimizes general multimodal and visual identity representations through a carefully designed identity-aware sampling mechanism.
Jiawei Cao, Junyi Feng, Jiashen Hua et al.
· 1 citation