Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.07766 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909026718056448 |
|---|---|
| author | Wang, Yingfeng Xiao, Yuxuan Liao, Shengcai |
| author_facet | Wang, Yingfeng Xiao, Yuxuan Liao, Shengcai |
| contents | Many vision applications require identity consistency beyond strict biometric recognition, especially under non-frontal views or when facial cues are missing. However, conventional face recognition models enforce intra-identity invariance, collapsing appearance variations such as hairstyle or styling changes into a single representation, limiting their use in appearance-sensitive scenarios. To address this limitation, we introduce Head Similarity, a new formulation that extends identity-centric recognition to structured whole-head similarity modeling. Our approach explicitly captures intra-identity appearance variation and enforces hierarchical similarity ordering across identity and appearance states, enabling meaningful comparison even under occlusion or rear-view conditions. We construct a large-scale benchmark from long-form videos with weakly-supervised appearance states, covering diverse poses, occlusions, and temporal changes. As a first step, we develop a simple yet effective framework that jointly models identity discrimination and appearance-sensitive similarity through hierarchical supervision and identity-aware distillation. Experiments show that conventional face recognition models fail to capture appearance-dependent similarity, while our approach demonstrates the feasibility of structured whole-head similarity modeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07766 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Head Similarity: Modeling Structured Whole-Head Appearance Beyond Face Recognition Wang, Yingfeng Xiao, Yuxuan Liao, Shengcai Computer Vision and Pattern Recognition Many vision applications require identity consistency beyond strict biometric recognition, especially under non-frontal views or when facial cues are missing. However, conventional face recognition models enforce intra-identity invariance, collapsing appearance variations such as hairstyle or styling changes into a single representation, limiting their use in appearance-sensitive scenarios. To address this limitation, we introduce Head Similarity, a new formulation that extends identity-centric recognition to structured whole-head similarity modeling. Our approach explicitly captures intra-identity appearance variation and enforces hierarchical similarity ordering across identity and appearance states, enabling meaningful comparison even under occlusion or rear-view conditions. We construct a large-scale benchmark from long-form videos with weakly-supervised appearance states, covering diverse poses, occlusions, and temporal changes. As a first step, we develop a simple yet effective framework that jointly models identity discrimination and appearance-sensitive similarity through hierarchical supervision and identity-aware distillation. Experiments show that conventional face recognition models fail to capture appearance-dependent similarity, while our approach demonstrates the feasibility of structured whole-head similarity modeling. |
| title | Head Similarity: Modeling Structured Whole-Head Appearance Beyond Face Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.07766 |