.png){kind=icon}
.png){kind=icon}
Return
TransFA: Transformer-based representation for face attribute evaluation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2025.112733.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We employ a novel transformer-based representation for face attribute evaluation, which can effectively integrate spatial inter-correlation between different attributes in similar semantic regions to enhance performance. • The hierarchical identity-constraint attribute loss is designed by the inherent relationship between face identity and semantic attribute, which can make feature representations contain robust discriminative information. • Experimental results illustrate the satisfactory performance of the proposed TransFA compared with state-of-the-art attribute evaluation methods. The code is publicly available in https://github.com/lorry30/TransFA .
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W