3 papers
cs.CV2026
Beyond Facial Consistency: Personalized Person Image Generation with Holistic Identity Preservation
Yuxuan Xiao, Shanshan Zhang, Jian Yang +1
Personalized person image generation requires preserving subject identity across both local facial details and broader appearance cues. Existing methods typically emphasize only on…
cs.CV2026
Head Similarity: Modeling Structured Whole-Head Appearance Beyond Face Recognition
Yingfeng Wang, Yuxuan Xiao, Shengcai Liao
Many vision applications require identity consistency beyond strict biometric recognition, especially under non-frontal views or when facial cues are missing. However, conventional…
cs.CV2025
Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learning
Xingping Dong, Tianran Ouyang, Shengcai Liao +2
Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit. To reduce the requirement of labels, a semi-supervise…