HiTPro achieves state-of-the-art unsupervised video-based visible-infrared person re-identification via temporal feature encoding, intra-camera prototyping, hierarchical cross-prototype alignment, and multi-level contrastive learning.
Diverse embedding expansion network and low-light cross-modality benchmark for visible-infrared person re- identification,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Transformer-based ReID embeddings encode BMI most strongly in deeper layers, followed by pitch, gender, and yaw, with pose peaking in middle layers and BMI increasing with depth; cross-spectral settings shift reliance toward structural cues.
citing papers explorer
-
Temporal Prototyping and Hierarchical Alignment for Unsupervised Video-based Visible-Infrared Person Re-Identification
HiTPro achieves state-of-the-art unsupervised video-based visible-infrared person re-identification via temporal feature encoding, intra-camera prototyping, hierarchical cross-prototype alignment, and multi-level contrastive learning.
-
AttriBE: Quantifying Attribute Expressivity in Body Embeddings for Recognition and Identification
Transformer-based ReID embeddings encode BMI most strongly in deeper layers, followed by pitch, gender, and yaw, with pose peaking in middle layers and BMI increasing with depth; cross-spectral settings shift reliance toward structural cues.