VLD uses CLIP text prompts and a spatial-temporal hub to learn video-level identity descriptions, setting new state-of-the-art results on HITSZ-VCM and BUPTCampus.
Appearance- preserving 3d convolution for video-based person re-identification,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Video-Level Language-Driven Video-Based Visible-Infrared Person Re-Identification
VLD uses CLIP text prompts and a spatial-temporal hub to learn video-level identity descriptions, setting new state-of-the-art results on HITSZ-VCM and BUPTCampus.