A CLIP-based framework with synthetic modality augmentation reports competitive zero-shot pedestrian re-identification across RGB, infrared, sketch, and text queries.
(2022) Multi-modal transformer for video retrieval[C], Computer Vision–ECCV 2020: 16th European Conference, 214-229
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A CLIP-based Uncertainty Modal Modeling (UMM) Framework for Pedestrian Re-Identification in Autonomous Driving
A CLIP-based framework with synthetic modality augmentation reports competitive zero-shot pedestrian re-identification across RGB, infrared, sketch, and text queries.