Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
CLIP-RD: Relative Distillation for Efficient CLIP Knowledge Distillation
Jeannie Chung, Hanna Jang, Ingyeong Yang +2
CLIP aligns image and text embeddings via contrastive learning and demonstrates strong zero-shot generalization. Its large-scale architecture requires substantial computational and…
cs.CV2024
Lifelong Person Search
Jae-Won Yang, Seungbin Hong, Jae-Young Sim
Person search is the task to localize a query person in gallery datasets of scene images. Existing methods have been mainly developed to handle a single target dataset only, howeve…