-
DynamiCS Public
Dynamic cluster-based data sampling for efficient and long-tail-aware vision-language model pre-training.
-
CLIPF Public
CLIPF: Contrastive Language-Image Pre-training with Word Frequency Masking — a frequency-based text masking strategy for efficient VLM pre-training (WACV 2026)
-
GLIP Public
Centered Masking for Language-Image Pre-training
-
-
-
TCE-CVSE Public
Textual Concept Expansion with Commonsense Knowledge to Improve Dual-Stream Image-Text Matching
{{ message }}