LVLM-recaptioned image-text data with negative descriptions and short-tag supervision yields a CLIP model that beats larger-data baselines on several benchmarks.
Vlmevalkit: An open-source toolkit for evaluating large multi-modality models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models
LVLM-recaptioned image-text data with negative descriptions and short-tag supervision yields a CLIP model that beats larger-data baselines on several benchmarks.