LVLM-recaptioned image-text data with negative descriptions and short-tag supervision yields a CLIP model that beats larger-data baselines on several benchmarks.
Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks
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
background 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.