Concept-centric short captions and cross-modal attention pooling yield SOTA compositionality in contrastive V&L models without degrading zero-shot or retrieval performance.
Teaching structured Vision&Language concepts to vi- sion&language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
No Hard Negatives Required: Concept Centric Learning Leads to Compositionality without Degrading Zero-shot Capabilities of Contrastive Models
Concept-centric short captions and cross-modal attention pooling yield SOTA compositionality in contrastive V&L models without degrading zero-shot or retrieval performance.