FAR-Net combines Q-Former cross-attention alignment with uncertainty-perturbed contrastive learning and reports up to 2.4 points higher Recall@1 on standard CIR benchmarks.
Context-aware multi- view summarization network for image-text matching,
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
unclear 1representative citing papers
citing papers explorer
-
FAR-Net: Multi-Stage Fusion Network with Enhanced Semantic Alignment and Adaptive Reconciliation for Composed Image Retrieval
FAR-Net combines Q-Former cross-attention alignment with uncertainty-perturbed contrastive learning and reports up to 2.4 points higher Recall@1 on standard CIR benchmarks.