Integrating Language Guidance Into Image-Text Matching for Correcting False Negatives
Open paper
Benchmark
Model
Rank
Results
cross-modal-retrieval-with-noisy-correspondence-on-coco-noisy
LG-ITM-SGARF
#5
R-Sum: 524.9
Image-to-text R@1: 79.6
Image-to-text R@5: 96.5
…
Rank counts only results with a code link.