List your company

Image-to-Text Retrieval on MS-COCO 1K

78.3R@1REPAIR
25.7839.41553.0566.685Mar 13, 2024Jun 21, 2024Sep 29, 2024Jan 7, 2025Apr 17, 2025Jul 26, 2025Nov 3, 2025

Evaluation results

MethodLinks
REPAIRNoise=20%2024.0378.396.898.3
MSCNNoise=20%2024.0378.197.298.8
NCRNoise=20%, re-implemented=true2024.0377.795.898.3
REPAIRNoise=40%2024.0376.495.498.4
NCRNoise=40%, re-implemented=true2024.037695.198.4
DECLNoise=20%2024.0375.695.198.3
BiCroNoise=20%, re-implemented=true2024.0375.595.298.1
BiCroNoise=40%, re-implemented=true2024.0375.595.298
MSCNNoise=40%2024.0374.894.998
BiCroNoise=60%, re-implemented=true2024.0374.794.297.9
MSCNNoise=60%2024.0374.495.197.9
REPAIRNoise=60%2024.0373.794.497.9
DECLNoise=40%2024.0373.694.697.9
VSE∞Noise=20%2024.0373.593.397
NCRNoise=60%, re-implemented=true2024.0372.89497.4
DECLNoise=60%2024.0369.793.497.5
SEPSFine-grained alignment=true, Zero-shot=true, Backbone=CLIP ViT-B/16, Training Dataset=Flickr2025.1165.877.4—
VSE∞Noise=40%2024.0353.384.392.1
SGRNoise=20%2024.0349.183.892.7
LAPSFine-grained alignment=true, Zero-shot=true, Backbone=CLIP ViT-B/16, Training Dataset=Flickr2025.1147.474.9—
SGRNoise=40%2024.0343.978.389.3
SGRNoise=60%2024.0337.673.386.3
VSE∞Noise=60%2024.0333.464.879.1
D2S-VSEFine-grained alignment=false, Zero-shot=true, Backbone=CLIP ViT-B/16, Training Dataset=Flickr2025.1132.362.3—
SCANFine-grained alignment=true, Zero-shot=true, Backbone=CLIP ViT-B/16, Training Dataset=Flickr2025.1130.559.8—
SCANNoise=40%2024.0330.165.279.2
SCANNoise=20%2024.0328.964.579.5
VSE++Fine-grained alignment=false, Zero-shot=true, Backbone=CLIP ViT-B/16, Training Dataset=Flickr2025.1128.156.4—
SCANNoise=60%2024.0327.859.874.8