OpenCodePapers

image-retrieval-on-flickr30k

Image Retrieval
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeRecall@10Recall@5Recall@1Recall@SumImage-to-text R@1Image-to-text R@10Image-to-text R@5QPSModelNameReleaseDate
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models✓ Link98.998.189.7BLIP-2 ViT-G (zero-shot, 1K test set)2023-01-30
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models✓ Link98.997.688.6BLIP-2 ViT-L (zero-shot, 1K test set)2023-01-30
HADA: A Graph-based Amalgamation Framework in Image-text Retrieval✓ Link98.0295.9481.36HADA2023-01-11
MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks✓ Link989682.594.999.999.5MaMMUT (ours)2023-03-29
HADA: A Graph-based Amalgamation Framework in Image-text Retrieval✓ Link97.7295.379.76ALBEF2023-01-11
HADA: A Graph-based Amalgamation Framework in Image-text Retrieval✓ Link96.7694.0875.56UNITER2023-01-11
A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval✓ Link90.284.157.4231.7LGSGM2021-06-04
A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval✓ Link8982.3228.7GSMN2021-06-04
VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words✓ Link88.182.057.4451.4VisualSparta2021-01-01