ML Research Wiki / Benchmarks / Image Retrieval with Multi-Modal Query / MIT-States

MIT-States

Image Retrieval with Multi-Modal Query Benchmark

Performance Over Time

📊 Showing 5 results | 📏 Metric: Recall@1

Top Performing Models

Rank Model Paper Recall@1 Date Code
1 ComposeAE Compositional Learning of Image-Text Query for Image Retrieval 13.90 2020-06-19 📦 ecom-research/ComposeAE
2 TIRG Composing Text and Image for Image Retrieval - An Empirical Odyssey 12.20 2018-12-18 📦 google/tirg 📦 naver/artemis 📦 yahoo/maaf 📦 alinstein/Modify-image-by-text
3 Show and Tell Show and Tell: A Neural Image Caption Generator 11.90 2014-11-17 📦 yashk2810/Image-Captioning 📦 jazzsaxmafia/show_and_tell.tensorflow 📦 oarriaga/neural_image_captioning
4 FiLM FiLM: Visual Reasoning with a General Conditioning Layer 10.10 2017-09-22 📦 kdaip/stabletts 📦 ethanjperez/film 📦 caffeinism/film-pytorch
5 Attribute as Operator Attributes as Operators: Factorizing Unseen Attribute-Object Compositions 8.80 2018-03-27 📦 Tushar-N/attributes-as-operators

All Papers (5)