| InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks | ✓ Link | 97.9 | 100 | 100 | | InternVL-G-FT (finetuned, w/o ranking) | 2023-12-21 |
| BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models | ✓ Link | 97.6 | 100 | 100 | | BLIP-2 ViT-G (zero-shot, 1K test set) | 2023-01-30 |
| ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities | ✓ Link | 97.6 | 100 | 100 | | ONE-PEACE (finetuned, w/o ranking) | 2023-05-18 |
| InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks | ✓ Link | 97.2 | 100 | 100 | | InternVL-C-FT (finetuned, w/o ranking) | 2023-12-21 |
| BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models | ✓ Link | 96.9 | 100 | 100 | | BLIP-2 ViT-L (zero-shot, 1K test set) | 2023-01-30 |
| ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training | ✓ Link | 96.1 | 99.9 | 100.0 | | ERNIE-ViL 2.0 | 2022-09-30 |
| Align before Fuse: Vision and Language Representation Learning with Momentum Distillation | ✓ Link | 95.9 | 99.8 | 100.0 | | ALBEF | 2021-07-16 |
| HADA: A Graph-based Amalgamation Framework in Image-text Retrieval | ✓ Link | 92.6 | 99.3 | 99.9 | | ALBEF | 2023-01-11 |
| HADA: A Graph-based Amalgamation Framework in Image-text Retrieval | ✓ Link | 87.3 | 98 | 99.2 | | UNITER | 2023-01-11 |
| A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval | ✓ Link | 76.4 | 94.3 | 97.3 | 268 | GSMN | 2021-06-04 |
| A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval | ✓ Link | 71 | 91.9 | 96.1 | 259 | LGSGM | 2021-06-04 |