Chat-based Image Retrieval 벤치마크
Chat-based Image Retrieval on VisDial
| Rank | Model | Recall@10 on 1 rounds | Recall@10 on 2 rounds | Recall@10 on 3 rounds | Hits@10 on 10 Round | Paper | Code | Year |
|---|---|---|---|---|---|---|---|---|
| 1 | ChatGPT & BLIP2 | 70 | 73.5 | 75.75 | – | |||
| 2 | Human & BLIP2 | 67 | 70 | 71.8 | – | |||
| 3 | ImageScope (CLIP-ViT-L/14) | – | – | – | 79.89 | ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning | pengfei-luo/ImageScope | 2025 |