Chat Based Image Retrieval On Visdial
평가 지표
Recall@10 on 1 rounds
Recall@10 on 2 rounds
Recall@10 on 3 rounds
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Recall@10 on 1 rounds | Recall@10 on 2 rounds | Recall@10 on 3 rounds | Paper Title | Repository |
|---|---|---|---|---|---|
| Human & BLIP2 | 67 | 70 | 71.8 | - | - |
| ChatGPT & BLIP2 | 70 | 73.5 | 75.75 | - | - |
| ImageScope (CLIP-ViT-L/14) | - | - | - | ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning | - |
0 of 3 row(s) selected.