Chat Based Image Retrieval On Visdial
المقاييس
Recall@10 on 1 rounds
Recall@10 on 2 rounds
Recall@10 on 3 rounds
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
| Paper Title | ||||
|---|---|---|---|---|
| ChatGPT & BLIP2 | 70 | 73.5 | 75.75 | - |
| Human & BLIP2 | 67 | 70 | 71.8 | - |
| ImageScope (CLIP-ViT-L/14) | - | - | - | ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning |
0 of 3 row(s) selected.