| Benchmark | Model | Rank | Results |
|---|---|---|---|
| sound-prompted-semantic-segmentation-on-ade20k | ImageBIND | #3 | mAP: 19.7mIoU: 20.5 |
| speech-prompted-semantic-segmentation-on-ade20k | ImageBIND | #3 | mAP: 20.2mIoU: 19.7 |
| temporal-relation-extraction-on-vinoground | ImageBind | #16 | Text Score: 9.4Video Score: 3.4Group Score: 0.6 |
| zero-shot-video-retrieval-on-msr-vtt | ImageBind | #21 | text-to-video R@1: 36.8text-to-video R@5: 61.8… |