| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Sound Source Localization | Flickr-SoundNet (test) | CIoU89.84 | 28 | |
| Visual Sound Source Localization | Flickr SoundNet (test) | LocAcc86.4 | 18 | |
| Audio-Visual Source Localization | Flickr-SoundNet 144k | CIoU90.4 | 14 | |
| Audio-Visual Source Localization | Flickr-SoundNet 10k | CIoU88.8 | 14 | |
| Visual Sound Source Localization | Flickr-SoundNet extended (test) | LocAcc86 | 11 | |
| Sound Source Localization | Flickr-SoundNet | Precision58.23 | 10 | |
| Image-to-Audio Retrieval | Flickr-SoundNet | mAP4.92 | 4 | |
| Audio-to-Image Retrieval | Flickr-SoundNet | mAP457 | 4 | |
| Image-to-Audio Retrieval | Flickr-SoundNet (test) | mAP- | 0 |