Speech Prompted Semantic Segmentation On
평가 지표
mAP
mIoU
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | mAP | mIoU | Paper Title | Repository |
|---|---|---|---|---|
| CAVMAE | 27.2 | 19.9 | Contrastive Audio-Visual Masked Autoencoder | - |
| DAVENet | 32.2 | 26.3 | Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input | - |
| ImageBIND | 20.2 | 19.7 | ImageBind: One Embedding Space To Bind Them All | - |
| DenseAV | 48.7 | 36.8 | Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language | - |
0 of 4 row(s) selected.