Speech Prompted Semantic Segmentation On
Metrics
mAP
mIoU
Results
Performance results of various models on this benchmark
| Paper Title | |||
|---|---|---|---|
| DenseAV | 48.7 | 36.8 | Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language |
| DAVENet | 32.2 | 26.3 | Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input |
| CAVMAE | 27.2 | 19.9 | Contrastive Audio-Visual Masked Autoencoder |
| ImageBIND | 20.2 | 19.7 | ImageBind: One Embedding Space To Bind Them All |
0 of 4 row(s) selected.