Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language
Open paper
Benchmark
Model
Rank
Results
sound-prompted-semantic-segmentation-on-ade20k
DenseAV
#1
mAP: 32.7
mIoU: 24.7
speech-prompted-semantic-segmentation-on-ade20k
DenseAV
#1
mAP: 48.7
mIoU: 36.8
Rank counts only results with a code link.