SOTAVerified

Speech Prompted Semantic Segmentation

Speech prompted semantic segmentation aims to predict semantic segments in an image from audio of a speaker saying the class or segment name

Papers

Showing 14 of 4 papers

TitleStatusHype
Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and LanguageCode2
ImageBind: One Embedding Space To Bind Them AllCode5
Contrastive Audio-Visual Masked AutoencoderCode2
Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input0
Show:102550

No leaderboard results yet.