lironui/VoiceAeroRef download history
lironui/VoiceAeroRef is an image segmentation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 629 times (97 in the last 7 days), and 1,144 times in total. It ranks #27,576 among datasets by monthly downloads.
VoiceAeroRef VoiceAeroRef is an audio-guided referring image segmentation resource for aerial and remote-sensing imagery. It pairs RISBench image-expression-mask triplets with spoken English referring expressions and provides controlled speech-corruption splits for robustness evaluati
Open lironui/VoiceAeroRef on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.