ali-vosoughi/oscar-dataset download history

ali-vosoughi/oscar-dataset is an image to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 926 times (33 in the last 7 days), and 12,641 times in total. It ranks #20,446 among datasets by monthly downloads.

OSCaR OSCaR is the public dataset release for the NAACL 2024 paper Object State Captioning and State Change Representation. This release packages the preserved OSCaR image assets, fine-tuning manifests, benchmark split metadata, and state-caption sidecars used around the LLaVA-based t

Open ali-vosoughi/oscar-dataset on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.