choucsan/VSI-33K download history

choucsan/VSI-33K is a visual question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 279 times (35 in the last 7 days), and 566 times in total. It ranks #51,971 among datasets by monthly downloads.

VSI-33K     VSI-33K is a compact, task-balanced video spatial-reasoning dataset derived from the ScanNet branch of VSI-590K. It contains 33,000 English video question-answer pairs grounded in 1,201 indoor ScanNet scene videos. The dataset is intended as a small,

Open choucsan/VSI-33K on Hugging Face

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