AlpachinoNLP/QTSplus-Dataset download history
AlpachinoNLP/QTSplus-Dataset is a visual question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 652 times (146 in the last 7 days), and 4,388 times in total. It ranks #26,827 among datasets by monthly downloads.
QTSplus-Dataset QTSplus-Dataset is a comprehensive dataset for video understanding that provides training signals for long-video multimodal language models. This dataset focuses on visual question answering with both multiple-choice (VSCQ) and free-form (VQA) formats. The scripts used