wenzhengzeng/D2VLM-Dataset download history
wenzhengzeng/D2VLM-Dataset is a video text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 69 times (5 in the last 7 days), and 548 times in total. It ranks #148,091 among datasets by monthly downloads.
Dataset used in D2VLM Paper | Code Here we provided the instruction for dataset preparation. We provided the transformed annotation (or steps for transformation) tailor for D2VLM, due to the new training objective design. Dataset Name Role Source E.T. Bench Evaluation Benchma