tsinghua-ee/video-SALMONN_2_testset download history
tsinghua-ee/video-SALMONN_2_testset is a video text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 452 times (5 in the last 7 days), and 4,518 times in total. It ranks #35,873 among datasets by monthly downloads.
video-SALMONN 2 Benchmark Github Link Paper Link Generate the caption corresponding to the video and the audio with video_salmonn2_test.json Organize your results in the format like the following example: [ { "id": ["0.mp4"], "pred": "Generated Caption" } ] Re