--- license: apache-2.0 --- Audio: 1. LibriSpeech test clean full set 2. Audio caps test full set Video: 1. NExTQA: nextqa_test.json ID provided in the "image" field Image: 1. Flickr30k: flickr30k_c
这个数据集是Reasoning-Intensive Video with Audio understanding Benchmark (RivaBench)的三个分区，包括Academic、StandUp和synthetic video detection。Academic和StandUp部分包含视频和音频资源，而synthetic video detection部分则提供了视频及其是否为合成的信
