For those data samples in VideoChat2-IT/video/conversation/videochat2/train.json, I'm wondering how these videos are downloaded and processed. I found the original Internvid(the source videos for videochat2) has different naming patterns for videos. For example, your data sample in this json file is 'LLP1dosmfIw_683.24.mp4', while the one I downloaded is '0ABL-ETtK44_00:01:55.680_00:02:00.880.mp4 '.
For those data samples in VideoChat2-IT/video/conversation/videochat2/train.json, I'm wondering how these videos are downloaded and processed. I found the original Internvid(the source videos for videochat2) has different naming patterns for videos. For example, your data sample in this json file is 'LLP1dosmfIw_683.24.mp4', while the one I downloaded is '0ABL-ETtK44_00:01:55.680_00:02:00.880.mp4 '.