jqsun98

I think it's a little bit difficult for me to finish my task with colab and I may be supposed to use a Linux machine.

The error also occurs.

so how could get the RGB and flow data? There is always a problem when unzipping these two zip files.

Except for pretrained model based on CLIP ViT-B/16, could you please upload the model's pretrained checkpoint file based on ViT-L/14? It achieves much competitive results on MSR-VTT and MSVD benchmarks....

Thanks for your advice! According to your suggestions, I have found the "InternVid-10M-FLT-INFO.jsonl" file, which contains the YoutubeID, Start_timestamp and End_timestamp. Then I convert timestamp in the form of seconds....