berniebear / multi-ht100m Goto Github PK

I would like to ask whether the feature of VATEX dataset uses I3D

I find the links to your multilingual HOWTO100M become invalid. Is there any updated link to download these data?

Thanks for this job, I don’t know if the pre-train model & code will be released in the future~

Thanks to Bernie for the great work!
If anyone is looking for code to train on Multi-MSRVTT, I've released the code for my Cross-Lingual Cross-Modal Knowledge Distillation paper here. The code has instructions on how to train multilingual text-video retrieval models, and we released pre-extracted features and model weights for easy use.

We also translated the text in the YouCook2 dataset and released the dataset / features.