1240446371

Can you provide the parameters after using how-to-100 for post-pretraining, or can you provide the parameters trained for downstream tasks? Due to limited computing resources, I would like to obtain...

In your “ zero shot text to video retrieval ” setting， you only use 1 gpu for eval，I want to kindly inquire how to use multi-gpu for evaluation？Can I change...

Thank you for your work！ But I have a question about zero shot video-retrieval task on activitynet dataset， which pretrain model I should use to reproduce the performance？Is Clip ViT-L-14.pt?...