search

whwu95 / Text4Vis

【AAAI'2023 & IJCV】Transferring Vision-Language Models for Visual Recognition: A Classifier Perspective
MIT License
202 stars 15 forks source link

Pre-trained models #3

Closed bashimr closed 1 year ago

bashimr commented 1 year ago

@whwu95

Are there any pre-trained models publicly available that I can use to test zero-shot? If not, are you open to sharing the models trained on Kinetics400 for testing purpose?

Thanks,

Imran

whwu95 commented 1 year ago

Hello,

Thank you for your interest in our project and for raising this issue. We have already open-sourced our pre-trained model, which can be found in the Model Zoo Section of our Readme. Specifically, we used the pre-trained ViT-L model with 8 frames for the zero-shot evaluation on UCF, HMDB, ActivityNet, and Kinetics-600.

bashimr commented 1 year ago

@whwu95 Thank you for getting back to me. I am looking for some assistance to try out the model for an internal project. Would you be open to a paid consulting via video conferencing? Thanks.