search

dhg-wei / TOPA

(NeurIPS 2024 Spotlight) TOPA: Extend Large Language Models for Video Understanding via Text-Only Pre-Alignment
MIT License
17 stars 0 forks source link

TEXT VID DATASET AND MODEL CHECKPOINT #2

Closed Divyanshupy closed 1 month ago

Divyanshupy commented 1 month ago

Dear Team,

Thank you for the amazing work. I was wondering if it was possible to release the dataset and the model checkpoints for the TOPA paper.

Thank you again for the amazing work.

WangWenhao0716 commented 1 month ago

+1

WangWenhao0716 commented 1 month ago

Also, an inference demo is expected. For example, something like this one is good: https://github.com/WangWenhao0716/AnyPatternStyle

dhg-wei commented 1 month ago

Thank you for your interest in our work! The data and checkpoints are released~

WangWenhao0716 commented 1 month ago

Thanks for authors' reply. Congrats for being accepted as Spotlight in NeurIPS 2024

Divyanshupy commented 1 month ago

Thank you so much and congratulations.

Divyanshupy commented 1 month ago

Hey, first of all, the code is very well-written and easy to follow. I have a request, will it be possible to share the text_vid dataset clip features and memory features you use for training/evaluating the model? Thank you again.

dhg-wei commented 1 month ago

@Divyanshupy Updated!

Divyanshupy commented 1 month ago

Amazing work and thank you for the help. I am closing the issue now.