search

Anirudh257 / strm

[CVPR 2022] Official Pytorch Implementation for "Spatio-temporal Relation Modeling for Few-shot Action Recognition". SOTA Results for Few-shot Action Recognition
https://anirudh257.github.io/strm/
98 stars 16 forks source link

question in extracting frames #9

Closed hitomizzz closed 2 years ago

hitomizzz commented 2 years ago

hi, thank you for your excellent work. I'm also interested in this research field, but I have several questions in preparing the dataset.

  1. how do you extract the videos into frames, did you use ffmpeg?
  2. if you used ffmpeg to extract the frames, can you share me with the detail of it? Such as how many fps(-r) do you extract each video and the quality (-q:v).

Thank you so much!

Anirudh257 commented 2 years ago

@hitomizzz Thanks for your interest in our work.

  1. Yes, I used FFmpeg.

  2. Please, follow the TRX paper for details: image

The paper can be found here: https://openaccess.thecvf.com/content/CVPR2021/papers/Perrett_Temporal-Relational_CrossTransformers_for_Few-Shot_Action_Recognition_CVPR_2021_paper.pdf