Some questions on using _decode_image rather than _decode_video

[alibaba-mmai-research]

Some questions on using _decode_image rather than _decode_video

[huang-ziyuan]

Thanks for using the code.

Yes, our dataset class is designed for directly reading from videos. Despite that it is capable of reading data from images, this function is designed for MoSI to read ImageNet data. We have not tried to read video data with _decode_image.

So,
(i) It depends, since different encoding method (image/video) can result in different decoded data. But you are welcome to try.
(ii) Our _decode_video is simply based on Decord. It outputs an video object and the frames are obtained by feeding the index to it. So the important operation is the sampling strategy, which is _segment_based_sampling for datasets like Something-Something and _interval_based_sampling for Kinetics.

[jwfanDL]

Thank you so much for your reply~