Thank you for your insightful work.
However, it is still not clear to prepare UCF101 and HMDB datasets for downstream task of audiovisual action recognition.
Could you kindly release the format of datasets (e.g. Tree -L 2)? and how to implement the data path to your work?
Thx!
Thank you for your insightful work.
However, it is still not clear to prepare UCF101 and HMDB datasets for downstream task of audiovisual action recognition.
Could you kindly release the format of datasets (e.g. Tree -L 2)? and how to implement the data path to your work?
Thx!