NKU-2urSt8g

Thanks for your exciting work~ But I have met a question when preparing the dataset. In your JSON file annotation, I notice variances named "plane_paras" for each plane. Could you...

[MBT] Input Data Format for AudioSet

2

Hello, I'm working on reproduce the results in your paper "Attention Bottlenecks for Multimodal Fusion" and try to implement MBT for other audiovisual video classification tasks. However, the preprocessing for...

Missed File

1

Thank you for your significant work! But the checkpoint of ResNet18 version is missed. Could you kindly update it? Thank you!

How to implement Multi-GPU for training

3

I've tried to implement data-parallel for training in multi-GPUs but it doesn't work. The model only runs in my first GPU. So I replace the model with ResNet with no...

Seems that there needs a well-trained model for demo.py. For comparison, could you kindly release this model?

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...