AdaFocus icon indicating copy to clipboard operation
AdaFocus copied to clipboard

Reducing spatial redundancy in video recognition. SOTA computational efficiency.

Results 9 AdaFocus issues
Sort by recently updated
recently updated
newest added

Thanks for your great job which will motivate a lot of works in this area! After checking your code, i found that for frames in a video it seems to...

I use the following parameters and take mobilenet and resnet-50 which trained by TSN as pre-trained. But the training results are strange!From the beginning, the training accuracy has reached 100%,...

And the number of num_segments_glancer is different from the number of num_segments_focuser. 但是论文Figure 2. Overview of AdaFocus. 中 输入到fG网络 和 fL网络的帧是一一对应的。请问,输入到fG网络 和 fL网络的帧的需要是一一对应的吗?

Hi, when I run the program. It will raise an error about the hydra module. It seems that the "strict" parameter has already been deprecated from the hydra 1.0 version....

With the same setting and same checkpoint (128s3_checkpoint.pth.tar), 75.0 mAP cannot be reproduced in my environment (achieved 74.4 ). The difference I know is that I use FPS1 frames, the...

I'm very interseted in your works. But when I experimented with the UCF101 dataset, the results were not encouraging ( just around 1%). Looking forward to your reply. THX! The...

A wonderful work! But I have a problem with evaluation. I can't flnd the code about the article SCSampler:Sampling Salient Clips from Video for Efficient Action Recognition. How can i...

Thanks for your great work! I want to know which part of the codes is about `AdaFouces+` since I wonder how to batch-process videos with different number of frames for...

Hello. Thanks for your work. Do you have the checkpoints and the corresponding codes for evaluating AdaFocus+, which leverages temporal redundancy in your release?