Skip to content


Repository files navigation

Similarity Guided Sampling

Source code of the CVPR 2021 paper: "3D CNNs with Adaptive Temporal Feature Resolutions".

Similarity Guided Sampling

Similarity Guided Sampling (SGS) is a differentiable module which can be plugged into existing 3D CNN architecture to reduce the computational cost (GFLOPs) while preserving the accuracy.

    Author    = {Mohsen Fayyaz, Emad Bahrami, Ali Diba, Mehdi Noroozi, Ehsan Adeli, Luc Van Gool, Juergen Gall},
    Title     = {{3D CNNs with Adaptive Temporal Feature Resolutions}},
    Booktitle = {{The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) }},
    Year      = {2021}


Please find installation instructions in You may follow the instructions in to prepare the datasets.

Quick Start

Follow the example in


The majority of this work is licensed under Apache 2.0 license. Portions of the project are available under separate license terms: SlowFast and 3D-ResNets-PyTorch.


The code is adapted from the following repositories: