AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Video Classification With Channel-Separated Convolutional Networks

Du Tran, Heng Wang, Lorenzo Torresani, Matt Feiszli

ICCV 2019 · Architectures and efficiency › CNN design · approach: Group convolution theory · 666 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
channel-separate 3D convs (ir-CSN) in 26-layer net (ablation)ResNet3D-26 · Kinetics-400 val (8-frame ablation)video top-1: 65.3 -> 62.4Hurt
channel-separate with interaction preserved (ip-CSN) in 26-layer net (ablation)ResNet3D-26 · Kinetics-400 val (8-frame ablation)video top-1: 65.3 -> 64.6Hurt
channel separation (ir-CSN) in 50-layer net (ablation)ResNet3D-50 · Kinetics-400 val (8-frame ablation)video top-1: 69.4 -> 70.3Improved
channel separation (ip-CSN) in 50-layer net (ablation)ResNet3D-50 · Kinetics-400 val (8-frame ablation)video top-1: 69.4 -> 70.8Improved
channel separation (ir-CSN) in 101-layer net (ablation)ResNet3D-101 · Kinetics-400 val (8-frame ablation)video top-1: 70.6 -> 71.3Improved
channel separation (ip-CSN) in 101-layer net (ablation)ResNet3D-101 · Kinetics-400 val (8-frame ablation)video top-1: 70.6 -> 71.8Improved
preserve channel interactions (ip-CSN over ir-CSN) in 26-layer net (ablation)CSN-26 · Kinetics-400 val (8-frame ablation)video top-1: 62.4 -> 64.6Improved
remove ReLU between 1x1x1 and 3x3x3 layers (ablation)ip-CSN · Kinetics-400 val (8-frame ablation)video top-1No clear effect
add space-time decomposition of 3D filters (ablation)ir-CSN-50 · Kinetics-400 val (8-frame ablation)video top-1: 70.3 -> 69.7Hurt
apply group convolution to 1x1x1 layers (bottleneck-DG) (ablation)bottleneck-D · Kinetics-400 val (8-frame ablation)video top-1 accuracyHurt
pretrain on Sports1M before Kinetics (ablation)ip-CSN-152 · Kinetics-400 valvideo top-1: 77.8 -> 79.2Improved
pretrain on Sports1M before Kinetics (ablation)ir-CSN-101 · Kinetics-400 valvideo top-1: 76.2 -> 78.1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy