AI Paper Atlas

Research map / Video / Action recognition

CoTeRe-Net: Discovering Collaborative Ternary Relations in Videos

Zhensheng Shi, Cheng Guan, Liangjie Cao, Qianqian Li, Ju Liang, Zhaorui Gu, Haiyong Zheng, Bing Zheng

ECCV 2020 · Video › Action recognition · approach: Disentangled action recognition · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
add channel relations (r=1) (ablation)3D ResNet-18 · Something-Something V1 (ablation, from scratch)top-1 accuracy: 43.1 -> 44.2Improved
add temporal relations (r=32) (ablation)3D ResNet-18 · Something-Something V1 (ablation, from scratch)top-1 accuracy: 43.1 -> 44.5Improved
add spatial relations with 3x3 convolution instead of 1x1 (ablation)3D ResNet-18 · Something-Something V1 (ablation, from scratch)top-1 accuracy: 43.4 -> 44.7Improved
lower MLP reduction ratio for channel relations (r=4 to r=1) (ablation)CoTeRe-ResNet-18 · Something-Something V1 (ablation, from scratch)top-1 accuracy: 43.3 -> 44.2Improved
lower MLP reduction ratio for temporal relations (r=128 to r=32) (ablation)CoTeRe-ResNet-18 · Something-Something V1 (ablation, from scratch)top-1 accuracy: 43.3 -> 44.5Improved
collaborate channel and temporal relations instead of one relation alone (ablation)CoTeRe-ResNet-18 · Something-Something V1 (ablation, from scratch)top-1 accuracy: 44.5 -> 44.9Improved
collaborate temporal and spatial relations (ablation)CoTeRe-ResNet-18 · Something-Something V1 (ablation, from scratch)top-1 accuracy: 44.7 -> 45.4Improved
add all three relations (ternary) instead of temporal+spatial (ablation)CoTeRe-ResNet-18 · Something-Something V1 (ablation, from scratch)top-1 accuracy: 45.4 -> 45.8Improved
combine ternary relations by addition instead of the product form of Eq. 12 (ablation)CTSR module · Something-Something V1 (ablation, from scratch)top-1 accuracy: about 0.3% lowerHurt
add CTSR modules (CoTeRe-Net) to ResNet-34 baseline, no pretrainResNet-34 · Something-Something V1top-1 accuracy: 47.2 -> 49.7Improved
add CTSR modules (CoTeRe-Net) to ResNet-34 baseline, no pretrainResNet-34 · Something-Something V2top-1 accuracy: 60.8 -> 63.2Improved
use ResNet-34 instead of ResNet-18 backbone (Kinetics pretrain) (ablation)CoTeRe-Net · Something-Something V1top-1 accuracy: 50.5 -> 52.8Improved

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