AI Paper Atlas

Research map / Video / Action recognition

Temporal Distinct Representation Learning for Action Recognition

Junwu Weng, Donghao Luo, Yabiao Wang, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Xudong Jiang, Junsong Yuan

ECCV 2020 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 35 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 PEM (ablation)TIM baseline · Something-Something V1 val (8f)top-1 accuracy: 46.1 -> 48.7Improved
add TD Loss (ablation)TIM baseline · Something-Something V1 val (8f)top-1 accuracy: 46.1 -> 48.4Improved
add PEM and TD Loss (ablation)TIM baseline · Something-Something V1 val (8f)top-1 accuracy: 46.1 -> 49.8Improved
add PEM instead of MEM channel enhancement (ablation)TIM baseline · Something-Something V1 val (8f)top-1 accuracy: 47.4 -> 48.7Improved
add PEM (ablation)TSM baseline · Something-Something V1 val (8f)top-1 accuracy: 45.6 -> 48.1Improved
add TD Loss (ablation)TSM baseline · Something-Something V1 val (8f)top-1 accuracy: 45.6 -> 47.5Improved
add PEM and TD Loss (ablation)TSM baseline · Something-Something V1 val (8f)top-1 accuracy: 45.6 -> 48.4Improved
regularize 50% of channels with TD Loss instead of 100% (ablation)TIM + TD Loss · Something-Something V1 val (8f)top-1 accuracy: 47.3 -> 48.4Improved
place TD Loss after temporal module instead of before (ablation)TIM + TD Loss · Something-Something V1 val (8f)top-1 accuracy: 46.9 -> 48.4Improved
place PEM after temporal module instead of before (ablation)TIM + PEM · Something-Something V1 val (8f)top-1 accuracy: 48.7 -> 49.0No clear effect
vary lambda from 1e-4 to 4e-4 (ablation)TIM + TD Loss · Something-Something V1 val (8f)top-1 accuracy: 47.9, 48.4, 47.8, 48.0No clear effect
add PEM (reduces training accuracy) (ablation)TIM baseline · Something-Something V1 traintraining accuracy: 79.03 -> 77.98Hurt

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