AI Paper Atlas

Research map / Video / Action recognition

Ensemble Deep Learning for Skeleton-Based Action Recognition Using Temporal Sliding LSTM Networks

Inwoong Lee, Doyoung Kim, Seoungyoon Kang, Sanghoon Lee

ICCV 2017 · Video › Action recognition · approach: Skeleton-based action recognition · 437 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 human cognitive coordinate transform to LSTM (ablation)LSTM · MSR Action3Daverage accuracy (%): 71.33 -> 77.43Improved
add salient motion features on top of HCC (ablation)LSTM + HCC · MSR Action3Daverage accuracy (%): 77.43 -> 91.78Improved
add multi-term TS-LSTM ensemble (v1) on top of HCC and SMF (ablation)LSTM + HCC + SMF · MSR Action3Daverage accuracy (%): 91.78 -> 96.63Improved
add pose TS-LSTM part and its loss (v2 over v1) (ablation)Ensemble TS-LSTM · MSR Action3Daverage accuracy (%): 96.63 -> 97.22Improved
add human cognitive coordinate transform to LSTM (ablation)LSTM · UTKinect-Actionaccuracy (%): 60.61 -> 72.73Improved
add salient motion features on top of HCC (ablation)LSTM + HCC · UTKinect-Actionaccuracy (%): 72.73 -> 93.94Improved
add multi-term TS-LSTM ensemble (v1) on top of HCC and SMF (ablation)LSTM + HCC + SMF · UTKinect-Actionaccuracy (%): 93.94 -> 95.96Improved
add pose TS-LSTM part and its loss (v2 over v1) (ablation)Ensemble TS-LSTM · UTKinect-Actionaccuracy (%): 95.96 -> 96.97Improved
add pose TS-LSTM part and its loss (v2 over v1) (ablation)Ensemble TS-LSTM · NTU RGB+D (cross-subject)accuracy (%): 73.88 -> 74.60Improved
add pose TS-LSTM part and its loss (v2 over v1) (ablation)Ensemble TS-LSTM · NTU RGB+D (cross-view)accuracy (%): 80.40 -> 81.25Improved
add pose TS-LSTM part and its loss (v2 over v1) (ablation)Ensemble TS-LSTM · Northwestern-UCLAaccuracy (%): 85.99 -> 89.22Improved
add pose TS-LSTM part and its loss (v2 over v1) (ablation)Ensemble TS-LSTM · UWA3DII (cross-view mean)accuracy (%): 72.4 -> 75.6Improved

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