AI Paper Atlas

Research map / Video / Action recognition

Part-Activated Deep Reinforcement Learning for Action Prediction

Lei Chen, Jiwen Lu, Zhanjie Song, Jie Zhou

ECCV 2018 · Video › Action recognition · approach: Skeleton-based action recognition · 53 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 reinforcement-learned part activation (ablation)skeleton proposal features · UTI Set #1 (OR=0.5)accuracy (%): 76.7 -> 91.7Improved
add reinforcement-learned part activation (ablation)skeleton proposal features · UTI Set #1 (OR=1.0)accuracy (%): 91.7 -> 96.7Improved
add reinforcement-learned part activation (ablation)skeleton proposal features · UTI Set #2 (OR=0.5)accuracy (%): 70.0 -> 83.3Improved
add reinforcement-learned part activation (ablation)skeleton proposal features · UTI Set #2 (OR=1.0)accuracy (%): 86.7 -> 91.7Improved
add reinforcement-learned part activation (ablation)skeleton proposal features · BIT-Interaction (OR=0.5)accuracy (%): 68.6 -> 85.9Improved
add reinforcement-learned part activation (ablation)skeleton proposal features · BIT-Interaction (OR=1.0)accuracy (%): 87.5 -> 91.4Improved
add local patch appearance features around joints to skeleton-only features (ablation)skeleton feature · UTI Set #1 (OR=0.5)accuracy (%): 69.9 -> 76.7Improved
add local patch appearance features around joints to skeleton-only features (ablation)skeleton feature · BIT-Interaction (OR=1.0)accuracy (%): 75.7 -> 87.5Improved
add local patch appearance features around joints to skeleton-only features (ablation)skeleton feature · UTI Set #2 (OR=0.5)accuracy (%): 66.7 -> 70.0Improved
use PA-DRL instead of AAC at half observationAAC · UTI Set #1 (OR=0.5)accuracy (%): 88.3 -> 91.7Improved
use PA-DRL instead of C3D recognition model at half observationC3D · UCF101 (OR=0.5)accuracy (%): 80.0 -> 87.3Improved
use PA-DRL instead of AAC at full observation on UTI Set #2AAC · UTI Set #2 (OR=1.0)accuracy (%): 63.9 -> 91.7Improved

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