AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

See Your Emotion from Gait Using Unlabeled Skeleton Data

Haifeng Lu, Xiping Hu, Bin Hu

AAAI 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Contrastive versus non-contrastive theory · 24 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 ACL ambiguity samples (ablation)GE-CLR on E-Gait · E-Gait, linear evaluationtop-1 accuracy: 76.38 -> 78.67Improved
Add C3L cross-coordinate supervision without ACL (ablation)GE-CLR on E-Gait · E-Gait, linear evaluationtop-1 accuracy: 76.38 -> 76.83Improved
Add both ACL and C3L (ablation)GE-CLR on E-Gait · E-Gait, linear evaluationtop-1 accuracy: 76.38 -> 79.59Improved
Use upsampling playback speed r=4 rather than r=2 (ablation)ACL with HSMB on E-Gait · E-Gait, ACL playback-speed ablationtop-1 accuracy: 77.06 -> 78.67Improved
Use upsampling playback speed r=8 rather than r=2 (ablation)ACL with HSMB on E-Gait · E-Gait, ACL playback-speed ablationtop-1 accuracy: 77.06 -> 78.67Improved
Add ACL to Cartesian-coordinate input (ablation)GE-CLR on E-Gait · E-Gait, Cartesian-coordinate ablationtop-1 accuracy: 76.38 -> 78.67Improved
Add ACL to Spherical-coordinate input (ablation)GE-CLR on E-Gait · E-Gait, Spherical-coordinate ablationtop-1 accuracy: 72.02 -> 74.08Improved
Add ACL to cross-coordinate learning (ablation)GE-CLR with C3L on E-Gait · E-Gait, cross-coordinate ablationtop-1 accuracy: 76.83 -> 79.59Improved
Use Cartesian and Spherical coordinates together instead of Cartesian alone (ablation)GE-CLR on E-Gait · E-Gait, coordinate ablationtop-1 accuracy: 76.38 -> 76.83Improved

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