AI Paper Atlas

Research map / 3D vision / 3D generation

3D Single-Person Concurrent Activity Detection Using Stacked Relation Network

Yi Wei, Wenbo Li, Yanbo Fan, Linghan Xu, Ming-Ching Chang, Siwei Lyu

AAAI 2020 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 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 relation layers in both RN-PP and RN-CLS (vs none) (ablation)SRN · UCLA concurrent activityMAP: 0.81 -> 0.93Improved
Add relation layers in RN-CLS only (vs none) (ablation)SRN · UCLA concurrent activityMAP: 0.81 -> 0.89Improved
Add relation layers in RN-PP (vs none in RN-PP) (ablation)SRN · UCLA concurrent activityOAP: 0.85 -> 0.91Improved
Add T-relation module in RN-CLS (ablation)SRN · UCLA concurrent activityMAP: 0.87 -> 0.93Improved
Add T-relation module to RN-PP as well (ablation)SRN · UCLA concurrent activityMAP: 0.93 -> 0.87Hurt
Add T-relation to RN-PP (ablation)SRN · UCLA concurrent activityER: 0.22 -> 0.24Hurt
Combine attentive weight with learnable base weight (vs learnable only) (ablation)SRN · UCLA concurrent activityMAP: 0.88 -> 0.93Improved
Combine learnable base weight with attentive weight (vs attentive only) (ablation)SRN · UCLA concurrent activityMAP: 0.83 -> 0.93Improved
Use decompositional class-wise representation instead of unified representation (ablation)SRN · UCLA concurrent activityER: 0.40 -> 0.22Improved
Use decompositional class-wise representation instead of unified representation (ablation)SRN · UCLA concurrent activityMAP: 0.86 -> 0.93Improved
SRN vs AGCN with same input featuresSRN · UCLA concurrent activityMAP: 0.86 -> 0.93Improved
SRN vs best baseline on new datasetSRN · New concurrent activity datasetOAP: 0.57 -> 0.61Improved

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