AI Paper Atlas

Research map / Video / Action recognition

Open Set Action Recognition via Multi-Label Evidential Learning

Chen Zhao, Dawei Du, Anthony Hoogs, Christopher Funk

CVPR 2023 · Video › Action recognition · approach: Disentangled 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
Use MULE with R-50 instead of DEAR with R-50AVA · AVA open setAUROC: 82.12 -> 86.92Improved
Use MULE with R-101 instead of DEAR with R-50AVA · AVA open setAUROC: 82.12 -> 88.75Improved
Use MULE with R-50 instead of DEAR with R-50Charades · Charades open setAUROC: 86.15 -> 85.49No clear effect
Use MULE with R-101 instead of DEAR with R-50Charades · Charades open setAUROC: 86.15 -> 88.49Improved
Add ACO-R actor-context-object relation representation (ablation)MULE · AVA open setAUROC: 51.23 -> 86.92Improved
Add Beta-ENN evidential learning (ablation)MULE · AVA open setAUROC: 57.10 -> 86.92Improved
Add M-EDC evidence debiasing constraint (ablation)MULE · AVA open setAUROC: 86.00 -> 86.92Improved
Use Beta loss instead of the ablated classifier/loss setup (ablation)MULE · AVA closed setmAP: 28.81 vs. 27.80Hurt

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