AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Bayesian Uncertainty Attribution-Guided Fine-Tuning for Open-Set Action Recognition

Shehan Senavirathna, Hongji Guo, Qiang Ji

ECCV 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Bayesian view of meta-learning · 0 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
apply Stage 1-3 refinement to deep ensembleVanilla DE · UCF101 vs HMDB51 (all four backbones)AUROC: TPN 84.39 -> 88.62; TSM 81.83 -> 85.51; I3D 85.10 -> 87.95Improved
add Stage 3 UAM-IA to Stages 1+2 (ablation)ensemble · UCF101 vs HMDB51 (TPN)AUROC: 86.21 -> 88.62Improved
add Stage 1 motion guidance on top of Stages 2+3 (ablation)ensemble · UCF101 vs HMDB51 (TPN)AUROC: 87.76 -> 88.62Improved
Stage 1 alone vs vanilla ensemble (ablation)ensemble · UCF101 vs HMDB51 (TPN)AUROC: 84.39 -> 84.78Improved
add Stage 2 epistemic regularization (Stage 1 + 3 present) (ablation)ensemble · UCF101 vs HMDB51 (TPN)AUROC: 88.03 -> 88.62Improved
regularize epistemic uncertainty instead of aleatoric (ablation)ensemble · UCF101 vs HMDB51 (TPN)AUROC: 85.38 -> 86.21Improved
regularize total uncertainty instead of CE only (ablation)ensemble · UCF101 vs HMDB51 (TPN)AUROC: 85.43 -> 85.94Improved
regularize aleatoric uncertainty instead of CE only (ablation)ensemble · UCF101 vs HMDB51 (TPN)AUROC: 85.43 -> 85.38No clear effect
UAM-IA instead of frame-difference mask (ablation)ensemble · UCF101 vs HMDB51 (TPN)AUROC: 87.18 -> 88.62Improved
amplify low-attribution regions (UAM-IA) vs suppress high-attribution (ablation)ensemble · UCF101 vs HMDB51 (TPN)AUROC: 87.42 -> 88.62Improved
increase UAM-IA alpha from 1.00 to 2.00 (ablation)ensemble · UCF101 vs HMDB51 (TPN)AUROC: 88.62 -> 87.26Hurt
distilled student vs SOAR (single model)student · UCF101 vs MiT-v2 / HMDB51AUROC: TPN HMDB 86.67 -> 88.50; TSM HMDB 85.96 -> 84.24; I3D MiT 94.60 -> 93.98Mixed

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