AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Modality-Aware Out-of-Distribution Detection for Multi-Modal Action Recognition

Lars Doorenbos, Duc Vu, Serdar Ozsoy, Juergen Gall

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 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
add audio to video and optical flow (ablation)Ours · EPIC-Kitchens:Kinetics Far-OODFPR@95: 12.8 -> 10.8Improved
add optical flow to video (ablation)Ours · EPIC-Kitchens:Kinetics Far-OODFPR@95: 15.4 -> 12.8Improved
combine feature, modality and probability scores instead of feature score r(x) alone (ablation)Ours · Near-OODFPR@95: 7.6Improved
use class-conditional linear map instead of single shared linear map (ablation)Ours · Kinetics-600 Near-OOD (late fusion)FPR@95: 63.3 -> 63.0No clear effect
use class-conditional linear map instead of fully connected map (ablation)Ours · Kinetics-600 Near-OOD (late fusion)FPR@95: 63.4 -> 63.0No clear effect
use full validation set instead of 1% subset (ablation)Ours · Kinetics-600 Near-OODAUC: 77.2 -> 77.0No clear effect
use probability distributions instead of logits for the distance (ablation)Ours · Kinetics Near/Far-OODFPR@95Improved
use different distance function (ablation)Ours · Kinetics Near-OOD and Kinetics:HMDB Far-OODFPR@95: 0.6No clear effect
use invariants (lowest-variance directions) instead of kNN or class-wise Mahalanobis for r(x) (ablation)Ours · Kinetics Near-OODFPR@95Improved
use relation between uni- and multi-modal predictions instead of A2D uni-modal disagreement (ablation)Ours s(x) · Kinetics Near-OODFPR@95: 9.9Improved
use relation between uni- and multi-modal predictions instead of A2D uni-modal disagreement (ablation)Ours s(x) · Kinetics:HMDB Far-OODFPR@95: 16.0Improved
add uni-modal heads post hoc instead of training with them (ablation)Ours · HMDB Near-OODFPR@95: 33.8 -> 34.2No clear effect

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