AI Paper Atlas

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

Towards Good Practices for Missing Modality Robust Action Recognition

Sangmin Woo, Sumin Lee, Yeonju Park, Muhammad Adi Nugroho, Changick Kim

AAAI 2023 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 60 citations (OpenAlex)

This paper tried a common change: Add dropout

Add dropout with p=0.1 · NTU60 · accuracy: 93.3 -> 92.6 Hurt

What 795 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 transformer fusion instead of summationResNet34 multimodal classifier · NTU60, missing modality settingsmean absolute accuracy discrepancy: 34.8 -> 21.0Improved
Add ImageNet initialization to the space encoderResNet34 multimodal classifier · NTU60, RGB+D+I and RGB+D to RGBaccuracy: 85.9 -> 89.2; 34.8 -> 39.5Improved
Add shifted center cropResNet34 multimodal classifier · NTU60accuracy: 89.2 -> 90.5; 39.5 -> 40.3Improved
Add temporal random samplingResNet34 multimodal classifier · NTU60accuracy: 90.5 -> 91.0; 40.3 -> 41.4Improved
Apply color jitter to RGBResNet34 multimodal classifier · NTU60accuracy: 91.0 -> 92.2; 41.4 -> 42.0Improved
Add label smoothing with α=0.1ResNet34 multimodal classifier · NTU60accuracy: 92.2 -> 93.3; 42.0 -> 42.5Improved
Apply color jitter to depth maps (ablation)ResNet34 multimodal classifier · NTU60, all modalitiesaccuracy: 93.3 -> 91.5Hurt
Add dropout with p=0.1 (ablation)ResNet34 multimodal classifier · NTU60accuracy: 93.3 -> 92.6Hurt
Add ActionMAE feature reconstruction and randomized modality droppingTransformer-fusion classifier · NTU60, infrared-only inferenceaccuracy: 35.4% -> 81.7%Improved
Add ActionMAE to transformer fusionTransformer-fusion classifier · NTU60, all modalitiesaccuracy: 92.6% -> 93.0%Improved
Add a memory token (ablation)ActionMAE (R+D) · NTU60, RGB+Daccuracy: 87.3 -> 92.5Improved
Add a memory token (ablation)ActionMAE (R+D) · NTU60, RGB-only inferenceaccuracy: 74.8 -> 84.5Improved

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