AI Paper Atlas

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

Multimodal Fusion via Teacher-Student Network for Indoor Action Recognition

Bruce X.B. Yu, Yan Liu, Keith C.C. Chan

AAAI 2021 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 67 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 teacher-derived spatial weights to the RGB student network while training both networks (ablation)ResNet18 student · NTU RGB+Daccuracy: 77.0 -> 79.5Improved
Add teacher-derived spatial weights to the RGB student network while training both networks (ablation)ResNet18 student · PKU-MMDaccuracy: 75.2 -> 76.4Improved
Use teacher-derived spatial weights with the teacher fixed in evaluation mode (ablation)ResNet18 student · NTU RGB+Daccuracy: 77.0 -> 81.5Improved
Use teacher-derived spatial weights with the teacher fixed in evaluation mode (ablation)ResNet18 student · PKU-MMDaccuracy: 75.2 -> 82.5Improved
Freeze the teacher while training the spatial-weight student rather than updating both networks (ablation)ResNet18 student · NTU RGB+Daccuracy: 79.5 -> 81.5Improved
Freeze the teacher while training the spatial-weight student rather than updating both networks (ablation)ResNet18 student · PKU-MMDaccuracy: 76.4 -> 82.5Improved
Add the RGB student prediction without spatial weights to the ST-GCN prediction (ablation)ST-GCN · NTU RGB+Daccuracy: 85.2 -> 91.9Improved
Add the frozen-teacher spatial-weight student prediction to MS-G3D (ablation)MS-G3D · NTU RGB+Daccuracy: 92.3 -> 95.0Improved
Add the frozen-teacher spatial-weight student prediction to MS-G3D (ablation)MS-G3D · PKU-MMDaccuracy: 95.6 -> 96.8Improved
Add the frozen-teacher spatial-weight student prediction to AGCN (ablation)AGCN · NTU RGB+Daccuracy: 86.7 -> 93.0Improved
Add the frozen-teacher spatial-weight student prediction to AGCN (ablation)AGCN · PKU-MMDaccuracy: 94.9 -> 96.6Improved

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