AI Paper Atlas

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

A Unified Multimodal De- and Re-Coupling Framework for RGB-D Motion Recognition

Benjia Zhou, Pichao Wang, Jun Wan, Yanyan Liang, Fan Wang

TPAMI 2023 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 39 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 multi-stage recoupling (3 RCM modules instead of 1) (ablation)UMDR · NTU RGB-D CS (RGB, 32 frames)accuracy: 91.46 -> 92.24Improved
add multi-stage recoupling (3 RCM modules instead of 1) (ablation)UMDR · NvGesture (RGB, 32 frames)accuracy: 84.52 -> 86.25Improved
add multi-stage recoupling (3 RCM modules instead of 1) (ablation)UMDR · NTU RGB-D CS (RGB, 16 frames)accuracy: 90.81 -> 91.37Improved
add recoupling self-distillation loss (lambda_d 0.2) (ablation)UMDR · NvGesture (RGB, 32 frames)accuracy: 85.04 -> 86.25Improved
add recoupling self-distillation loss (lambda_d 0.2) (ablation)UMDR · NTU RGB-D CS (RGB, 32 frames)accuracy: 91.56 -> 92.24Improved
raise recoupling loss weight from 0.2 to 0.3 (ablation)UMDR · NTU RGB-D CS (RGB, 32 frames)accuracy: 92.24 -> 91.87Hurt
use batch-wise instead of pair-wise ShuffleMix+ (ablation)UMDR · NTU RGB-D CS (RGB, 32 frames)accuracy: 91.41 -> 92.24Improved
use discrete instead of continuous temporal mixing (ablation)UMDR · IsoGD (RGB, 32 frames)accuracy: 63.18 -> 63.68Improved
use continuous instead of discrete temporal mixing (ablation)UMDR · NvGesture (RGB, 32 frames)accuracy: 86.25 -> 86.88Improved
add MixUp alone (alpha_m 0.8) to baselineUMDR · IsoGD (RGB)accuracy: +7.63%Improved
add MixUp alone to baseline on small-scale data (ablation)UMDR · NvGestureaccuracyNo clear effect
add ShuffleMix to MixUp (ShuffleMix+) on small datasets (ablation)UMDR · NvGestureaccuracy: +2.1%Improved

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