AI Paper Atlas

Research map / Video / Action recognition

MoBind: Motion Binding for Fine-Grained IMU-Video Pose Alignment

Duc Duy Nguyen, Tat-Jun Chin, Minh Hoai

CVPR 2026 · Video › Action recognition · approach: Temporal action segmentation · 1 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 Masked Token Prediction auxiliary task (ablation)MoBind · TotalCapture action recognition (finetune)accuracy: 0.55 -> 0.72Improved
Add Masked Token Prediction auxiliary task (ablation)MoBind · TotalCapture action recognition (1-NN)accuracy: 0.53 -> 0.71Improved
Add Masked Token Prediction auxiliary task (ablation)MoBind · mRi action recognition (1-NN)accuracy: 0.76 -> 0.86Improved
Add Masked Token Prediction auxiliary task (ablation)MoBind · mRi action recognition (finetune)accuracy: 0.97 -> 0.98Improved
Add hierarchical contrastive levels (token, local, global) (ablation)MoBind · mRiR@1, sync, localizationImproved
Align IMU with 2D pose rather than raw video, with local plus global alignment vs global-only baselinesMoBind · TotalCapture retrievalR@1 IMU->Video: 0.51 -> 0.87Improved
Hierarchical body-part alignment vs best baseline for synchronizationMoBind · EgoHumans synchronizationMAE (s): 1.01 -> 0.04Improved
Use longer clips for synchronizationMoBind · mRi synchronizationaccuracy: 97% (2-min) -> 100% (3-min)Improved
Offset-classification baseline instead of contrastive embeddingIMUSync · EgoHumans synchronizationaccuracy: 0.82 vs 1.00 (MoBind)No clear effect
Add random sensor dropout trainingMoBind · TotalCapture retrievalR@kImproved
Use IMU-to-CLIP style global-only alignmentIMU2CLIP · TotalCapture retrievalR@1 IMU->Video: 0.87 (MoBind) vs 0.06Hurt

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