← Back to the feed
Energy & materialsResearch findings

Successful Development of Adaptive DOF-Specific Fusion Model for Hand Kinematics

Original published 2026.11.16 03:48 KSTAdded to Blackdeck 2026.11.17 19:40 KST

What has changed?

A learnable query per degree of freedom enables context-adaptive fusion of visual and EMG data.

Key points

  1. Proposes a multimodal framework to accurately estimate 20 hand joint angles using egocentric vision and HD-sEMG.
  2. Introduces a degree-of-freedom-specific query mechanism for adaptive fusion of visual and EMG signals.
  3. Demonstrates superior performance in visually ambiguous conditions and under synthetic occlusion.

Connect it to your work

The model dynamically combines visual and EMG inputs based on the varying informativeness across joints.

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivDoF-Query Transformer for Adaptive Fusion of Egocentric Vision and Forearm HD-sEMG in Continuous Hand Kinematics