AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

MotionTransformer: Transferring Neural Inertial Tracking between Domains

Changhao Chen, Yishu Miao, Chris Xiaoxuan Lu, Linhai Xie, Phil Blunsom, Andrew Markham, Niki Trigoni

AAAI 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing · 64 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 reconstruction decoder loss (ablation)MotionTransformer · Hand to PocketMSE of label prediction: 0.313 -> 0.119Improved
add reconstruction decoder loss (ablation)MotionTransformer · Hand to BagMSE of label prediction: 0.335 -> 0.123Improved
add reconstruction decoder loss (ablation)MotionTransformer · Hand to TrolleyMSE of label prediction: 0.113 -> 0.098Improved
add perceptual consistency loss (ablation)MotionTransformer · Hand to PocketMSE of label prediction: 0.315 -> 0.119Improved
add perceptual consistency loss (ablation)MotionTransformer · Hand to BagMSE of label prediction: 0.202 -> 0.123Improved
add perceptual consistency loss (ablation)MotionTransformer · Hand to TrolleyMSE of label prediction: 0.140 -> 0.098Improved
domain adaptation with MotionTransformer vs source-onlyMotionTransformer · Hand to BagMSE of label prediction: 1.129 -> 0.123Improved
MotionTransformer vs CyCADA with LSTMMotionTransformer · Hand to PocketMSE of label prediction: 0.237 -> 0.119Improved
MotionTransformer vs ADDA with LSTMMotionTransformer · Hand to TrolleyMSE of label prediction: 0.216 -> 0.098Improved
add 1K labelled target sequences (semi-supervised) (ablation)MotionTransformer · Hand to BagMSE of label prediction: 0.123 -> 0.075Improved
add 1K labelled target sequences (semi-supervised) (ablation)MotionTransformer · Hand to PocketMSE of label prediction: 0.119 -> 0.113No clear effect

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