Improving IMU based human activity recognition using simulated multimodal representations and a MoE classifier

The lack of labeled sensor data for Human Activity Recognition (HAR) has driven researchers to synthesize Inertial Measurement Unit (IMU) data from video, utilizing the rich activity annotations available in video datasets. However, current synthetic IMU data often struggles to capture subtle, fine-...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	Lala Shakti Swarup Ray, Qingxin Xia, Vitor Fortes Rey, Kaishun Wu, Paul Lukowicz
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	Frontiers Media S.A. 2025-08-01
Σειρά:	Frontiers in Computer Science
Θέματα:	HAR sensor simulation multi-modal learning pretraining MoE classifier
Διαθέσιμο Online:	https://www.frontiersin.org/articles/10.3389/fcomp.2025.1569205/full
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!