COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition
Baiyu Chen, Zechen Li, Flora D. Salim
Proc. ACM IMWUT 10· 2026
IMUDOI
Summary
Teacher/student-agnostic (video: VideoMAE, TimeSformer; time-series: MOMENT, Mantis). Reported to improve downstream egocentric HAR across several datasets, matching or beating fully supervised models, with strong cross-dataset generalisation.
Key facts
- Venue: Proc. ACM IMWUT 10(2), published 2026-06-15 (CC BY 4.0); presented at UbiComp/ISWC 2026 (Shanghai, week of 2026-10-12)
- Signals: accel, gyro
- Form factor: head
Updated: Oct 12, 2026
Related Research
- AutoResearcHAR: A Multi-Agent Framework for Dataset Adaptive IMU Based Human Activity Recognition
Treats IMU-HAR as a whole-pipeline optimisation problem run by LLM agents: a Data Agent (source sele
- Lapras: Latent Reasoning for Time Series Language Models
Post-training framework for time-series language models (TSLMs): instead of verbalising the signal i
- REFIT: Recognize, Fix, and Test Wearable Sensor Placement Shifts without Labels
A gradient-free, label-free input calibration that sits in front of a frozen IMU activity classifier