Dynamic Influence-Weighted Distillation for Single-IMU Activity Recognition

Not provided in the abstract

knowledge distillationactivity recognitionsensor fusion

2608.24904

Builder Relevance

80%

3h ago

Abstract

The paper presents a method to enhance single-IMU activity recognition by leveraging multi-IMU training data through dynamic influence weighting.

Reality Card

Core Claim

Dynamic Influence Weighting (DIW) improves the performance of a single-IMU model by achieving a pooled out-of-fold macro-F1 score of 0.638451, surpassing both Supervised and Fixed-weight KD methods.

Method / Result

DIW achieved a 7.66 percentage point improvement over Supervised methods in activity recognition.

Limitations

The study relies on a specific dataset (WEAR) and may not generalize to other datasets or real-world applications without further validation.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.

← Back to all papers