Entrar
insight - Mobile Sensing
IMG2IMU: Übertragung von Wissen von großen Bildern auf IMU-Sensoranwendungen
Bildwissen kann erfolgreich auf IMU-Sensoranwendungen übertragen werden, um die Leistung zu verbessern.
CODA: A COst-efficient Test-time Domain Adaptation Mechanism for Human Activity Recognition (HAR)
CODA proposes a cost-efficient domain adaptation mechanism for mobile sensing, ensuring robust adaptation to uncertain conditions.
CODA: A COst-efficient Test-time Domain Adaptation Mechanism for Human Activity Recognition
CODA proposes a cost-efficient domain adaptation mechanism for mobile sensing, addressing real-time drifts with active learning theory.
IMG2IMU: Translating Knowledge from Large-Scale Images to IMU Sensing Applications
大規模画像からIMUセンシングアプリケーションへの知識移行を可能にするIMG2IMUの効果的な提案と評価。
IMG2IMU: Leveraging Vision Knowledge for IMU Sensing Applications
The author proposes IMG2IMU to transfer knowledge from large-scale images to IMU sensing tasks, utilizing sensor-aware augmentations and spectrogram transformations. By adapting vision knowledge, IMG2IMU outperforms baselines in IMU sensing tasks with limited training data.
Produtos | Recursos
© 2024 by Linnk AI