Nobuyuki Oishi, Philip Birch, Paula Lago, Daniel Roggen, “Physically plausible data augmentations in contrastive learning for wearable IMU-based activity recognition,” Knowledge-Based Systems, 348, 2026,
https://doi.org/10.1016/j.knosys.2026.116367.
Our new paper on physically plausible data augmentation for wearable
https://ieeexplore.ieee.org/document/11391511
N. Oishi, P. Birch, D. Roggen and P. Lago, “Physically Plausible Data Augmentations for Wearable IMU-based Human Activity Recognition Using Physics Simulation,” in IEEE Sensors Journal, doi: 10.1109/JSEN.2026.3661047.
A New Paper on Low Light Enhancement
C. Liu, Z. Wang, P. Birch and X. Wang, “Efficient Retinex-Based Framework for Low-Light Image Enhancement without Additional Networks,” in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2024.3520802.
New Paper on augmentation in human activity recognition
Oishi, Nobuyuki, Phil Birch, Daniel Roggen, and Paula Lago. 2025. “WIMUSim: Simulating Realistic Variabilities in Wearable IMUs for Human Activity Recognition.” Frontiers of Computer Science 7 (January): 1514933.
https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2025.1514933/full
ETTrack: enhanced temporal motion predictor for multi-object tracking
Han, X., Oishi, N., Tian, Y. et al. ETTrack: enhanced temporal motion predictor for multi-object tracking. Appl Intell 55, 33 (2025). https://doi.org/10.1007/s10489-024-05866-4
Our new paper on tracking multiple people using a transformer to learn complex motion patterns.