MAWKDN: A multimodal fusion wavelet knowledge distillation approach based on cross-view attention for action recognition

Z Quan, Q Chen, M Zhang, W Hu… - … on Circuits and …, 2023‏ - ieeexplore.ieee.org
The recognition performance of existing vision-based human action recognition (HAR)
methods is greatly reduced in the case of low camera resolution or occlusion. Wearable …

SMTDKD: A semantic-aware multimodal transformer fusion decoupled knowledge distillation method for action recognition

Z Quan, Q Chen, W Wang, M Zhang, X Li… - IEEE Sensors …, 2023‏ - ieeexplore.ieee.org
Multimodal sensors, including vision sensors and wearable sensors, offer valuable
complementary information for accurate recognition tasks. Nonetheless, the heterogeneity …

[HTML][HTML] Online continual learning for human activity recognition

M Schiemer, L Fang, S Dobson, J Ye - Pervasive and Mobile Computing, 2023‏ - Elsevier
Sensor-based human activity recognition (HAR), with the ability to recognise human
activities from wearable or embedded sensors, has been playing an important role in many …

Activity recognition in rehabilitation training based on ensemble stochastic configuration networks

W Jiao, R Li, J Wang, D Wang, K Zhang - Neural Computing and …, 2023‏ - Springer
Rehabilitation training for patients with limb activity dysfunction and sub-healthy state has
gradually shifted from therapies to strategies with remote assistance. Stochastic …

Cross-person activity recognition method using snapshot ensemble learning

S Xu, Z He, W Shi, Y Wang, T Ohtsuki… - 2022 IEEE 96th …, 2022‏ - ieeexplore.ieee.org
Human activity recognition (HAR) is one of the most promising technologies in the smart
home, especially radio frequency (RF-based) method, which has the advantages of low cost …

The Solution for the sequential task continual learning track of the 2nd Greater Bay Area International Algorithm Competition

S Pan, X Wu, T Li, L Huang, M Feng, Z Wan… - arxiv preprint arxiv …, 2024‏ - arxiv.org
This paper presents a data-free, parameter-isolation-based continual learning algorithm we
developed for the sequential task continual learning track of the 2nd Greater Bay Area …

Distribution-Level Memory Recall for Continual Learning: Preserving Knowledge and Avoiding Confusion

S Cheng, K Geng, C He, Z Qiu, L Xu… - IEEE Transactions …, 2025‏ - ieeexplore.ieee.org
Continual learning (CL) aims to enable deep neural networks (DNNs) to learn new data
without forgetting previously learned knowledge. The key to achieving this goal is to avoid …

Multi-AP CSI fusion and features optimization-based behavioral sensing on WiFi platform

J Ding, Y Wang, J Zhang, H Chen, H Si… - IEEE Sensors …, 2023‏ - ieeexplore.ieee.org
The prevalence of WiFi infrastructures has enabled the advancement of a wide range of WiFi-
based intelligent applications. Behavioral sensing, as an increasingly popular example, is …

[HTML][HTML] Non-Contact Cross-Person Activity Recognition by Deep Metric Ensemble Learning

C Ye, S Xu, Z He, Y Yin, T Ohtsuki, G Gui - Bioengineering, 2024‏ - mdpi.com
In elderly monitoring or indoor intrusion detection, the recognition of human activity is a key
task. Owing to several strengths of Wi-Fi-based devices, including their non-contact and …

Jointly prediction of activities, locations, and starting times for isolated elderly people

A Chaudhary, R Mishra, HP Gupta… - IEEE Journal of …, 2021‏ - ieeexplore.ieee.org
Restrictive public health measures such as isolation and quarantine have been used to
reduce the pandemic virus's transmission. With no proper treatment, older adults have been …