9 citations · 14 across the 3 of their papers we have counts for
4 papers · 1 filter
Deconfounding Causal Inference through Two-Branch Framework with Early-Forking for Sensor-Based Cross-Domain Activity Recognition
Di Xiong, Lei Zhang, Shuoyuan Wang +2
Recently, domain generalization (DG) has emerged as a promising solution to mitigate distribution-shift issue in sensor-based human activity recognition (HAR) scenario. However, mo…
Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning
Di Xiong, Shuoyuan Wang, Lei Zhang +2
Human Activity Recognition (HAR) aims to recognize activities by training models on massive sensor data. In real-world deployment, a crucial aspect of HAR that has been largely ove…
Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence
Wenbo Huang, Jinghui Zhang, Guang Li +6
In few-shot action recognition (FSAR), long sub-sequences of video naturally express entire actions more effectively. However, the high computational complexity of mainstream Trans…
Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition
Shuoyuan Wang, Jindong Wang, HuaJun Xi +3
Human Activity Recognition (HAR) models often suffer from performance degradation in real-world applications due to distribution shifts in activity patterns across individuals. Tes…