9 citations · 17 across the 4 of their papers we have counts for
6 papers
Efficient Video Dataset Distillation via Cluster-Guided Prototype Blending
Chongle Ren, Guang Li, Wenbo Huang +3
Video dataset distillation aims to compress a large video dataset into a compact surrogate set that preserves its training utility. Most existing approaches synthesize condensed vi…
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…
SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action Recognition
Wenbo Huang, Jinghui Zhang, Xuwei Qian +3
High frame-rate (HFR) videos of action recognition improve fine-grained expression while reducing the spatio-temporal relation and motion information density. Thus, large amounts o…
Otter: Mitigating Background Distractions of Wide-Angle Few-Shot Action Recognition with Enhanced RWKV
Wenbo Huang, Jinghui Zhang, Zhenghao Chen +6
Wide-angle videos in few-shot action recognition (FSAR) effectively express actions within specific scenarios. However, without a global understanding of both subjects and backgrou…
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…