8 papers
LiquidTAD: Efficient Temporal Action Detection via Parallel Liquid-Inspired Temporal Relaxation
Zepeng Sun, Naichuan Zheng, Hailun Xia +3
Temporal Action Detection (TAD) requires precise localization of action boundaries within long, untrimmed video sequences. While current high-performing methods achieve strong accu…
Towards Green Wearable Computing: A Physics-Aware Spiking Neural Network for Energy-Efficient IMU-based Human Activity Recognition
Naichuan Zheng, Hailun Xia, Zepeng Sun +2
Wearable IMU-based Human Activity Recognition (HAR) relies heavily on Deep Neural Networks (DNNs), which are burdened by immense computational and buffering demands. Their power-hu…
S3T-Former: A Purely Spike-Driven State-Space Topology Transformer for Skeleton Action Recognition
Naichuan Zheng, Hailun Xia, Zepeng Sun +2
Skeleton-based action recognition is crucial for multimedia applications but heavily relies on power-hungry Artificial Neural Networks (ANNs), limiting their deployment on resource…
Patch as Node: Human-Centric Graph Representation Learning for Multimodal Action Recognition
Zeyu Liang, Hailun Xia, Naichuan Zheng
While human action recognition has witnessed notable achievements, multimodal methods fusing RGB and skeleton modalities still suffer from their inherent heterogeneity and fail to…
SNN-Driven Multimodal Human Action Recognition via Sparse Spatial-Temporal Data Fusion
Naichuan Zheng, Hailun Xia, Zeyu Liang +1
Multimodal human action recognition based on RGB and skeleton data fusion, while effective, is constrained by significant limitations such as high computational complexity, excessi…
MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition
Naichuan Zheng, Hailun Xia, Zeyu Liang +1
In recent years, multimodal Graph Convolutional Networks (GCNs) have achieved remarkable performance in skeleton-based action recognition. The reliance on high-energy-consuming con…