Tag: human activity recognition

A deep neural decision forest model fuses convolutional feature extraction with differentiable decision trees to reach 98.5 percent motion recognition ...

A new study shows that a frozen CLIP vision-language model with lightweight adapters can improve human activity recognition in low-light ...

A new mini-review maps what happens when multimodal sensing, federated privacy and continual adaptation must work simultaneously in human activity ...

A flexible triboelectric-gated transistor developed at Dongguk University operated without a battery and reproduced memory and learning behavior used to ...

A new graph neural network framework called GlucoSense combines smartphone activity recognition with glucose forecasting to identify early type 2 ...

Researchers at Durham University have developed a dual-stream neural network that applies parallel attention to sensor modalities and time steps, ...

Researchers in India have developed CAT-Net, a hybrid deep learning model combining convolutional networks, coordinate attention, and Transformer encoders to ...

Researchers at the University of the Punjab have introduced HumCareADL, a demographically diverse multimodal wearable dataset, and HyMCL-Net, a hybrid ...

Researchers have introduced a Riemannian manifold-based loss function that pushes multimodal Transformer models to state-of-the-art accuracy in human activity recognition ...

Researchers at Aston University have created SEdgeNet, a graph neural network that recognises human activities from sparse millimetre-wave radar point ...