Activity recognition
https://arxiv.org/abs/1805.07648
On Attention Models for Human Activity Recognition
Most approaches that model time-series data in human activity recognition based on body-worn sensing (HAR) use a fixed size temporal context to represent different activities. This might, however, not be apt for sets of activities with individ- ually varyi
arxiv.org
https://perso.liris.cnrs.fr/christian.wolf/papers/pres-cvpr2018w-oral.pdf
https://perso.liris.cnrs.fr/christian.wolf/
Christian Wolf - LIRIS UMR 5205 - INSA de Lyon
Christian WOLF is associate professor (Maître de Conférences, HDR) at INSA de Lyon and LIRIS, a CNRS laboratory, since sept. 2005. He is interested in machine learning and computer vision, especially the visual analysis of complex scenes in motion. His w
perso.liris.cnrs.fr
https://arxiv.org/abs/1802.07898
Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points
We propose a method for human activity recognition from RGB data that does not rely on any pose information during test time and does not explicitly calculate pose information internally. Instead, a visual attention module learns to predict glimpse sequenc
arxiv.org