First and second order dynamics in a hierarchical SOM system for action recognition
Human recognition of the actions of other humans is very efficient and is based on patterns
of movements. Our theoretical starting point is that the dynamics of the joint movements is …
of movements. Our theoretical starting point is that the dynamics of the joint movements is …
[HTML][HTML] Hierarchical growing grid networks for skeleton based action recognition
Z Gharaee - Cognitive Systems Research, 2020 - Elsevier
In this paper, a novel cognitive architecture for action recognition is developed by applying
layers of growing grid neural networks. Using these layers makes the system capable of …
layers of growing grid neural networks. Using these layers makes the system capable of …
Online recognition of actions involving objects
We present an online system for real time recognition of actions involving objects working in
online mode. The system merges two streams of information processing running in parallel …
online mode. The system merges two streams of information processing running in parallel …
Online recognition of unsegmented actions with hierarchical SOM architecture
Z Gharaee - Cognitive Processing, 2021 - Springer
Automatic recognition of an online series of unsegmented actions requires a method for
segmentation that determines when an action starts and when it ends. In this paper, a novel …
segmentation that determines when an action starts and when it ends. In this paper, a novel …
[PDF][PDF] Hierarchical Self-organizing Maps System for Action Classification.
We present a novel action recognition system that is able to learn how to recognize and
classify actions. Our system employs a three-layered neural network hierarchy consisting of …
classify actions. Our system employs a three-layered neural network hierarchy consisting of …
A Bayesian approach to reinforcement learning of vision-based vehicular control
In this paper, we present a state-of-the-art reinforcement learning method for autonomous
driving. Our approach employs temporal difference learning in a Bayesian framework to …
driving. Our approach employs temporal difference learning in a Bayesian framework to …
Action in mind: a neural network approach to action recognition and segmentation
Z Gharaee - arxiv preprint arxiv:2104.14870, 2021 - arxiv.org
Recognizing and categorizing human actions is an important task with applications in
various fields such as human-robot interaction, video analysis, surveillance, video retrieval …
various fields such as human-robot interaction, video analysis, surveillance, video retrieval …
[PDF][PDF] ral N etwork A
Z GHARAEE - lucs.lu.se
Recognizing and categorizing human actions is an important task with applications in
various fields such as human-robot interaction, video analysis, surveillance, video retrieval …
various fields such as human-robot interaction, video analysis, surveillance, video retrieval …