Proceedings Article10.1109/AVSS.2012.85
Action Recognition from Experience
Peter Henry Tu,Thomas B. Sebastian,Dashan Gao +2 more
- 18 Sep 2012
- pp 124-129
3
TL;DR: A reinforcement learning model, which allows for an agent to interact with a simulated 3D learning environment under the initial guidance of an all knowing oracle, is proposed and it is hypothesized that the ability to recognize an action may in fact be a byproduct of learning how to perform an action.
read more
Abstract: A reinforcement learning model, which allows for an agent to interact with a simulated 3D learning environment under the initial guidance of an all knowing oracle is proposed. Methods are presented that allow the agent to learn how to perform a set of task oriented actions. It is then hypothesized that the ability to recognize an action may in fact be a byproduct of learning how to perform an action. Evidence supporting this conjecture is presented using both simulated and real world imagery.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Systems and methods for action recognition
Peter Henry Tu,Ting Yu,Dashan Gao,Thomas B. Sebastian,Yi Yao +4 more
- 28 Dec 2011
Abstract: Systems provided herein include a learning environment and an agent. The learning environment includes an avatar and an object. A state signal corresponding to a state of the learning environment includes a location and orientation of the avatar and the object. The agent is adapted to receive the state signal, to issue an action capable of generating at least one change in the state of the learning environment, to produce a set of observations relevant to a task, to hypothesize a set of action models configured to explain the observations, and to vet the set of action models to identify a learned model for the task.
3
Towards an Automated Language Acquisition System for Grounded Agency
James Kubricht,Sharon G. Small,Ting Liu,Peter Henry Tu +3 more
- 02 Sep 2021
TL;DR: In this article, the authors take the view that prior to acquiring natural language, an agent has experienced the world in a largely private manner, from which it has learned that objects and object categories exist, they persist over time and possess attributes.
2
Patent
Action-based models to identify learned tasks
Peter Henry Tu,Ting Yu,Dashan Gao,Thomas B. Sebastian,Yi Yao +4 more
- 28 Dec 2011
TL;DR: In this paper, an agent is adapted to receive the state signal, issue an action capable of generating at least one change in the state of the learning environment, to produce a set of observations relevant to a task, and hypothesize the set of action models configured to explain the observations, and to vet the learned model for the task.
1
References
Introduction to algorithms: 4. Turtle graphics
TL;DR: In this article, a language similar to logo is used to draw geometric pictures using this language and programs are developed to draw geometrical pictures using it, which is similar to the one we use in this paper.
15.4K
Reinforcement learning: a survey
TL;DR: Central issues of reinforcement learning are discussed, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state.
The mirror-neuron system.
TL;DR: A neurophysiological mechanism appears to play a fundamental role in both action understanding and imitation, and those properties specific to the human mirror-neuron system that might explain the human capacity to learn by imitation are stressed.
7.8K
•Posted Content
Reinforcement Learning: A Survey
TL;DR: A survey of reinforcement learning from a computer science perspective can be found in this article, where the authors discuss the central issues of RL, including trading off exploration and exploitation, establishing the foundations of RL via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state.
5.9K
Learning realistic human actions from movies
Ivan Laptev,Marcin Marszalek,Cordelia Schmid,B. Rozenfeld +3 more
- 23 Jun 2008
TL;DR: A new method for video classification that builds upon and extends several recent ideas including local space-time features,space-time pyramids and multi-channel non-linear SVMs is presented and shown to improve state-of-the-art results on the standard KTH action dataset.