Filters








7,279 Hits in 5.8 sec

A Sensory-Motor Linguistic Theory for Artificial Cognitive Systems

2007 2007 IEEE 9th Workshop on Multimedia Signal Processing  
We propose a linguistic approach to model lexicon of human actions, previously learned and stored. human activity. The Human Activity Language (HAL)  ...  Kinetology, synthesis (generation) of executed action sequences from the phonology of human movement, finds basic primitives for t p human motion (segmentation) and associates them with A sens symbols  ...  In methodology and introduce a parallel learning algorithm kinetology, our goal is to identify the motor primitives to induce a grammar system representing a single action.  ... 
doi:10.1109/mmsp.2007.4412885 fatcat:w4aut4wi5vcb5jepbdh5urmyae

Inferring Definite-Clause Grammars to Express Multivariate Time Series [chapter]

Gabriela Guimarães, Luís Moniz Pereira
2005 Lecture Notes in Computer Science  
This paper proposes the use of definitive-clause grammars for the induction of temporal expressions, thereby providing a more powerful framework than context-free grammars.  ...  The approach uses an adaptation of temporal ontological primitives often used in AI-systems.  ...  If no temporal relations have to be considered, for instance for the generation of a rule-based description of the primitive patterns, then Machine Learning algorithms can be used straightforwardly.  ... 
doi:10.1007/11504894_46 fatcat:afo3l2i4bvahhlxoq5eipstvg4

The syntax of human actions and interactions

Gutemberg Guerra-Filho, Yiannis Aloimonos
2012 Journal of Neurolinguistics  
Kinetology, the phonology of human movement, involves the learning of motor primitives through segmentation and symbolization.  ...  Among these aspects, we find the discovery of motor primitives used to build complex motion; the representation of complex actions in terms of these primitives; the generalization of movement concerning  ...  Kinetology, the phonology of human movement, involves the learning of motor primitives through segmentation and symbolization.  ... 
doi:10.1016/j.jneuroling.2009.12.006 fatcat:i4foiofnszho5cvw4hb6xu6aje

THE MORPHOLOGY OF HUMAN ACTIONS: FINDING ESSENTIAL ACTUATORS, MOTION PATTERNS, AND THEIR COORDINATION

GUTEMBERG GUERRA-FILHO
2009 International Journal of Humanoid Robotics  
In this paper, we present the steps required for the construction of a praxicon, a structured lexicon of human actions, through the learning of grammar systems for human actions.  ...  Therefore, our approach was successful in both representational and learning aspects, and may serve as a tool to parse movement, learn patterns, and to generate actions.  ...  The SNPR algorithm 14 learned syntagmatic elements (sequences) and paradigmatic elements (sets) from minimal elements which are perceptual primitives (e.g. letters or phonemes).  ... 
doi:10.1142/s0219843609001814 fatcat:zx6cjygbrnfrtc67225oeejvvi

Small Human Group Detection and Event Representation Based on Cognitive Semantics

Yafeng Yin, Guang Yang, Hong Man
2013 2013 IEEE Seventh International Conference on Semantic Computing  
We proposed a novel video event representation based on cognitive semantics for small human group detection and event recognition in this paper.  ...  The induced grammar rules will then be used to parse test videos. The experimental results on the BEHAVE and Collective data set demonstrate the effectiveness of the proposed method.  ...  [6] introduced attribute grammar for event recognition and anomaly detection.  ... 
doi:10.1109/icsc.2013.20 dblp:conf/semco/YinYM13 fatcat:mwzapjac4fdpjel6gg5rgnp5fq

Accurate Dynamic Sketching of Faces from Video

Zijian Xu, Jiebo Luo
2007 2007 IEEE Conference on Computer Vision and Pattern Recognition  
., for face recognition or new capabilities of manipulating faces). We have previously developed a framework for generating face sketches from still images.  ...  We adopt the same hierarchical compositional graph model originally developed for still images for face representation, where each graph node corresponds to a multimodal model of a certain facial feature  ...  Acknowledgments We would like to thanks Professor Song-Chun Zhu of UCLA for valuable discussions and the Lotus Hill Research Institute (China) for providing the annotated face database. References  ... 
doi:10.1109/cvpr.2007.383488 dblp:conf/cvpr/XuL07 fatcat:zugkjkajunaonf7dgcimr54g5a

End-user programming of a social robot by dialog

Javi F. Gorostiza, Miguel A. Salichs
2011 Robotics and Autonomous Systems  
The built sequence is internally implemented as a Sequence Function Chart (SFC), which allows parallel execution, modularity and re-use.  ...  One of the main challenges faced by social robots is how to provide intuitive, natural and enjoyable usability for the end-user.  ...  for robot learning.  ... 
doi:10.1016/j.robot.2011.07.009 fatcat:tx23m6zjdnh27mlbtqilcn77zq

The minimalist grammar of action

K. Pastra, Y. Aloimonos
2011 Philosophical Transactions of the Royal Society of London. Biological Sciences  
In this grammar, action terminals combine hierarchically into temporal sequences of actions of increasing complexity; the actions are bound with the involved tools and affected objects and are governed  ...  However, structuring action has important implications on action learning and generalization, in both human cognition research and computation.  ...  Just like we can learn filters for objects, we can also learn them for body parts, legs, arms, heads, torsos and hands.  ... 
doi:10.1098/rstb.2011.0123 pmid:22106430 pmcid:PMC3223786 fatcat:wiuyoyn3jjeibathm6qieeekwi

Recovering the Basic Structure of Human Activities from a Video-Based Symbol String

Kris Kitani, Yoichi Sato, Akihiro Sugimoto
2007 2007 IEEE Workshop on Motion and Video Computing (WMVC'07)  
In this paper, we present a framework for identifying noise and recovering the basic activity grammar from a noisy symbol string produced by video.  ...  However, most of the research in this area has yet to address the issue of learning the activity grammars from a noisy input source, namely, video.  ...  structure (a discrete temporal sequence of primitive actions).  ... 
doi:10.1109/wmvc.2007.34 fatcat:vkalntqy5bezjbkqwo7kau7ehu

RECOVERING THE BASIC STRUCTURE OF HUMAN ACTIVITIES FROM NOISY VIDEO-BASED SYMBOL STRINGS

KRIS M. KITANI, YOICHI SATO, AKIHIRO SUGIMOTO
2008 International journal of pattern recognition and artificial intelligence  
In this paper, we present a framework for identifying noise and recovering the basic activity grammar from a noisy symbol string produced by video.  ...  However, most of the research in this area has yet to address the issue of learning the activity grammars from a noisy input source, namely, video.  ...  structure (a discrete temporal sequence of primitive actions).  ... 
doi:10.1142/s0218001408006776 fatcat:gvebk3qicfgajolyxhaxjujd6q

Human Activity Language: Grounding Concepts with a Linguistic Framework [chapter]

Gutemberg Guerra-Filho, Yiannis Aloimonos
2006 Lecture Notes in Computer Science  
In syntax, we suggest four lexical categories for our Human Activity Language (noun, verb, adjective, and adverb). These categories are combined into sentences through syntax for human movement.  ...  In morphology, we extend sequential language learning to incorporate associative learning with our parallel learning approach.  ...  Grammar forest tree for the hip joint during walk forward. Fig. 9 . 9 Fig. 9. Parallel grammar system learning.  ... 
doi:10.1007/11930334_7 fatcat:e3auzlxyhnbsbmcyymnwozi7cy

Learning Relational Grammars from Sequences of Actions [chapter]

Blanca Vargas-Govea, Eduardo F. Morales
2009 Lecture Notes in Computer Science  
This paper introduces FOSeq, an algorithm that learns grammars from sequences of actions.  ...  From m sequences of the same task, FOSeq generates m grammars and performs a generalization process over the best grammar to cover most of the sequences.  ...  The authors thank the reviewers for their useful comments. This research was sponsored by CONACYT under grant 203873 .  ... 
doi:10.1007/978-3-642-10268-4_105 fatcat:u6atedy4sfh3lclreggpqpnygu

A method for automated temporal knowledge acquisition applied to sleep-related breathing disorders

G. Guimarães, J.-H. Peter, T. Penzel, A. Ultsch
2001 Artificial Intelligence in Medicine  
First, Artificial Neural Networks with unsupervised learning are used for the detection of elementary patterns in selected time series.  ...  At this level, a rule-based description of the detected structures is generated using a machine learning algorithm.  ...  attribute.  ... 
doi:10.1016/s0933-3657(01)00089-6 pmid:11704438 fatcat:cgkqqioy6nbkfmf3sjg45xzniu

Extracting interpretable muscle activation patterns with time series knowledge mining

Fabian Mörchen, Alfred Ultsch, Olaf Hoos
2005 Journal of Knowledge-based & Intelligent Engineering Systems  
The coordination process can be studied by observing complex, often cyclic movements, which are dynamically repeated in an almost identical manner.  ...  The understanding of complex muscle coordination is an important goal in human movement science. There are numerous applications in medicine, sports, and robotics.  ...  target attribute.  ... 
doi:10.3233/kes-2005-9304 fatcat:v6w7zrlzczhf3gqr6i464nhisi

Learning morphological phenomena of Modern Greek an exploratory approach

Y. Kotsanis, A. Kokkinos Dimitrios, A.G. Manousopoulou, G. Papakonstantinou
1996 Research in Learning Technology  
The computational implementation of the model can be used for creating environments for learning through design and learning by teaching.  ...  mechanism for pattern matching.  ...  Doukas for their contribution and support in the above study.  ... 
doi:10.1080/0968776960040305 fatcat:bsqahu3iibhfrapzqrl75c3una
« Previous Showing results 1 — 15 out of 7,279 results