Filters








3,109 Hits in 9.7 sec

Computational Models of Human Visual Attention and Their Implementations: A Survey

Akisato KIMURA, Ryo YONETANI, Takatsugu HIRAYAMA
2013 IEICE transactions on information and systems  
top-down  ...  This survey finally discusses possible future directions for research into human visual attention and saliency computation. key words: human visual attention, computational model, saliency, bottom-up,  ...  Kazuhiko Kojima of Sanyo Electric Co.Ltd, and anonymous associate editors and reviewers for their valuable discussions and useful comments, which helped to improve of this work.  ... 
doi:10.1587/transinf.e96.d.562 fatcat:vkz3cdismbhadgzhickap3tzlm

A Context-Dependent Attention System for a Social Robot

Cynthia Breazeal, Brian Scassellati
1999 International Joint Conference on Artificial Intelligence  
The attention system integrates perceptions (motion detection, color saliency, and face popouts) with habituation effects and influences from the robot's motivational and behavioral state to create a context-dependent  ...  This activation map is used to direct eye movements and to satiate the drives of the motivational system.  ...  Future Work In this paper we have demonstrated an attentional system that combines bottom-up perceptions and habituation effects with top-down behavioral and motivational influences.  ... 
dblp:conf/ijcai/BreazealS99 fatcat:ahjfcse4ezcv3g4irxu6zvydbu

Models of Bottom-up Attention and Saliency [chapter]

Laurent Itti
2005 Neurobiology of Attention  
frameworks that combine bottom-up and top-down attention control signals.  ...  It has become clear that attention guides where to look next based on both bottom-up (image-based) and top-down (task-dependent) cues (James, 1890/1981).  ...  may attract attention based on combined bottom-up salience and top-down expectations.  ... 
doi:10.1016/b978-012375731-9/50098-7 fatcat:zbfgjq2sbbbsffpjf4mchireli

Computational visual attention systems and their cognitive foundations

Simone Frintrop, Erich Rome, Henrik I. Christensen
2010 ACM Transactions on Applied Perception  
It provides an extensive survey of the grounding psychological and biological research on visual attention as well as the current state of the art of computational systems.  ...  Based on concepts of the human visual system, computational visual attention systems aim to detect regions of interest in images.  ...  Note however that in a computational system, it is also possible to deal with both maps in parallel and use the bottom-up and the top-down information for different purposes.  ... 
doi:10.1145/1658349.1658355 fatcat:tv6pjh7m5zfhjb3pewtci3gtiy

A visual attention focusing system using an active stereoscopic vision sensor

Yann Ducrocq, Shahram Bahrami, Luc Duvieubourg, Francois Cabestaing
2010 2010 2nd International Conference on Image Processing Theory, Tools and Applications  
Several studies have shown that human perception and more specially the visual perception can be decomposed into a bottom-up process and a top-down process.  ...  In this work, in order to mimic the human behavior or at least improve vision systems, we use a new active stereovision setup and a model of the human visual perception based on the two previous approaches  ...  The top-down part influences the bottom-up part and modifies focus parameters got from the saliency map.  ... 
doi:10.1109/ipta.2010.5586790 dblp:conf/ipta/DucrocqBDC10 fatcat:cog64vkiuzajfezi53h5pl4ila

Fusion of Saliency Maps for Visual Attention Selection in Dynamic Scenes

Jiawei Xu, Shigang Yue
2013 International Journal of Advanced Research in Artificial Intelligence (IJARAI)  
We added three saliencies maps up together to reflect dominant motion features into the attention model, i.e., the fused saliency map at each frame is adjusted by the top-down, static and motion saliency  ...  The computational saliency map is superimposed by a set of saliency maps via different predefined approaches.  ...  This paper has addressed the bottom-up cues into the saliency model, however, in human visual system, top-down attention and the combination of the bottom-up and top-down cues play significant role in  ... 
doi:10.14569/ijarai.2013.020408 fatcat:vvoxbf4wevbyha454sccjzmkf4

What Guides Visual Overt Attention under Natural Conditions? Past and Future Research

Kai Kaspar
2013 ISRN Neuroscience  
In addition to that, the current scope on top-down factors in visual attention is enlarged by discussing the impact of emotions and motivational tendencies on viewing behavior.  ...  Against this background, strengths and limitations of the bottom-up approach are discussed and future directions in this field are outlined.  ...  It is a challenging task for future research to incorporate bottom-up factors and emotion as a strong top-down factor.  ... 
doi:10.1155/2013/868491 pmid:24959568 pmcid:PMC4045567 fatcat:epkhaeitwrdv3izsd5bbuykfgy

Assessment of computational visual attention models on medical images

Varun Jampani, Ujjwal, Jayanthi Sivaswamy, Vivek Vaidya
2012 Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing - ICVGIP '12  
These approximately correspond to conjunctive and disjunctive targets in a visual search task. Saliency maps were computed using three popular models namely Itti-Koch [7], GBVS [3] and SR [4] .  ...  Based on the results of the above study, we propose extensions for the two best performing models. The first extension makes use of top down knowledge such as lung segmentation.  ...  IK and GBVS are biologically motivated saliency models, which closely follow FIT.  ... 
doi:10.1145/2425333.2425413 dblp:conf/icvgip/JampaniUSV12 fatcat:csx4tjxflfhbjjcteoy4d6q75y

Vision, Attention Control, and Goals Creation System [chapter]

Konstantinos Rapantzikos, Yannis Avrithis, Stefanos Kolias
2010 Perception-Action Cycle  
It seems that there is an informal agreement on the four important functions of the attention process: (a) the bottom-up process, which is responsible for the saliency of the input stimuli; (b) the top-down  ...  The Holy Grail of this study is the exact modeling of the interaction between the visual sensory and the process of perception.  ...  It is based on both the resonance of top-down and bottom-up processes (Cutsuridis 2009 ).  ... 
doi:10.1007/978-1-4419-1452-1_11 fatcat:cyydaayk3zauncho44knonuqfm

Learning to Model Task-Oriented Attention

Xiaochun Zou, Xinbo Zhao, Jian Wang, Yongjia Yang
2016 Computational Intelligence and Neuroscience  
Using this database as training and testing examples, we learn a model of saliency based on bottom-up image features and target position feature.  ...  Models of saliency can be used to predict fixation locations, but a large body of previous saliency models focused on free-viewing task.  ...  Acknowledgments The work is supported by NSF of China (nos. 61117115 and 61201319), the Fundamental Research Funds for the Central Universities, and NWPU "Soaring Star" and "New Talent and Direction" Program  ... 
doi:10.1155/2016/2381451 pmid:27247561 pmcid:PMC4876208 fatcat:d7s33wkmcvgwxfevul57c4poa4

Computational Visual Attention [chapter]

Simone Frintrop
2011 Computer Analysis of Human Behavior  
Machines face similar challenges as humans: they have to deal with a large amount of input data and have to select the most promising parts.  ...  In this chapter, we explain the underlying biological and psychophysical grounding of visual attention, show how these mechanisms can be implemented computationally, and discuss why and under what conditions  ...  Bottom-up and Top-down Cues Compete for Attention In human perception, bottom-up and top-down cues compete for attention all of the time.  ... 
doi:10.1007/978-0-85729-994-9_4 fatcat:dgo37g2lvvcp3dumnbfiaghf2u

Learning to predict where humans look

Tilke Judd, Krista Ehinger, Fredo Durand, Antonio Torralba
2009 2009 IEEE 12th International Conference on Computer Vision  
Most saliency approaches are based on bottom-up computation that does not consider top-down image semantics and often does not match actual eye movements.  ...  Where eye tracking devices are not a viable option, models of saliency can be used to predict fixation locations.  ...  Tilke Judd was supported by a Xerox graduate fellowship. We thank Aude Oliva for the use of her eye tracker and Barbara Hidalgo-Sotelo for help with eye tracking.  ... 
doi:10.1109/iccv.2009.5459462 dblp:conf/iccv/JuddEDT09 fatcat:nby3n3odkzfrbchzlytcaqi4x4

Fundamentals of Agent Perception and Attention Modelling [chapter]

Christopher Peters, Ginvera Castellano, Matthias Rehm, Elisabeth André, Amaryllis Raouzaiou, Kostas Rapantzikos, Kostas Karpouzis, Gaultiero Volpe, Antonio Camurri, Asimina Vasalou
2010 Cognitive Technologies  
Perception and attention mechanisms are of great importance for entities situated within complex dynamic environments.  ...  Here, we describe the rationale behind endowing artificial entities, or virtual agents, with real-time perception and attention systems.  ...  Object-based approaches may be used in the implementation of both bottom-up and top-down systems.  ... 
doi:10.1007/978-3-642-15184-2_16 fatcat:aslga5qcdjc5ragjuhyljqcxdm

7 Attentive Classification [chapter]

Simone Frintrop
2006 Lecture Notes in Computer Science  
Second, since the attention system is able to make use of top-down target-information, the combination of the systems yields a significant reduction of false detections for objects which are usually difficult  ...  First, regions of interest are detected by a biologically motivated attention system. Second, these regions are analyzed by a fast classifier based on the Adaboost learning technique.  ...  These are combined to a Top-down Saliency Map S td which competes for global saliency with the Bottom-up Map.  ... 
doi:10.1007/11682110_7 fatcat:332gnrkidvafncrqdratocpx2m

Top-Down and Bottom-Up Cues Based Moving Object Detection for Varied Background Video Sequences

Chirag I. Patel, Sanjay Garg, Tanish Zaveri, Asim Banerjee
2014 Advances in Multimedia  
Many bottom-up approaches and one combination of bottom-up and top-down approaches are proposed in the present paper.  ...  Moving object detection is a crucial and critical task for any surveillance system.  ...  combination of bottom-up and top-down cues based approach.  ... 
doi:10.1155/2014/879070 fatcat:zlqn25ebrjhylceetar4pukw6i
« Previous Showing results 1 — 15 out of 3,109 results