Filters








30,769 Hits in 9.7 sec

Accumulative Computation Method for Motion Features Extraction in Active Selective Visual Attention [chapter]

Antonio Fernández-Caballero, María T. López, Miguel A. Fernández, José Mira, Ana E. Delgado, José M. López-Valles
2005 Lecture Notes in Computer Science  
The aim of this paper is to highlight the importance of the accumulative computation method for motion features extraction in the active selective visual attention model proposed.  ...  A new method for active visual attention is briefly introduced in this paper.  ...  Acknowledgements This work is supported in part by the Spanish CICYT TIN2004-07661-C01-01 and TIN2004-07661-C02-02 grants.  ... 
doi:10.1007/978-3-540-30572-9_16 fatcat:vprodlxc6jctxlphq4s5mhza2u

Neurally Inspired Mechanisms for the Dynamic Visual Attention Map Generation Task [chapter]

Maria T. López, Miguel A. Fernández, Antonio Fernández-Caballero, Ana E. Delgado
2003 Lecture Notes in Computer Science  
A model for dynamic visual attention is briefly introduced in this paper.  ...  This paper mainly focuses on those subtasks of the model inspired in neuronal mechanisms, such as accumulative computation and lateral interaction.  ...  Motion Features Extraction Motion Interest Map Shape Features Extraction 3 Accumulative computation and lateral interaction subtasks 3.1 Subtask "Working Memory Generation" The process of obtaining  ... 
doi:10.1007/3-540-44868-3_88 fatcat:h2s6zwccxzeobnpv3od3sp2t3e

Motion features to enhance scene segmentation in active visual attention

María T. López, Antonio Fernández-Caballero, Miguel A. Fernández, José Mira, Ana E. Delgado
2006 Pattern Recognition Letters  
A new computational model for active visual attention is introduced in this paper.  ...  scene segmentation outputs in this dynamic visual attention method.  ...  The authors are thankful to the anonymous reviewers for their very helpful comments.  ... 
doi:10.1016/j.patrec.2005.09.010 fatcat:bovocarcjbflxlcesokssqewgi

Dynamic stereoscopic selective visual attention (DSSVA): Integrating motion and shape with depth in video segmentation

A FERNANDEZCABALLERO, M LOPEZ, S SAIZVALVERDE
2008 Expert systems with applications  
Depth inclusion as an important parameter for dynamic selective visual attention is presented in this article.  ...  The three models are based on the accumulative computation problemsolving method.  ...  Acknowledgements This work is supported in part by the Spanish CICYT TIN2004-07661-C02-02 grant and the Junta de Comunidades de Castilla-La Mancha PBI06-0099 grant.  ... 
doi:10.1016/j.eswa.2007.01.007 fatcat:jqmwyimuxbh7fgmas4mohhimkq

Dynamic visual attention model in image sequences

María T. López, Miguel A. Fernández, Antonio Fernández-Caballero, José Mira, Ana E. Delgado
2007 Image and Vision Computing  
A new computational architecture of dynamic visual attention is introduced in this paper.  ...  Thus, the three tasks involved in the attention model are introduced. The Feature-Extraction task obtains those features (color, motion and shape features) necessary to perform object segmentation.  ...  Acknowledgements This work is supported in part by the Spanish CICYT TIN2004-07661-C02-01 and TIN2004-07661-C02-  ... 
doi:10.1016/j.imavis.2006.05.004 fatcat:3w7k32n4szfezj5m56bflq633i

Algorithmic lateral inhibition method in dynamic and selective visual attention task: Application to moving objects detection and labelling

María T. López, Antonio Fernández-Caballero, José Mira, Ana E. Delgado, Miguel A. Fernández
2006 Expert systems with applications  
In this paper, the algorithmic lateral inhibition (ALI) method is now applied in the generic dynamic and selective visual attention (DSVA) task with the objective of moving objects detection, labelling  ...  The four basic subtasks, namely feature extraction, feature integration, attention building and attention reinforcement in our proposal of DSVA are described in detail by inferential CommonKADS schemes  ...  Acknowledgements This work is supported in part by the Spanish CICYT TIN2004-07661-C02-01 and TIN2004-07661-C02-02 grants.  ... 
doi:10.1016/j.eswa.2005.09.062 fatcat:sozlsnplknarhj6j5hj47vfe2m

Video Structuring: From Pixels To Visual Entities

Ruxandra Tapu, Titus Zaharia
2012 Zenodo  
Publication in the conference proceedings of EUSIPCO, Bucharest, Romania, 2012  ...  The human brain and visual system actively seek for regions of interest by paying more attention to some specific parts of the image/ video.  ...  Stationary attention model A powerful method of computing bottom-up visual cues is proposed in [13] . First, the input image is segmented into regions based on a graph partition strategy [19] .  ... 
doi:10.5281/zenodo.51978 fatcat:5tsrcrfs2zggjch4bxzcjzvfki

Manipulation-skill Assessment from Videos with Spatial Attention Network [article]

Zhenqiang Li, Yifei Huang, Minjie Cai, Yoichi Sato
2019 arXiv   pre-print
In particular, we propose a novel RNN-based spatial attention model that considers accumulated attention state from previous frames as well as high-level knowledge about the progress of an undergoing task  ...  Our motivation here is to estimate attention in videos that helps to focus on critically important video regions for better skill assessment.  ...  elements: 1) instantaneous visual information in each frame (deep appearance-motion features); 2) highlevel task-related knowledge; 3) accumulate information of attention.  ... 
arXiv:1901.02579v2 fatcat:l2zebsl475c2pg7xnwz5rli6su

Revisiting Algorithmic Lateral Inhibition and Accumulative Computation [chapter]

Antonio Fernández-Caballero, María T. López, Miguel A. Fernández, José M. López-Valles
2009 Lecture Notes in Computer Science  
This paper is dedicated to the computational formulations of both methods, which have led to quite efficient solutions of problems related to motion-based computer vision.  ...  called "algorithmic lateral inhibition", a generalization of lateral inhibition anatomical circuits, and "accumulative computation", a working memory related to the temporal evolution of the membrane  ...  From the good results obtained by means of these methods in computer-visionbased motion analysis, the following step was the challenge of facing selective visual attention (dynamic) by means of a research  ... 
doi:10.1007/978-3-642-02264-7_7 fatcat:3vixstt3afbidpuctdollm4nfq

Self-Supervised Learning of Audio-Visual Objects from Video [article]

Triantafyllos Afouras, Andrew Owens, Joon Son Chung, Andrew Zisserman
2020 arXiv   pre-print
and tracking speakers, (c) correcting misaligned audio-visual data, and (d) active speaker detection.  ...  We demonstrate the effectiveness of the audio-visual object embeddings that our model learns by using them for four downstream speech-oriented tasks: (a) multi-speaker sound source separation, (b) localizing  ...  Thandavan for infrastructure support. This work is funded by the UK EPSRC CDT in AIMS, DARPA Medifor, and a Google-DeepMind Graduate Scholarship. Bibliography  ... 
arXiv:2008.04237v1 fatcat:6qs4sxx3qfgzdcr77zlw7zzyvi

A conceptual frame with two neural mechanisms to model selective visual attention processes

José Mira, Ana E. Delgado, María T. López, Antonio Fernández-Caballero, Miguel A. Fernández
2008 Neurocomputing  
In this work we explore a way of saving this gap for the case of the attentional processes, consisting in (1) proposing in first place a conceptual model of the attention double bottom-up/top-down organization  ...  computation) formulated at symbolic level, and, (5) assessing the validity of the proposal by accommodating the works of the research team on diverse aspects of attention associated to visual surveillance  ...  This work is also supported in part by Junta de Comunidades de Castilla-La Mancha PBI06-099 Grant.  ... 
doi:10.1016/j.neucom.2007.10.005 fatcat:lk7dck6fgrd5vlobaoee75qo2q

Speech/non-speech detection in meetings from automatically extracted low resolution visual features

Hayley Hung, Sileye O Ba
2010 2010 IEEE International Conference on Acoustics, Speech and Signal Processing  
In this paper we address the problem of estimating who is speaking from automatically extracted low resolution visual cues from group meetings.  ...  Due to the high probability of losing the audio stream during video conferences, this work proposes methods for estimating speech using just low resolution visual cues.  ...  FEATURE EXTRACTION 3.1 Estimating Motion We estimate body motion in the close-view video streams by extracting visual activity features directly from the compressed domain.  ... 
doi:10.1109/icassp.2010.5494913 fatcat:wi6xzjgykfb37miey5r7jz67qa

Multiple Image Objects Detection, Tracking, and Classification using Human Articulated Visual Perception Capability [chapter]

HeungKyu Lee
2008 Brain, Vision and AI  
For doing this, skeletonization of the motion region is done, and then motion analysis is done to compute motion feature variation using selected feature points (R. Cutler, et al. 2000 , H.  ...  To extract multivariate feature vectors, shape and motion information are computed using Fourier descriptor, gradients, and motion feature variation (A. J. Lipton, et al. 1998 , Y.  ...  Furthermore, it works as a valuable resource for researchers interested in this field.  ... 
doi:10.5772/6040 fatcat:xmuljcpyzbbzvomxqsqfoc2jju

Driver hand activity analysis in naturalistic driving studies: challenges, algorithms, and experimental studies

Eshed Ohn-Bar, Sujitha Martin, Mohan Manubhai Trivedi
2013 Journal of Electronic Imaging (JEI)  
The static-cue-based method extracts features in each frame in order to learn a hand presence model for each of the three regions.  ...  The motioncue-based hand detection uses temporally accumulated edges in order to maintain the most reliable and relevant motion information.  ...  We also thank our UCSD LISA colleagues, in particular Dr. Cuong Tran and Mr. Minh Van Ly, and are also thankful to Mr.  ... 
doi:10.1117/1.jei.22.4.041119 fatcat:scjepctzurcedklore3awv2tiu

A Computing Model of Selective Attention for Service Robot Based on Spatial Data Fusion

Huanzhao Chen, Guohui Tian
2018 Journal of Robotics  
Both static features and dynamic features are composed in attention selection computing process. Information from sensor networks is transformed and incorporated into the model.  ...  We proposed a computing model of selective attention which is biologically inspired by visual attention mechanism, which aims at predicting focus of attention (FOA) in a domestic environment.  ...  A Saliency Computing Model of Selective Attention The general procedure of saliency computing model for selective attention is illustrated in Figure 2 .  ... 
doi:10.1155/2018/5368624 fatcat:6hlv3mrsizfydab7kupevw5cby
« Previous Showing results 1 — 15 out of 30,769 results