Filters








3,010 Hits in 4.8 sec

Computational Scene Analysis [chapter]

DeLiang Wang
2007 Studies in Computational Intelligence  
Recent results on visual and auditory scene analysis are described in the oscillatory correlation framework, with emphasis on real-world scenes.  ...  The LEGION network lays a computational foundation for oscillatory correlation, which is a special form of temporal correlation.  ...  This research was supported in part by an AFOSR grant (FA9550-04-1-0117) and an AFRL grant (FA8750-04-1-0093).  ... 
doi:10.1007/978-3-540-71984-7_8 fatcat:x2rojzgtrrelphdiqs4rkgfium

Neural mechanisms of scene segmentation: recordings from the visual cortex suggest basic circuits for linking field models

R. Eckhorn
1999 IEEE Transactions on Neural Networks  
Other recently observed cortical effects that potentially support scene segmentation are shortly reviewed to stimulate further ideas for models.  ...  This was supported by the discovery of synchronized neural activities in cat and monkey visual cortex which occurred stimulus dependent either oscillatory (30-100 Hz) or nonrhythmical, internally generated  ...  of PCNN's for scene segmentation often Fig. 6 .  ... 
doi:10.1109/72.761705 pmid:18252546 fatcat:b7uahvt6ajgezd2e2srooradea

Direct physiological evidence for scene segmentation by temporal coding

A. K. Engel, P. Konig, W. Singer
1991 Proceedings of the National Academy of Sciences of the United States of America  
Theoretical studies have suggested that scene segmentation may be accomplished by a temporal coding mechanism using synchronization of neuronal responses.  ...  These results are compatible with the hypothesis that responses to individual objects in a scene are distuished by synchrony, whereas responses to different objects show no temporal correlation, thus allowing  ...  According to these proposals, perceptual coherence within a segment of a scene should be expressed by response synchronization of feature-detecting neurons.  ... 
doi:10.1073/pnas.88.20.9136 pmid:1924376 pmcid:PMC52667 fatcat:mo642vcw7bacpilmefzqvtucoi

An oscillatory correlation model of object-based attention

Marcos G. Quiles, DeLiang Wang, Liang Zhao, Roseli A. F. Romero, De-Shuang Huang
2009 2009 International Joint Conference on Neural Networks  
We present a neurocomputational model of object-based selection in the framework of oscillatory correlation.  ...  By segmenting an input scene and integrating the segments with their conspicuity obtained from a saliency map, the model selects salient objects rather than salient locations.  ...  The oscillatory correlation theory has been applied to various tasks of scene analysis (see [21] for an extensive review).  ... 
doi:10.1109/ijcnn.2009.5178597 dblp:conf/ijcnn/QuilesWZRH09 fatcat:yqskf4v3lvfn5gfl64hbhqz7w4

The Time Dimension for Scene Analysis

D. Wang
2005 IEEE Transactions on Neural Networks  
The temporal correlation theory as well as its special form -oscillatory correlation theory, is discussed as an adequate representation theory to address the binding problem.  ...  Recent advances in understanding oscillatory dynamics are reviewed, and these advances have overcome key computational obstacles for the development of the oscillatory correlation theory.  ...  This work was supported in part by an NSF grant (IIS-0081058) and an AFOSR grant (F49620-01-1-0027).  ... 
doi:10.1109/tnn.2005.852235 pmid:16342484 fatcat:36wrmgjbzvfb5ccrihz5ncrvfi

A learning algorithm for oscillatory cellular neural networks

C.Y. Ho, H. Kurokawa
1999 Neural Networks  
Furthermore, by using special grouping synapses it is demonstrated that temporal segregation of overlapping gray-level and color segments can also be achieved.  ...  The dynamics of traditional oscillatory models is simplified by using only one plastic synapse, and the overall complexity for hardware implementation is reduced.  ...  This project was supported in part by CityU strategic grant 7000749-570.  ... 
doi:10.1016/s0893-6080(99)00035-0 pmid:12662659 fatcat:zhzmkghct5dflgflbjgy5fjqze

Selecting salient objects in real scenes: An oscillatory correlation model

Marcos G. Quiles, DeLiang Wang, Liang Zhao, Roseli A.F. Romero, De-Shuang Huang
2011 Neural Networks  
We present a neurocomputational model of object-based selection in the framework of oscillatory correlation.  ...  By segmenting an input scene and integrating the segments with their conspicuity obtained from a saliency map, the model selects salient objects rather than salient locations.  ...  The oscillatory correlation theory has been applied to various tasks of scene analysis, such as texture segmentation, motion analysis, and auditory scene segregation (see [37] for an extensive review  ... 
doi:10.1016/j.neunet.2010.09.002 pmid:20884173 fatcat:ypv4dku4jjaq7h2xaqhtsyiihq

Separation of speech from interfering sounds based on oscillatory correlation

DeLiang L. Wang, G.J. Brown
1999 IEEE Transactions on Neural Networks  
In the oscillatory correlation framework, a stream is represented by a population of synchronized relaxation oscillators, each of which corresponds to an auditory feature, and different streams are represented  ...  The core of the model is a two-layer oscillator network that performs stream segregation on the basis of oscillatory correlation.  ...  Recently, Brown and Wang [10] gave an account of concurrent vowel separation based on oscillatory correlation. The oscillatory correlation theory is supported by neurobiological findings.  ... 
doi:10.1109/72.761727 pmid:18252568 fatcat:rrxycz2b65d4rfzik5fhg5zawa

Page 374 of Neural Computation Vol. 8, Issue 2 [page]

1996 Neural Computation  
Its possible application to scene analysis was discussed by von der Malsburg and Buhmann (1992).  ...  Temporal segmentation can be implemented in oscillatory networks using two very different mechanisms. One is to have each segment os- cillate with a different frequency.  ... 

Object selection based on oscillatory correlation

D.L. Wang
1999 Neural Networks  
The limit cycle trajectory is shown with a bold curve, and its direction of motion is indicated by arrowheads.  ...  As a special case, the selection network without local excitation gives rise to a new form of oscillatory WTA. ᭧ Fig. 2. Nullclines and trajectories of a single oscillator.  ...  The work described here was supported in part by an ONR grant (N00014-93-1-0335), an NSF grant (IRI-9423312), and an ONR Young Investigator Award (N00014-96-1-0676).  ... 
doi:10.1016/s0893-6080(99)00028-3 pmid:12662669 fatcat:4yzh3n37obg23bzptmwvz4vjq4

Visual Selection and Shifting Mechanisms Based on a Network of Chaotic Wilson-Cowan Oscillators

Liang Zhao, Fabricio A. Breve, Marcos G. Quiles, Roseli A.F. Romero
2007 Third International Conference on Natural Computation (ICNC 2007) Vol V  
The oscillators representing each object in a given visual scene are synchronized to produce a chaotic trajectory.  ...  The model can not only discriminate each object among others in a given visual scene, but also deliver the focus of attention to a salient object in an instant of time.  ...  Acknowledgment This work is supported by the São Paulo State Research Foundation (FAPESP) and the Brazilian National Research Council (CNPq).  ... 
doi:10.1109/icnc.2007.811 dblp:conf/icnc/0001BQR07 fatcat:qmure6wnkrfevmsogkw6lani4u

Pattern Segmentation in Associative Memory

DeLiang Wang, Joachim Buhmann, Christoph von der Malsburg
1990 Neural Computation  
Correlations are created naturally by the usual associative connections. In our simulations, temporal patterns take the form of oscillatory bursts of activity.  ...  Segmention of patterns takes place in the temporal domain, components of one pattern becoming temporally correlated with each other and anticorrelated with the components of all other patterns.  ...  Correlations are created naturally by the usual associative connections. In our simulations, temporal patterns take the form of oscillatory bursts of activity.  ... 
doi:10.1162/neco.1990.2.1.94 fatcat:rfasn3nu55e3zb332iakrsvqge

Image Segmentation Based on Oscillatory Correlation

DeLiang Wang, David Terman
1997 Neural Computation  
The network exhibits a natural capacity in segmenting images. The oscillatory dynamics leads to a computer algorithm, which is applied successfully to segmenting real graylevel images.  ...  We show that the resulting oscillator network separates an image into several major regions, plus a background consisting of all noisy regions, and illustrate network properties by computer simulation.  ...  DLW was supported in part by the ONR grant N00014-93-1-0335, the NSF grant IRI-9423312, and the ONR YIP Award N00014-96-1-0676. DT was supported in part by the NSF grant DMS-9423796.  ... 
doi:10.1162/neco.1997.9.4.805 pmid:9161023 fatcat:g2glewj2mzcfdfs26hiekhms2q

Neural Mechanisms of Visual Feature Binding Investigated with Microelectrodes and Models

Reinhard Eckhorn
1999 Visual Cognition  
Hence, object continuity would be represented by phase continuity. Besides feature binding, feature separation is necessary for scene segmentation.  ...  A third temporal coding aspect is temporal segmentation by the short activation-inhibition cycles of fast oscillations or short transient stimulus-locked responses, which may prevent perceptual "smearing  ...  Hence, object continuity would be represented by phase continuity. Besides feature binding, feature separation is necessary for scene segmentation.  ... 
doi:10.1080/135062899394975 fatcat:irap5j2adndztnojjwlqx57bpy

Motion segmentation based on motion/brightness integration and oscillatory correlation

E. Cesmeli, DeLiang Wang
2000 IEEE Transactions on Neural Networks  
The second stage performs segmentation based on local motion estimates. In the brightness pathway, the input scene is segmented into regions based on brightness distribution.  ...  Inspired by the visual system, the motion pathway has two stages. The first stage estimates local motion at locations with reliable information.  ...  We address these challenges by using an oscillatory neural network to perform motion-based segmentation by integrating motion and brightness cues.  ... 
doi:10.1109/72.857773 pmid:18249820 fatcat:uqqtdrkyunexrapii2fdzajjmu
« Previous Showing results 1 — 15 out of 3,010 results