40 Hits in 2.9 sec

A Space-Variant Visual Pathway Model for Data Efficient Deep Learning

Piotr Ozimek, Nina Hristozova, Lorinc Balog, Jan Paul Siebert
2019 Frontiers in Cellular Neuroscience  
This work has now enabled DCNNs to process input images approaching one million pixels in size, in real time, using only consumer grade graphics processor (GPU) hardware in a single pass of the DCNN.  ...  ) in the context of robot vision and egocentric perception systems.  ...  The authors would like to thank Prof. Lars Muckli for his collaboration and support for the retina work reported here.  ... 
doi:10.3389/fncel.2019.00036 pmid:30971891 pmcid:PMC6444208 fatcat:mqssy7cdwff33gx3em552brwea

Capture of fixation by rotational flow; a deterministic hypothesis regarding scaling and stochasticity in fixational eye movements

Nicholas M. Wilkinson, Giorgio Metta
2014 Frontiers in Systems Neuroscience  
Here we focus on the dynamical profile of fixational tremor, and argue that tremor may be a signal which usefully reflects the workings of oculomotor postural control.  ...  Spiral waves have a repertoire of functionally interesting dynamical properties, including persistence, which suggest that they could in theory contribute to persistent neural activity in the oculomotor  ...  We thank the reviewers for motivating significant improvements in the paper.  ... 
doi:10.3389/fnsys.2014.00029 pmid:24616670 pmcid:PMC3935396 fatcat:bg5sqbl7lzfk5je3bvvgdgfhmq

Space-variant Fourier analysis: the exponential chirp transform

G. Bonmassar, E.L. Schwartz
1997 IEEE Transactions on Pattern Analysis and Machine Intelligence  
One evident motivation for this is that the spacecomplexity of the human visual system is reduced by up to four orders of magnitude (Rojer and Schwartz, 1990) via the use of space-variant architecture  ...  (jar a given ratio of field width to maximum resolution).  ...  Acknowledgements We thank Gil Engel for interesting discussions and Bruce Fischl for assistance in the implementation.  ... 
doi:10.1109/34.625108 fatcat:ztrwl6twj5h6jmjd4pcjatchpq

A space-variant model for motion interpretation across the visual field

Manuela Chessa, Guido Maiello, Peter J. Bex, Fabio Solari
2016 Journal of Vision  
We further show that the model is able to estimate direction of heading in real-world scenes, thus validating the model's potential application to neuromimetic robotic architectures.  ...  The model describes the deep hierarchy of the first stages of the dorsal visual pathway and is space variant, since it takes into account the retino-cortical transformation of the primate visual system  ...  of the proposed feed-forward architecture is based on spatiotemporal filtering.  ... 
doi:10.1167/16.2.12 pmid:27580091 fatcat:mvmdl5eluvh6zoiqx2cxqcnik4

Foveated image coding system and method for image bandwidth reduction [article]

Wilson S. Geisler, Philip Kortum, Austin, The University Of Texas At, Austin, The University Of Texas At
One version of the system includes a simple, inexpensive, parallel pipeline architecture, which enhances the capability for conventional and foveated data compression.  ...  A foveated imaging system, which can be implemented on a general purpose computer and greatly reduces the transmission bandwidth of images has been developed.  ...  Further, these Systems have utilized an Archimedes spiral to represent the falloff function applied to the image in their descriptions of the foveation method.  ... 
doi:10.26153/tsw/4343 fatcat:5suxp2ml4nfepioyobstfi7zw4

Primate Extrastriate Cortical Area MST: A Gateway between Sensation and Cognition

Benedict Wild, Stefan Treue
2021 Journal of Neurophysiology  
This review of more than 90 studies focuses on providing clarity of the heterogeneous findings on MST in the macaque cortex and its putative homolog in the human cortex.  ...  One such area is the medial superior temporal cortex (MST), a motion-sensitive, direction-selective part of the primate visual cortex.  ...  ACKNOWLEDGMENTS We thank Amr Maamoun for helpful discussion and Bobbie Smith for helpful comments on the manuscript.  ... 
doi:10.1152/jn.00384.2020 pmid:33656951 fatcat:r6ypc5rsl5g7tghilns4nnaygi

Deep neural network model of haptic saliency

Anna Metzger, Matteo Toscani, Arash Akbarinia, Matteo Valsecchi, Knut Drewing
2021 Scientific Reports  
The model successfully predicted where participants touched the stimuli.  ...  We trained a variational autoencoder to predict the spatial distribution of touch duration from the surface relief of the haptic stimuli.  ...  We are grateful to Jasmin Müller and Oleksandra Nychyporchuk for helping with data collection and the preparation of the setup figure.  ... 
doi:10.1038/s41598-020-80675-6 pmid:33446756 fatcat:neosxa4lb5c63cx35rcx2ceveq

Centripetal force draws the eyes, not memory of the target, toward the center

Dirk Kerzel
2003 Journal of Experimental Psychology. Learning, Memory and Cognition  
spiral tube situation exist.  ...  In the spiral tube problem, it would act to pull the object toward the center of the tube.  ... 
doi:10.1037/0278-7393.29.3.458 pmid:12776756 fatcat:ych4qchof5bzrel2hm2bf5qwme

Bioinspired Visual Motion Estimation

Garrick Orchard, Ralph Etienne-Cummings
2014 Proceedings of the IEEE  
Replicating biological visual sensing was one of the first tasks attempted in the neuromorphic field. In this paper we focus specifically on the task of visual motion estimation.  ...  We describe the task itself, present the progression of works from the early first attempts through to the modern day state-of-the-art, and provide an outlook for future directions in the field.  ...  The spiral stimulus used has been superimposed on the image as a yellow dashed line. Fig. 11 shows another example of the architecture operating on real world data.  ... 
doi:10.1109/jproc.2014.2346763 fatcat:pdocaf6w2nez3nym4yzfpznyqe

CAVIAR: A 45k Neuron, 5M Synapse, 12G Connects/s AER Hardware Sensory–Processing– Learning–Actuating System for High-Speed Visual Object Recognition and Tracking

R. Serrano-Gotarredona, M. Oster, P. Lichtsteiner, A. Linares-Barranco, R. Paz-Vicente, F. Gomez-Rodriguez, L. Camunas-Mesa, R. Berner, M. Rivas-Perez, T. Delbruck, Shih-Chii Liu, R. Douglas (+6 others)
2009 IEEE Transactions on Neural Networks  
CAVIAR uses the asychronous address-event representation (AER) communication framework and was developed in the context of a European Union funded project.  ...  This paper describes CAVIAR, a massively parallel hardware implementation of a spike-based sensing-processing-learning-actuating system inspired by the physiology of the nervous system.  ...  (a) Architecture and underlying layout of the four populations or quadrants receiving inputs from four convolution chips. (b) The architecture of one of the quadrants, each with 256 neurons.  ... 
doi:10.1109/tnn.2009.2023653 pmid:19635693 fatcat:gecxue2nabhrvbxlag5xoiokju

2020 Index IEEE Transactions on Visualization and Computer Graphics Vol. 26

2021 IEEE Transactions on Visualization and Computer Graphics  
., +, TVCG Jan. 2020 949-959 DeepOrganNet: On-the-Fly Reconstruction and Visualization of 3D / 4D Lung Models from Single-View Projections by Deep Deformation Network.  ...  ., Simulating Liquids on Dynamically Warping Grids; TVCG June 2020 2288-2302 Igarashi, T., see Ibayashi, H., 2288-2302 Isaacs, K., see Williams, K., 1118-1128 Isenberg, P., see Chang, R., TVCG Jan. 2020  ...  ., +, Image resolution DeepOrganNet: On-the-Fly Reconstruction and Visualization of 3D / 4D Lung Models from Single-View Projections by Deep Deformation Network.  ... 
doi:10.1109/tvcg.2021.3111804 fatcat:lvhpoz5sqjhclo3roocrdtzs2m

Defense Advanced Research Projects Agency (Darpa) Fiscal Year 2019 Budget Estimates

Department Of Defense Comptroller's Office
2018 Zenodo  
Efforts focus on identified medical gaps in warfighter carerelated to health monitoring and preventing the spread of infectious disease.  ...  for long-term national security enhancement through the discovery of new phenomena and the exploration of the potential of such phenomena for defense applications.  ...  Depending on the need, a ReImagine imager would be able to selectively collect and simultaneously process data from a specific ROI, for example, at a higher resolution (i.e., foveated imaging), at a higher  ... 
doi:10.5281/zenodo.1215599 fatcat:kxduvg6a5nflhf6iilkwnolobu

Application of Mouse Models to Research in Hearing and Balance

Kevin K. Ohlemiller, Sherri M. Jones, Kenneth R. Johnson
2016 Journal of the Association for Research in Otolaryngology  
Depending on the research question, however, some mouse models and research designs will be more appropriate than others.  ...  Every application of mice is founded on assumptions about what mice represent and how the information gained may be generalized.  ...  the genetic variability of human populations.  ... 
doi:10.1007/s10162-016-0589-1 pmid:27752925 pmcid:PMC5112220 fatcat:naj42zr53fhnnkax6a743cdere

Eye movements in active visual search: A computable phenomenological model

T. D. Keech, L. Resca
2010 Attention, Perception & Psychophysics  
For example, about 3% of the times that the target is even directly foveated, it is still not recognized (Motter & Belky, 1998a , p. 1808 .  ...  the same bimodal characteristics as those derived from the observations, both indicating the presence of spiraling or circulat-(panel B).  ...  So, this article ultimately reflects the remarkable expertise collectively provided to the authors by all the individuals mentioned above.  ... 
doi:10.3758/app.72.2.285 pmid:20139446 fatcat:75supyu7efhcvmkr6dai5tmqrm

Incremental focus of attention for robust visual tracking

K. Toyama, G.D. Hager
1996 Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
We present the Incremental Focus of Attention (IFA) architecture for robust, adaptive, real-time motion tracking.  ...  In particular, examples show that recovery times after lost tracking depend primarily on the number of objects visually similar to the target in the field of view.  ...  This article describes the development of the IFA architecture for efficient and robust vision-based tracking.  ... 
doi:10.1109/cvpr.1996.517073 dblp:conf/cvpr/ToyamaH96 fatcat:aetnuqwj25drzhsmfl7qpc6qfm
« Previous Showing results 1 — 15 out of 40 results