Filters








1,657 Hits in 7.7 sec

Biologically-inspired robust motion segmentation using mutual information

Anna-Louise Ellis, James Ferryman
2014 Computer Vision and Image Understanding  
Biologically-Inspired Segmentation 44 The ability of primates to recognise objects of interest, regardless of illu-45 mination and background, drives much of the biologically inspired computa-46 2 includes  ...  As flies are capable of 89 exploiting optical flow, which modelled by calculating the local image mo-90 tion with Reichardt motion detectors (and referred to as Elementary Motion 91 Detectors), they use  ...  retinal signals that occur in primate vision, in order to assist further pro-160 cessing of that input, in a primate biologically inspired manner, in the visual 161 cortex.  ... 
doi:10.1016/j.cviu.2014.01.009 fatcat:c5pozz2awbeq5nia5m24memcxa

Bio-inspired computer vision: Towards a synergistic approach of artificial and biological vision

N. V. Kartheek Medathati, Heiko Neumann, Guillaume S. Masson, Pierre Kornprobst
2016 Computer Vision and Image Understanding  
Studies in biological vision have always been a great source of inspiration for design of computer vision algorithms.  ...  Based on this comparative analysis of computer and biological vision, we present some recent models in biological vision and highlight a few models that we think are promising for future investigations  ...  H N acknowledges support from DFG in the SFB/TRR 'A Companion Technology for Cognitive Technical Systems. P K acknowledges support from the EC IP project FP7-ICT-2011-9 no. 600847 (RENVISION).  ... 
doi:10.1016/j.cviu.2016.04.009 fatcat:lad5bwlqgbb5nhgtnxj6d32mc4

Naturalistic stimuli reveal a dominant role for agentic action in visual representation

James V. Haxby, M. Ida Gobbini, Samuel A. Nastase
2020 NeuroImage  
Naturalistic, dynamic movies evoke strong, consistent, and information-rich patterns of activity over a broad expanse of cortex and engage multiple perceptual and cognitive systems in parallel.  ...  The use of naturalistic stimuli enables functional brain imaging research to explore cognitive domains that are poorly sampled in highly-controlled experiments.  ...  in the representation of biological motion than the representation of facial form in natural viewing.  ... 
doi:10.1016/j.neuroimage.2020.116561 pmid:32001371 fatcat:owim5b636nfndoxuv3sqsccygy

Biologically-Inspired Computational Neural Mechanism for Human Action/activity Recognition: A Review

Bardia Yousefi, Chu Kiong Loo
2019 Electronics  
Theoretical neuroscience investigation shows valuable information on the mechanism for recognizing the biological movements in the mammalian visual system.  ...  This involves many different fields of researches such as psychological, neurophysiology, neuro-psychological, computer vision, and artificial intelligence (AI).  ...  (human as a moving object in video sequences (image frames)).  ... 
doi:10.3390/electronics8101169 fatcat:v6cuchycurd2xg7cx545dwujy4

Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision?

N. Kruger, P. Janssen, S. Kalkan, M. Lappe, A. Leonardis, J. Piater, A. J. Rodriguez-Sanchez, L. Wiskott
2013 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Computational modeling of the primate visual system yields insights of potential relevance to some of the challenges that computer vision is facing, such as object recognition and categorization, motion  ...  The hierarchal processing in the primate visual system is characterized by a sequence of different levels of processing (in the order of ten) that constitute a deep hierarchy in contrast to the flat vision  ...  We would also like to thank Michael D'Zmura for fruitful discussions.  ... 
doi:10.1109/tpami.2012.272 pmid:23787340 fatcat:fpocio4ptzc43iv6nt4fyx4aum

Bio-Inspired Optic Flow from Event-Based Neuromorphic Sensor Input [chapter]

Stephan Tschechne, Roman Sailer, Heiko Neumann
2014 Lecture Notes in Computer Science  
Computational models of visual processing often use framebased image acquisition techniques to process a temporally changing stimulus.  ...  We introduce a new approach for the modelling of cortical mechanisms of motion detection along the dorsal pathway using this type of representation.  ...  .: High Accuracy Optical Flow Estimation Based on a Theory for Warping. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25-36.  ... 
doi:10.1007/978-3-319-11656-3_16 fatcat:adym3otnfrhd5ovkm562gmy77m

A Connectionist Model May Shed Light on Neural Mechanisms for Visually Guided Reaching

Bartlett W. Mel
1991 Journal of Cognitive Neuroscience  
During motion planning, in- ternally driven sequences of imagined joint postures give rise, via the learned synaptic pathway, to the sequences of visual mental images that are used to develop motion plans  ...  This relation is thus a useful mechanism for aiming at and/or tracking a visual target. Once again, a biologically motivated instance of this function is shown in Figure 2F.  ... 
doi:10.1162/jocn.1991.3.3.273 pmid:23964842 fatcat:v7k3rri7lrcbvngxoy7c2jvyrq

A Model for Encoding Multiple Object Motions and Self-Motion in Area MST of Primate Visual Cortex

Richard S. Zemel, Terrence J. Sejnowski
1998 Journal of Neuroscience  
Many cells in the dorsal part of the medial superior temporal (MST) region of visual cortex respond selectively to specific combinations of expansion/contraction, translation, and rotation motions.  ...  Inputs to the model were generated from sequences of raytraced images that simulated realistic motion situations, combining observer motion, eye movements, and independent ob-ject motions.  ...  Representations and generalization in the multiple-cause model We tested the generalization ability of our model using the same test set of 50 flow fields from novel motion sequences.  ... 
doi:10.1523/jneurosci.18-01-00531.1998 pmid:9412529 fatcat:bupvghs5crattd2oyq6cr7r7ju

Going in circles is the way forward: the role of recurrence in visual inference [article]

Ruben S. van Bergen, Nikolaus Kriegeskorte
2020 arXiv   pre-print
Biological visual systems exhibit abundant recurrent connectivity. State-of-the-art neural network models for visual recognition, by contrast, rely heavily or exclusively on feedforward computation.  ...  exploit sequential dependencies in their data for better inference and prediction, and (5) leverage the power of iterative computation.  ...  ACKNOWLEDGEMENTS We thank Samuel Lippl, Heiko Schütt, Andrew Zaharia, Tal Golan and Benjamin Peters for detailed comments on a draft of this paper.  ... 
arXiv:2003.12128v3 fatcat:c7vjrebe4bbbnna34s4zlashaa

Attending to visual motion

John K. Tsotsos, Yueju Liu, Julio C. Martinez-Trujillo, Marc Pomplun, Evgueni Simine, Kunhao Zhou
2005 Computer Vision and Image Understanding  
Visual motion analysis has focused on decomposing image sequences into their component features. There has been little success at re-combining those features into moving objects.  ...  A new feed-forward motion-processing pyramid is presented motivated by the neurobiology of primate motion processes.  ...  Acknowledgments A number of people have contributed to this effort in important ways and we wish to express our thanks for their assistance: Sean Culhane, Stefan Treue, Guy Orban, Albert Rothenstein, Winky  ... 
doi:10.1016/j.cviu.2004.10.011 fatcat:jljx2rrhfncv3o26ir6j5ftrmq

Physiologically Inspired Model for the Visual Recognition of Transitive Hand Actions

F. Fleischer, V. Caggiano, P. Thier, M. A. Giese
2013 Journal of Neuroscience  
Our model accomplishes the recognition of hand actions from real video stimuli, exploiting exclusively mechanisms that can be implemented in a biologically plausible way by cortical neurons.  ...  While most existing models focus on the possible role of motor representations in action recognition, we propose a model showing that many critical properties of action-selective visual neurons can be  ...  The remaining sequences and in particular all sequences from dataset C were used for testing.  ... 
doi:10.1523/jneurosci.4129-12.2013 pmid:23575854 pmcid:PMC6619087 fatcat:we3p5fh5n5amlndgvuwkpqsqri

Unsupervised neural network models of the ventral visual stream

Chengxu Zhuang, Siming Yan, Aran Nayebi, Martin Schrimpf, Michael C. Frank, James J. DiCarlo, Daniel L. K. Yamins
2021 Proceedings of the National Academy of Sciences of the United States of America  
Taken together, these results illustrate a use of unsupervised learning to provide a quantitative model of a multiarea cortical brain system and present a strong candidate for a biologically plausible  ...  Deep neural networks currently provide the best quantitative models of the response patterns of neurons throughout the primate ventral visual stream.  ...  as computation models for the ventral visual cortex.  ... 
doi:10.1073/pnas.2014196118 pmid:33431673 fatcat:remyumahdze3jopzuxbz5rudhu

Implementation of structure-mapping inference by event-file binding and action planning: a model of tool-improvisation analogies

Chris Fields
2010 Psychological Research  
Tool improvisation requires correctly inferring the motion and force-transfer aVordances of an object; hence tool improvisation requires structure mapping driven by relational properties.  ...  However, tool-improvisation inferences are executed by members of a variety of non-human primate and other species.  ...  ConXict of interest statement The author states that he has no conXicts of interest relevant to the reported research.  ... 
doi:10.1007/s00426-010-0290-7 pmid:20526615 fatcat:y2ajzm3h65ec5nouofxx45tf6a

Bio-inspired visual attention for silicon retinas based on spiking neural networks applied to pattern classification [article]

Amélie Gruel, Jean Martinet
2021 arXiv   pre-print
This biological mechanism, more specifically saliency detection, has long been used in multimedia indexing to drive the analysis only on relevant parts of images or videos for further processing.  ...  In this paper, we review the biological background behind the attentional mechanism, and introduce a case study of event videos classification with SNNs, using a biology-grounded low-level computational  ...  [18] , in the form of three successive stages: a network inspired by the biological retina extracts the low-level image features, which are then decomposed into multiple visual pathways.  ... 
arXiv:2105.14753v1 fatcat:iwpob5wx6bc6tpjpzee6jz5ija

A modular network scheme for unsupervised 3D object recognition

Satoshi Suzuki, Hiroshi Ando
2000 Neurocomputing  
We evaluate the performance of the proposed modular network scheme through simulations using 3D wire-frame objects and discuss its related issues on object representations in the primate visual cortex.  ...  This paper presents an unsupervised learning scheme for recognizing 3D objects from their 2D projected images.  ...  Poggio for their helpful and insightful discussions. We are also grateful to the anonymous reviewers for useful comments on the paper.  ... 
doi:10.1016/s0925-2312(99)00148-4 fatcat:nrmzhsdmdng45m7rllnobnvzqi
« Previous Showing results 1 — 15 out of 1,657 results