9th European Signal Processing Conference (EUSIPCO 1998), 1998
In this work we introduce a method for generating a complete object representation based on its c... more In this work we introduce a method for generating a complete object representation based on its cover by a set of 2D views. This view-based representation has applications in several areas such as object recognition, computer graphics and video compression. The notion of image-based modeling received considerable attention in recent years. The basic motivation is to avoid the computational-intensive process of acquiring a 3D model followed by rendering. Instead, the approach uses a number of model images taken from different poses of the 3D object or scene as a basis. From these views any pose can be synthesized directly. Prior work used a small number of views to represent the object from a limited range of viewing directions. In the current work, a complete model that allows a presentation of the object from any viewing direction is introduced. A second novel aspect of the current work is a method for obtaining correspondence between views using a special pattern illumination. The...
Workshop on Modeling the Perception of Intentions David Pautler (pautlerd@ihpc.a-star.edu.sg) Pro... more Workshop on Modeling the Perception of Intentions David Pautler (pautlerd@ihpc.a-star.edu.sg) Programme in Computational Social Cognition, Institute of High Performance Computing 1 Fusionopolis Way, 16-16 Connexis Singapore 138632 Keywords: intention recognition; action understanding; theory of mind; event perception; social cognition; computational modeling; probabilistic inference. exploring a complex cognitive activity from different disciplinary perspectives. The Organizer Abstract While trained as a computer scientist myself, I have led a project on this topic for two years, collaborating closely with cognitive and social psychologists. Together we have completed a literature review spanning the disciplines listed above, designed and built a computational simulation furthering the schema-matching line of research, and published that work in a journal article last year: Attributing intentions to others based on observations of their behavior is a core cognitive ability. It is al...
Combining deep learning with brain-like innate structures may guide network models toward human-l... more Combining deep learning with brain-like innate structures may guide network models toward human-like learning
The present study was aimed at examining the factors inducing feature creation in the perceptual ... more The present study was aimed at examining the factors inducing feature creation in the perceptual and semantic sys-tems. The proposed research was guided by the hypothesis that due to the substantial load of categorization tasks, a preference exists for encoding features that are informative for the recognition of multiple categories. This claim extends theories stipulating that features are encoded for each categorization task individually and challenges theories that focus solely on encoding coincidences in input patterns. The research hypotheses were tested in a series of experi-ments, requiring participants to learn several new categories in controlled conditions. Experiment 1 demonstrated that while acquiring a sequence of four novel perceptual categories, features that are informative for recognizing several categories are created. This was observed despite an absence of suspicious coincidences in the input patterns. More-over, Experiment 1 provided evidence that after acquirin...
Cortical maps and feedback connections are ubiquitous features of the visual cerebral cortex. The... more Cortical maps and feedback connections are ubiquitous features of the visual cerebral cortex. The role of the feedback connections, however, is unclear. This study was aimed at revealing possible organizational relationships between the feedback projections from area V2 and the functional maps of orientation and retinotopy in area V1. Optical imaging of intrinsic signals was combined with cytochrome oxidase histochemistry and connectional anatomy in owl monkeys. Tracer injections were administered at orientation-selective domains in regions of pale and thick cytochrome oxidase stripes adjacent to the border between these stripes. The feedback projections from V2 were found to be more diffuse than the intrinsic horizontal connections within V1, but they nevertheless demonstrated clustering. The clusters of feedback axons projected preferentially to interblob cytochrome oxidase regions. The distribution of preferred orientations of the recipient domains in V1 was broad but appeared bi...
Proceedings of the Royal Society of London. Series B. Biological Sciences, 1979
The interpretation of structure from motion is examined from a computional point of view. The que... more The interpretation of structure from motion is examined from a computional point of view. The question addressed is how the three dimensional structure and motion of objects can be inferred from the two dimensional transformations of their projected images when no three dimensional information is conveyed by the individual projections. The following scheme is proposed: (i) divide the image into groups of four elements each; (ii) test each group for a rigid interpretation; (iii) combine the results obtained in (ii). It is shown that this scheme will correctly decompose scenes containing arbitrary rigid objects in motion, recovering their three dimensional structure and motion. The analysis is based primarily on the ʻstructure from motion’ theorem which states that the structure of four non-coplanar points is recoverable from three orthographic projections. The interpretation scheme is extended to cover perspective projections, and its psychological relevance is discussed.
ABSTRACTThe laminar location of the cell bodies and terminals of interareal connections determine... more ABSTRACTThe laminar location of the cell bodies and terminals of interareal connections determines the hierarchical structural organization of the cortex and has been intensively studied. However, we still have only a rudimentary understanding of the connectional principles of feedforward (FF) and feedback (FB) pathways. Quantitative analysis of retrograde tracers was used to extend the notion that the laminar distribution of neurons interconnecting visual areas provides an index of hierarchical distance (percentage of supragranular labeled neurons [SLN]). We show that: 1) SLN values constrain models of cortical hierarchy, revealing previously unsuspected areal relations; 2) SLN reflects the operation of a combinatorial distance rule acting differentially on sets of connections between areas; 3) Supragranular layers contain highly segregated bottom‐up and top‐down streams, both of which exhibit point‐to‐point connectivity. This contrasts with the infragranular layers, which contain ...
9th European Signal Processing Conference (EUSIPCO 1998), 1998
In this work we introduce a method for generating a complete object representation based on its c... more In this work we introduce a method for generating a complete object representation based on its cover by a set of 2D views. This view-based representation has applications in several areas such as object recognition, computer graphics and video compression. The notion of image-based modeling received considerable attention in recent years. The basic motivation is to avoid the computational-intensive process of acquiring a 3D model followed by rendering. Instead, the approach uses a number of model images taken from different poses of the 3D object or scene as a basis. From these views any pose can be synthesized directly. Prior work used a small number of views to represent the object from a limited range of viewing directions. In the current work, a complete model that allows a presentation of the object from any viewing direction is introduced. A second novel aspect of the current work is a method for obtaining correspondence between views using a special pattern illumination. The...
Workshop on Modeling the Perception of Intentions David Pautler (pautlerd@ihpc.a-star.edu.sg) Pro... more Workshop on Modeling the Perception of Intentions David Pautler (pautlerd@ihpc.a-star.edu.sg) Programme in Computational Social Cognition, Institute of High Performance Computing 1 Fusionopolis Way, 16-16 Connexis Singapore 138632 Keywords: intention recognition; action understanding; theory of mind; event perception; social cognition; computational modeling; probabilistic inference. exploring a complex cognitive activity from different disciplinary perspectives. The Organizer Abstract While trained as a computer scientist myself, I have led a project on this topic for two years, collaborating closely with cognitive and social psychologists. Together we have completed a literature review spanning the disciplines listed above, designed and built a computational simulation furthering the schema-matching line of research, and published that work in a journal article last year: Attributing intentions to others based on observations of their behavior is a core cognitive ability. It is al...
Combining deep learning with brain-like innate structures may guide network models toward human-l... more Combining deep learning with brain-like innate structures may guide network models toward human-like learning
The present study was aimed at examining the factors inducing feature creation in the perceptual ... more The present study was aimed at examining the factors inducing feature creation in the perceptual and semantic sys-tems. The proposed research was guided by the hypothesis that due to the substantial load of categorization tasks, a preference exists for encoding features that are informative for the recognition of multiple categories. This claim extends theories stipulating that features are encoded for each categorization task individually and challenges theories that focus solely on encoding coincidences in input patterns. The research hypotheses were tested in a series of experi-ments, requiring participants to learn several new categories in controlled conditions. Experiment 1 demonstrated that while acquiring a sequence of four novel perceptual categories, features that are informative for recognizing several categories are created. This was observed despite an absence of suspicious coincidences in the input patterns. More-over, Experiment 1 provided evidence that after acquirin...
Cortical maps and feedback connections are ubiquitous features of the visual cerebral cortex. The... more Cortical maps and feedback connections are ubiquitous features of the visual cerebral cortex. The role of the feedback connections, however, is unclear. This study was aimed at revealing possible organizational relationships between the feedback projections from area V2 and the functional maps of orientation and retinotopy in area V1. Optical imaging of intrinsic signals was combined with cytochrome oxidase histochemistry and connectional anatomy in owl monkeys. Tracer injections were administered at orientation-selective domains in regions of pale and thick cytochrome oxidase stripes adjacent to the border between these stripes. The feedback projections from V2 were found to be more diffuse than the intrinsic horizontal connections within V1, but they nevertheless demonstrated clustering. The clusters of feedback axons projected preferentially to interblob cytochrome oxidase regions. The distribution of preferred orientations of the recipient domains in V1 was broad but appeared bi...
Proceedings of the Royal Society of London. Series B. Biological Sciences, 1979
The interpretation of structure from motion is examined from a computional point of view. The que... more The interpretation of structure from motion is examined from a computional point of view. The question addressed is how the three dimensional structure and motion of objects can be inferred from the two dimensional transformations of their projected images when no three dimensional information is conveyed by the individual projections. The following scheme is proposed: (i) divide the image into groups of four elements each; (ii) test each group for a rigid interpretation; (iii) combine the results obtained in (ii). It is shown that this scheme will correctly decompose scenes containing arbitrary rigid objects in motion, recovering their three dimensional structure and motion. The analysis is based primarily on the ʻstructure from motion’ theorem which states that the structure of four non-coplanar points is recoverable from three orthographic projections. The interpretation scheme is extended to cover perspective projections, and its psychological relevance is discussed.
ABSTRACTThe laminar location of the cell bodies and terminals of interareal connections determine... more ABSTRACTThe laminar location of the cell bodies and terminals of interareal connections determines the hierarchical structural organization of the cortex and has been intensively studied. However, we still have only a rudimentary understanding of the connectional principles of feedforward (FF) and feedback (FB) pathways. Quantitative analysis of retrograde tracers was used to extend the notion that the laminar distribution of neurons interconnecting visual areas provides an index of hierarchical distance (percentage of supragranular labeled neurons [SLN]). We show that: 1) SLN values constrain models of cortical hierarchy, revealing previously unsuspected areal relations; 2) SLN reflects the operation of a combinatorial distance rule acting differentially on sets of connections between areas; 3) Supragranular layers contain highly segregated bottom‐up and top‐down streams, both of which exhibit point‐to‐point connectivity. This contrasts with the infragranular layers, which contain ...
Uploads