Multi-modal primitives as functional models of hyper-columns and their use for contextual integration

Authors:
Norbert Krüger;Florentin Wörgötter
Affiliations:
Media Lab, Aalborg University Copenhagen;Computational Neuroscience, University of Stirling
Venue:
BVAI'05 Proceedings of the First international conference on Brain, Vision, and Artificial Intelligence
Year:
2005

Citing 8
Cited 4

An Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image Sequences

IEEE Transactions on Pattern Analysis and Machine Intelligence
Integration of visual modules: an extension of the Marr paradigm

Integration of visual modules: an extension of the Marr paradigm
Performance of optical flow techniques

International Journal of Computer Vision
Signal Processing for Computer Vision

Signal Processing for Computer Vision
An explicit and compact coding of geometric and structural image information applied to stereo processing

Pattern Recognition Letters
Early Cognitive Vision: Using Gestalt-Laws for Task-Dependent, Active Image-Processing

Natural Computing: an international journal
Optical flow estimation from monogenic phase

IWCM'04 Proceedings of the 1st international conference on Complex motion
The monogenic signal

IEEE Transactions on Signal Processing

Continuous dimensionality characterization of image structures

Image and Vision Computing
Probabilistic Pose Recovery Using Learned Hierarchical Object Models

Cognitive Vision
Probabilistic object models for pose estimation in 2D images

DAGM'11 Proceedings of the 33rd international conference on Pattern recognition
Three dilemmas of signal- and symbol-based representations in computer vision

BVAI'05 Proceedings of the First international conference on Brain, Vision, and Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we describe a biological motivated image representation in terms of local multi–modal primitives. These primitives are functional abstractions of hypercolumns in V1 [13]. The efficient and generic coding of visual information in terms of local symbolic descriptiones allows for a wide range of applications. For example, they have been used to investigate the multi–modal character of Gestalt laws in natural scenes [14], to code a multi–modal stereo matching and to investigate the role of different visual modalities for stereo [11], and to use a combination of stereo and grouping as well as Rigid Body Motion to acquire reliable 3D information as demonstrated in this publication.