Sven Dickinson -- Research


Overview

My research revolves around the problem of object recognition, in general, and generic object recognition, in particular. Humans are very good at recognizing novel exemplars from known classes and very poor at differentiating fine geometric or appearance-based differences between objects. The opposite is true in computer vision. Early recognition systems arising out of the AI community in the early 70's attempted to recognize object classes based on their coarse, prototypical shape, but failed in their efforts to recover more abstract shape descriptions from real images of real objects. Over the next 30 years, the community steadily backed away from the generic recognition problem with increasingly detailed models that were exemplar specific. Although we can now recognize object exemplars with greater geometric and appearance-based complexity, these techniques simply don't scale up to real object classes where local appearance-based feature correspondences don't exist across the exemplars in a class, and where feature correspondences are typically many-to-many (and not one-to-one).

Since 1985, my research has explored the problem of generic recognition and its many component subproblems, including shape representation, image abstraction, perceptual grouping, shape indexing, shape matching, and shape tracking. In addition, I have applied various generic recognition frameworks to a number of applications, including content-based image retrieval, vision-based aids for the disabled, vision-based navigation, the integration of vision and language, and space robotics, to name just a few. The following sections highlight some of the problems we've explored along with some of the progress we've made. Generic recognition is the holy grail of object recognition, and it poses some wonderful challenges. Since recognition is a multifaceted problem, including representation, indexing, matching, and applications, you'll find many of my papers below listed under multiple categories. The edited collections and overview chapters, immediately below, provide an overview of the problem, talk about issues facing the community, and provide an extensive review.

Shape Perception in Human and Computer Vision: An Interdisciplinary Perspective
S. Dickinson and Z. Pizlo (Eds.)
Advances in Computer Vision and Pattern Recognition Series, Springer Verlag, 2013.

The Role of Mid-Level Shape Priors in Perceptual Grouping and Image Abstraction
S. Dickinson, A. Levinshtein, P. Sala, and C. Sminchisescu
In Shape Perception in Human and Computer Vision: An Interdisciplinary Perspective, S. Dickinson and Z. Pizlo (Eds.), Springer Verlag, in press.

preface to Special Issue on Shape Perception: Recent Results and Models
Z. Pizlo and S. Dickinson, Guest Editors
Seeing and Perceiving, Volume 25, 2012, pp 235--236.

The Evolution of Object Categorization and the Challenge of Image Abstraction
S. Dickinson
in: S. Dickinson, B. Schiele, and M. Tarr, (eds), Object Categorization: Computer and Human Vision Perspectives, Cambridge University Press, 2009, pp 1--37.

Introduction to the Special Section on Graph Algorithms in Computer Vision
S. Dickinson, M. Pelillo, and R. Zabih,
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 23, Number 10, October 2001, pp 1049--1052.

Object Representation and Recognition
S. Dickinson,
in: E. Lepore and Z. Pylyshyn (eds.), What is Cognitive Science?, Basil Blackwell publishers, 1999, pp 172--207.

Object Categorization: Computer and Human Vision Perspectives
S. Dickinson, B. Schiele, and M. Tarr, (eds),
Cambridge University Press, 2009.

Shape Representation/Recovery

Generic object recognition requires modeling the shape of an object in a way that the resulting description is invariant to within-class shape deformation. Since two coffee cups can have different surface markings, handle shapes, and body profiles, a class-based description simply cannot describe local shape or appearance. Still, there are some big questions to answer. For example, should shape representations be object-centered or viewer-centered? What are the component primitives of such descriptions? How do we recover these primitives? Do we represent shape differently at different scales? Below you'll find a number of generic shape descriptions we've explored over the years.

Part-Based Views

3-D Volumetric Shape Abstraction from a Single 2-D Image
P. Sala and S. Dickinson
Proceedings, 5th International IEEE Workshop on 3D Representation and Recognition (3dRR-15), Santiago, Chile, December 17, 2015.

The Role of Model-Based Segmentation in the Recovery of Volumetric Parts from Range Data
S. Dickinson, D. Metaxas, and A. Pentland,
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 3, March 1997, pp 259--267.

Active Object Recognition Integrating Attention and Viewpoint Control
S. Dickinson, H. Christensen, J. Tsotsos, and G. Olofsson,
Computer Vision and Image Understanding, Vol. 67, No. 3, September 1997, pp 239--260.

Active Object Recognition Integrating Attention and Viewpoint Control

S. Dickinson, H. Christensen, J. Tsotsos, and G. Olofsson,
Proceedings, European Conference on Computer Vision (ECCV), May 1994, pp B:3--14.

Part-Based Modeling and Qualitative Recognition
S. Dickinson,
in: A. Jain and P. Flynn (eds.), Three-Dimensional Object Recognition Systems, Advances in Image Communication and Machine Vision Series, Elsevier Science Publishers, Amsterdam, 1993, pp 201--228.

3-D Shape Recovery using Distributed Aspect Matching
S. Dickinson, A. Pentland, and A. Rosenfeld,
IEEE Transactions on Pattern Analysis and Machine Intelligence, special issue on Interpretation of 3-D Scenes, Vol. 14, No. 2, 1992, pp 174--198.

From Volumes to Views: An Approach to 3-D Object Recognition
S. Dickinson, A. Pentland, and A. Rosenfeld,
Computer Vision and Image Understanding, special issue on CAD-based vision, Vol. 55, No. 2, March 1992, pp 130--154.

From Volumes to Views: An Approach to 3-D Object Recognition
S. Dickinson, A. Pentland, and A. Rosenfeld,
Proceedings, IEEE Workshop on Directions in Automated ``CAD-Based'' Vision, Maui, HI, June, 1991, pp 85--96.

Qualitative 3-D Shape Reconstruction Using Distributed Aspect Matching
S. Dickinson, A. Pentland, and A. Rosenfeld,
Proceedings, Third IEEE International Conference on Computer Vision (ICCV), Osaka, Japan, December, 1990, pp 257--262.

A Representation for Qualitative 3-D Object Recognition Integrating Object-Centered and Viewer-Centered Models
S. Dickinson, A. Pentland, and A. Rosenfeld,
in: K. Leibovic (ed.), Vision: A Convergence of Disciplines, Springer Verlag, NY, 1990, pp 398--421.

Deformable Models

The Role of Model-Based Segmentation in the Recovery of Volumetric Parts from Range Data
S. Dickinson, D. Metaxas, and A. Pentland,
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 3, March 1997, pp 259--267.

Using Aspect Graphs to Control the Recovery and Tracking of Deformable Models
S. Dickinson and D. Metaxas,
International Journal of Pattern Recognition and Artificial Intelligence, Vol. 11, No. 1, February, 1997, pp 115--142.

Integrating Qualitative and Quantitative Object Representations in the Recovery and Tracking of 3-D Shape
S. Dickinson and D. Metaxas,
in: L. Harris and M. Jenkin (eds.), Computational and Psychophysical Mechanisms of Visual Coding, Cambridge University Press, New York, NY, 1997, pp 221--248.

Integrating Qualitative and Quantitative Shape Recovery
S. Dickinson and D. Metaxas,
International Journal of Computer Vision, Vol. 13, No. 3, 1994, pp 1--20.

Decoupling Recognition and Localization in CAD-Based Vision
S. Dickinson and D. Metaxas,
Proceedings, 2nd IEEE CAD-Based Vision Workshop, Champion, PA, February 1994, pp 246--257.

Integration of Quantitative and Qualitative Techniques for Deformable Model Fitting from Orthographic, Perspective, and Stereo Projections
D. Metaxas and S. Dickinson,
Proceedings, Fourth International Conference on Computer Vision (ICCV), Berlin, May, 1993, pp 641--649.

Functional Models

Recognition by Functional Parts
E. Rivlin, S. Dickinson, and A. Rosenfeld,
Computer Vision and Image Understanding, special issue on Function-based Object Recognition, Vol. 62, No. 2, September, 1995, pp 164--176.

Recognition by Functional Parts
E. Rivlin, S. Dickinson, and A. Rosenfeld,
Proceedings, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, June 1994, pp 267--274.

Saliency Maps

View-Based Object Recognition Using Saliency Maps
A. Shokoufandeh, I. Marsic, and S. Dickinson,
Image and Vision Computing, Volume 17, 1999, pp 445--460.

View-Based Object Matching
A. Shokoufandeh, I. Marsic, and S. Dickinson,
Proceedings, IEEE International Conference on Computer Vision (ICCV), Bombay, January 4--7, 1998, pp 588--595.

Shock Graphs

Shock Graph
S. Dickinson, A. Shokoufandeh, and K. Siddiqi
In: Katsushi Ikeuchi (Ed.). Computer Vision: A Reference Guide, Springer, New York, NY, 2014, pp 729-737.

Coarse-to-Fine Object Recognition using Shock Graphs
A. Bataille and S. Dickinson,
Proceedings, 5th IAPR-TC15 Workshop on Graph-Based Representations for Pattern Recognition, Poitiers, France, April 2005.

View-Based 3-D Object Recognition using Shock Graphs
D. Macrini, A. Shokoufandeh, S. Dickinson, K. Siddiqi, and S. Zucker,
Proceedings, International Conference on Pattern Recognition (ICPR), Quebec, August, 2002.

Spectral Methods for View-Based 3-D Object Recognition using Silhouettes
D. Macrini, A. Shokoufandeh, S. Dickinson, K. Siddiqi, and S. Zucker,
Proceedings, Joint IAPR International Workshop on Syntactical and Structural Pattern Recognition, Windsor, ON, August, 2002.

Shock Graphs and Shape Matching
K. Siddiqi, A. Shokoufandeh, S. Dickinson, and S. Zucker,
International Journal of Computer Vision, Volume 30, 1999, pp 1--24.

Shock Graphs and Shape Matching
K. Siddiqi, A. Shokoufandeh, S. Dickinson, and S. Zucker,
Proceedings, IEEE International Conference on Computer Vision (ICCV), Bombay, January 4--7, 1998, pp 222--229.

Bone Graphs

Bone Graphs: Medial Shape Parsing and Abstraction
D. Macrini, S. Dickinson, D. Fleet, and K. Siddiqi,
Computer Vision and Image Understanding, special issue on Graph-Based Representations, Vol. 115, No. 7, July 2011, pp 1044--1061.

Object Categorization using Bone GraphsBone Graphs
D. Macrini, S. Dickinson, D. Fleet, and K. Siddiqi,
Computer Vision and Image Understanding, Vol. 115, No. 8, August 2011, pp 1187--1206.

From Skeletons to Bone Graphs: Medial Abstraction for Object Recogtnition
D. Macrini, K. Siddiqi, and S. Dickinson,
Proceedings, IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, June 2008.

Other Skeletal Descriptions

Skeletal Shape Abstraction from Examples
F. Demirci, A. Shokoufandeh, and S. Dickinson,
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 31, No. 5, May 2009, pp 944--952.

Object Recognition as Many-to-Many Feature Matching
F. Demirci, A. Shokoufandeh, Y. Keselman, L. Bretzner, and S. Dickinson,
International Journal of Computer Vision, Volume 69, Number 2, August, 2006, pp 203--222.

Many-to-Many Feature Matching in Object Recognition
A. Shokoufandeh, Y. Keselman, F. Demirci, D. Macrini, and S. Dickinson,
in H. Christensen and H.-H. Nagel (eds.), Cognitive Vision Systems: Sampling the Spectrum of Approaches, Springer-Verlag, Berlin, 2006, pp 107--125.

3-D Model Retrieval Using Medial Surfaces
K. Siddiqi, J. Zhang, D. Macrini, S. Dickinson, and A. Shokoufandeh,
in: Medial Representations: Mathematics, Algorithms and Applications,
K. Siddiqi and S. Pizer (eds.), Kluwer, Boston, 2008, pp 309--326.

Retrieving Articulated 3-D Models Using Medial Surfaces
K. Siddiqi, J. Zhang, D. Macrini, A. Shokoufandeh, S. Bioux, and S. Dickinson
Machine Vision and Applications (MVA), Vol. 19, No. 4, July, 2008, pp 261--275.

Retrieving Articulated 3-D Models Using Medial Surfaces and their Graph Spectra
J. Zhang, K. Siddiqi, D. Macrini, A. Shokoufandeh, and S. Dickinson,
Proceedings, International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), St. Augustine, FL, November, 2005.

3D Object Retrieval using Many-to-many Matching of Curve Skeletons
N. Cornea, M. F. Demirci, D. Silver, A. Shokoufandeh, S. Dickinson, and P. Kantor,
Proceedings, The International Conference on Shape Modeling and Applications (SMI), MIT, June 2005.

Many-to-Many Graph Matching via Metric Embedding
Y. Keselman, A. Shokoufandeh, M. Demirci, and S. Dickinson,
Proceedings, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Madison, WI, June 2003.

Many-to-Many Feature Matching in Object Recognition
A. Shokoufandeh, Y. Keselman, F. Demirci, D. Macrini, and S. Dickinson,
in H. Christensen and H.-H. Nagel (eds.), Cognitive Vision Systems: Sampling the Spectrum of Approaches, Springer-Verlag, Berlin, 2006, pp 107--125.

Canonical Skeletons for Shape Matching
M. van Eede, D. Macrini, A. Telea, C. Sminchisescu, and S. Dickinson,
International Conference on Pattern Recognition, Hong Kong, August, 2006.

Optimal Inference for Hierarchical Skeleton Abstraction
A. Telea, C. Sminchisescu, and S. Dickinson,
Proceedings, International Conference on Pattern Recognition (ICPR), Cambridge, U.K., August 2004.

Skeleton Based Shape Matching and Retrieval
H. Sundar, D. Silver, N. Gagvani, and S. Dickinson,
Proceedings, Shape Modelling and Applications Conference, SMI 2003, Seoul, Korea, May 2003.

Blobs and Ridges

The Representation and Matching of Categorical Shape
A. Shokoufandeh, L. Bretzner, D. Macrini, M.F. Demirci, C. Jonsson, and S. Dickinson,
Computer Vision and Image Understanding (CVIU), Volume 103, 2006, pp 139--154.

Object Recognition as Many-to-Many Feature Matching
F. Demirci, A. Shokoufandeh, Y. Keselman, L. Bretzner, and S. Dickinson,
International Journal of Computer Vision, Volume 69, Number 2, August, 2006, pp 203--222.

Many-to-Many Feature Matching in Object Recognition
A. Shokoufandeh, Y. Keselman, F. Demirci, D. Macrini, and S. Dickinson,
in H. Christensen and H.-H. Nagel (eds.), Cognitive Vision Systems: Sampling the Spectrum of Approaches, Springer-Verlag, Berlin, 2006, pp 107--125.

Learning Hierarchical Shape Models from Examples
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), St. Augustine, FL, November, 2005.

Many-to-Many Feature Matching Using Spherical Coding of Directed Graphs
M. Demirci, A. Shokoufandeh, S. Dickinson, Y. Keselman, and L. Bretzner,
Proceedings, European Conference on Computer Vision (ECCV), Prague, May, 2004.

On the Representation and Matching of Qualitative Shape at Multiple Scales
A. Shokoufandeh, S. Dickinson, C. Jonsson, L. Bretzner, and T. Lindeberg,
Proceedings, European Conference on Computer Vision (ECCV), Copenhagen, May, 2002.

Top Points

The Representation and Matching of Images using Top Points
F. Demirci, B. Platel, A. Shokoufandeh, L. Florack, and S. Dickinson,
Journal of Mathematical Imaging and Vision, Vol. 35, No. 2, 2009, pp 103--116.

Discrete Representation of Top Points via Scale-Space Tessellation
B. Platel , M. F. Demirci, A. Shokoufandeh, L.M.J. Florack, F.M.W. Kanters, and S.J. Dickinson,
Proceedings, 5th International Conference on Scale Space and PDE Methods in Computer Vision, Hofgeismar, Germany, April 2005.

Geons

Geons
S. Dickinson and I. Biederman
In: Katsushi Ikeuchi (Ed.). Computer Vision: A Reference Guide, Springer, New York, NY, 2014, pp 338-346.

Panel Report: The Potential of Geons for Generic 3-D Object Recognition

S. Dickinson, R. Bergevin, I. Biederman, J.-O. Eklundh, A. Jain, R. Munck-Fairwod, and A. Pentland,
Image and Vision Computing, Vol. 15, No. 4, April 1997, pp 277--292.

Canonical View Modeling

Selecting Canonical Views for View-Based 3-D Object Recognition
T. Denton, M. Demirci, J. Abrahamson, A. Shokoufandeh, and S. Dickinson,
Proceedings, International Conference on Pattern Recognition (ICPR), Cambridge, U.K., August 2004.

View Degeneracy

A Computational Model of View Degeneracy
S. Dickinson, D. Wilkes, and J. Tsotsos,
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 21, Number 8, 1999, pp 673--689.

A Quantitative Model of View Degeneracy and its Application to Active Focal Length Control
D. Wilkes, S. Dickinson and J. Tsotsos,
Proceedings, International Conference on Computer Vision (ICCV), Cambridge, MA, June 20--23, 1995, pp 938--944.

Shape Abstraction

The failure of the early generic recognition systems was due to their inability to bridge the representational gap between the kinds of low-level features (e.g., edges, corners, lines, and regions) they could extract and the complex primitives that made up their generic object descriptions. The critical assumption these systems made was that there was a one-to-one correspondence between an extracted image feature and a generic model feature. This assumption restricted the approach to somewhat contrived objects where the assumption held. If a line was detected in the image, it must have matched an occluding boundary (limb) or salient surface discontinuity on a prototypical model of the object. Somehow, we must "lift" the extracted low-level features to more abstract descriptions at the level of our prototypical models. I call this the problem of abstraction, and think it's the greatest obstacle to generic object recognition the community faces. Below you'll find some approaches we've taken to solving this problem.

General Issues

The Role of Mid-Level Shape Priors in Perceptual Grouping and Image Abstraction
S. Dickinson, A. Levinshtein, P. Sala, and C. Sminchisescu
In Shape Perception in Human and Computer Vision: An Interdisciplinary Perspective, S. Dickinson and Z. Pizlo (Eds.), Springer Verlag, in press.

The Evolution of Object Categorization and the Challenge of Image Abstraction
S. Dickinson
in: S. Dickinson, B. Schiele, and M. Tarr, (eds), Object Categorization: Computer and Human Vision Perspectives, Cambridge University Press, pp 1--37.

Learning Abstract Shape Descriptions from Examples

3-D Volumetric Shape Abstraction from a Single 2-D Image
P. Sala and S. Dickinson
Proceedings, 5th International IEEE Workshop on 3D Representation and Recognition (3dRR-15), Santiago, Chile, December 17, 2015.

Skeletal Shape Abstraction from Examples
F. Demirci, A. Shokoufandeh, and S. Dickinson,
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 31, No. 5, May 2009, pp 944--952.

Qualitative 3D Surface Reconstruction from Images
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Snowbird Learning Workshop, Snowbird, Utah, April 2008.

Generic Model Abstraction from Examples
Y. Keselman and S. Dickinson,
IEEE Transactions on Pattern Analysis and Machine Intelligence, special issue on Syntactic and Structural pattern Recognition, Volume 27, Number 7, July 2005.

Bridging the Representation Gap Between Models and Exemplars
Y. Keselman and S. Dickinson,
Proceedings, IEEE Computer Society Workshop on Models versus Exemplars in Computer Vision, Kauai, Hawaii, December, 2001.

Generic Model Abstraction from Examples
Y. Keselman and S. Dickinson,
Proceedings, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Kauai, Hawaii, December, 2001.

Multi-Scale Skeletal Abstraction

A Framework for Symmetric Part Detection in Cluttered Scenes
T. Lee, S. Fidler, A. Levinshtein, C. Sminchisescu, and S. Dickinson
Symmetry, Volume 7, 2015, pp 1333-1351.

The Role of Mid-Level Shape Priors in Perceptual Grouping and Image Abstraction
S. Dickinson, A. Levinshtein, P. Sala, and C. Sminchisescu
In Shape Perception in Human and Computer Vision: An Interdisciplinary Perspective, S. Dickinson and Z. Pizlo (Eds.), Springer Verlag, in press.

Detecting Curved Symmetric Parts using a Deformable Disc Model
T. Lee, S. Fidler, and S. Dickinson
Proceedings, International Conference on Computer Vision (ICCV), Sydney, Australia, December 2013.

Multiscale Symmetric Part Detection and Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson
International Journal of Computer Vision (IJCV), Volume 104, Number 2, 2013, pp 117--134.

Multiscale Symmetric Part Detection and Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, International Conference on Computer Vision (ICCV), Kyoto, Japan, September 2009.

Canonical Skeletons for Shape Matching
M. van Eede, D. Macrini, A. Telea, C. Sminchisescu, and S. Dickinson,
International Conference on Pattern Recognition, Hong Kong, August, 2006.

Optimal Inference for Hierarchical Skeleton Abstraction
A. Telea, C. Sminchisescu, and S. Dickinson,
Proceedings, International Conference on Pattern Recognition (ICPR), Cambridge, U.K., August 2004.

Multi-Scale Blob/Ridge Abstraction

A Framework for Symmetric Part Detection in Cluttered Scenes
T. Lee, S. Fidler, A. Levinshtein, C. Sminchisescu, and S. Dickinson
Symmetry, Volume 7, 2015, pp 1333-1351.

Detecting Curved Symmetric Parts using a Deformable Disc Model
T. Lee, S. Fidler, and S. Dickinson
Proceedings, International Conference on Computer Vision (ICCV), Sydney, Australia, December 2013.

Multiscale Symmetric Part Detection and Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson
International Journal of Computer Vision (IJCV), Volume 104, Number 2, 2013, pp 117--134.

Multiscale Symmetric Part Detection and Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, International Conference on Computer Vision (ICCV), Kyoto, Japan, September 2009.

The Representation and Matching of Categorical Shape
A. Shokoufandeh, L. Bretzner, D. Macrini, M.F. Demirci, C. Jonsson, and S. Dickinson,
Computer Vision and Image Understanding (CVIU), Volume 103, 2006, pp 139--154.

On the Representation and Matching of Qualitative Shape at Multiple Scales
A. Shokoufandeh, S. Dickinson, C. Jonsson, L. Bretzner, and T. Lindeberg,
Proceedings, European Conference on Computer Vision (ECCV), Copenhagen, May, 2002.

Learning Decompositional Models from Examples

Learning Hierarchical Shape Models from Examples
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), St. Augustine, FL, November, 2005.

Part-Based Shape Abstraction

A Framework for Symmetric Part Detection in Cluttered Scenes
T. Lee, S. Fidler, A. Levinshtein, C. Sminchisescu, and S. Dickinson
Symmetry, Volume 7, 2015, pp 1333-1351.

3-D Volumetric Shape Abstraction from a Single 2-D Image
P. Sala and S. Dickinson
Proceedings, 5th International IEEE Workshop on 3D Representation and Recognition (3dRR-15), Santiago, Chile, December 17, 2015.

The Role of Mid-Level Shape Priors in Perceptual Grouping and Image Abstraction
S. Dickinson, A. Levinshtein, P. Sala, and C. Sminchisescu
In Shape Perception in Human and Computer Vision: An Interdisciplinary Perspective, S. Dickinson and Z. Pizlo (Eds.), Springer Verlag, in press.

Detecting Curved Symmetric Parts using a Deformable Disc Model
T. Lee, S. Fidler, and S. Dickinson
Proceedings, International Conference on Computer Vision (ICCV), Sydney, Australia, December 2013.

Multiscale Symmetric Part Detection and Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson
International Journal of Computer Vision (IJCV), Volume 104, Number 2, 2013, pp 117--134.

Spatiotemporal Contour Grouping using Abstract Part Models
P. Sala and S. Dickinson,
Proceedings, Asian Conference on Computer Vision (ACCV), Queenstown, New Zealand, November 2010.

Contour Grouping and Abstraction Using Simple Part Models
P. Sala and S. Dickinson,
Proceedings, European Conference on Computer Vision (ECCV), Crete, Greece, September 2010.

Multiscale Symmetric Part Detection and Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, International Conference on Computer Vision (ICCV), Kyoto, Japan, September 2009.

Model-Based Perceptual Grouping and Shape Abstraction
P. Sala and S. Dickinson,
Proceedings, Sixth IEEE Computer Society Workshop on Perceptual Organization in Computer Vision (POCV), Anchorage, Alaska, June 23, 2008.

Contour Grouping and Abstraction Using Simple Part Models
P. Sala and S. Dickinson,
Proceedings, European Conference on Computer Vision (ECCV), Crete, Greece, September 2010.

Human Vision

How is it that humans can recognize scenes depicted in line drawings almost as effectively as they can in color photographs? In this body of work, we study the problem of human shape perception in the context contour images, seeking to understand the role of nonaccidental relations in rapid scene classification.

Local Contour Symmetry Facilitates Scene Categorization
J. Wilder, M. Rezanejad, S. Dickinson, K. Siddiqi, A. Jepson, and D. B. Walther
Cognition, Volume 182, 2019, pp 3071--317.

Spatial Relationships Between Contours Impact Rapid Scene Classification
J. Wilder, S. Dickinson, A. Jepson, and D. B. Walther
Journal of Vision, Volume 18, Number 8, 2018, pp 1--15.

Object Indexing

Object recognition consists of two component problems: indexing and matching (or verification). Indexing is the process that takes the query image (containing one or more objects) and quickly finds a small set of model candidates that might account for the object(s) in the image. It has to be fast and it has to be sublinear, for the database may have thousands or millions of objects. Below you'll find some approaches we've taken to this problem.

3-D Object Indexing using Part-Based Views

3-D Volumetric Shape Abstraction from a Single 2-D Image
P. Sala and S. Dickinson
Proceedings, 5th International IEEE Workshop on 3D Representation and Recognition (3dRR-15), Santiago, Chile, December 17, 2015.

From Volumes to Views: An Approach to 3-D Object Recognition
S. Dickinson, A. Pentland, and A. Rosenfeld,
Computer Vision and Image Understanding, special issue on CAD-based vision, Vol. 55, No. 2, March 1992, pp 130--154.

2-D Shape Indexing using a Modal Description of Shape

Shape-Based Indexing in a Medical Image Database
W. Zhang, S. Dickinson, S. Sclaroff, J. Feldman, and S. Dunn,
Proceedings, IEEE Workshop on Biomedical Image Analysis, Santa Barbara, CA, June 26--27, 1998, pp 221--230.

Structural Indexing using Grapha Spectra

3-D Model Retrieval Using Medial Surfaces
K. Siddiqi, J. Zhang, D. Macrini, S. Dickinson, and A. Shokoufandeh,
in: Medial Representations: Mathematics, Algorithms and Applications,
K. Siddiqi and S. Pizer (eds.), Kluwer, Boston, 2008, pp 309--326.

Retrieving Articulated 3-D Models Using Medial Surfaces
K. Siddiqi, J. Zhang, D. Macrini, A. Shokoufandeh, S. Bioux, and S. Dickinson
Machine Vision and Applications (MVA), Vol. 19, No. 4, July, 2008, pp 261--275.

Retrieving Articulated 3-D Models Using Medial Surfaces and their Graph Spectra
J. Zhang, K. Siddiqi, D. Macrini, A. Shokoufandeh, and S. Dickinson,
Proceedings, International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), St. Augustine, FL, November, 2005.

Indexing Hierarchical Structures using Graph Spectra
A. Shokoufandeh, D. Macrini, S. Dickinson, K. Siddiqi, and S. Zucker,
IEEE Transactions on Pattern Analysis and Machine Intelligence, special issue on Syntactic and Structural pattern Recognition, Volume 27, Number 7, July 2005.

View-Based 3-D Object Recognition using Shock Graphs
D. Macrini, A. Shokoufandeh, S. Dickinson, K. Siddiqi, and S. Zucker,
Proceedings, International Conference on Pattern Recognition (ICPR), Quebec, August, 2002.

Indexing using a Spectral Encoding of Topological Structure
A. Shokoufandeh, S. Dickinson, K. Siddiqi, and S. Zucker,
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Fort Collins, CO, June 1999, pp 491--497.

Viewpoint-Invariant Shape Indexing for Content-Based Image Retrieval

Viewpoint-Invariant Indexing for Content-Based Image Retrieval
S. Dickinson, A. Pentland, and S. Stevenson,
Proceedings, IEEE International Workshop on Content-based Access of Image and Video Databases, Bombay, January 3, 1998, pp 20--30.

Object Matching

Once the indexing process has pruned the large database down to a small number of candidates, the final step consists of verifying the candidates (hypotheses), returning a distance measure used to rank-order the candidates. When the object to be recognized is occluded, perturbed by noise, embedded in a cluttered scene, or represented at a different scale from the model being matched to it, the matching problem becomes more challenging. We have explored these issues in a number of matching strategies, which we include below.

Object Recognition using Part-Based Aspect Graphs

Active Object Recognition Integrating Attention and Viewpoint Control
S. Dickinson, H. Christensen, J. Tsotsos, and G. Olofsson,
Computer Vision and Image Understanding, Vol. 67, No. 3, September 1997, pp 239--260.

Active Object Recognition Integrating Attention and Viewpoint Control

S. Dickinson, H. Christensen, J. Tsotsos, and G. Olofsson,
Proceedings, European Conference on Computer Vision (ECCV), May 1994, pp B:3--14.

Part-Based Modeling and Qualitative Recognition
S. Dickinson,
in: A. Jain and P. Flynn (eds.), Three-Dimensional Object Recognition Systems, Advances in Image Communication and Machine Vision Series, Elsevier Science Publishers, Amsterdam, 1993, pp 201--228.

3-D Shape Recovery using Distributed Aspect Matching
S. Dickinson, A. Pentland, and A. Rosenfeld,
IEEE Transactions on Pattern Analysis and Machine Intelligence, special issue on Interpretation of 3-D Scenes, Vol. 14, No. 2, 1992, pp 174--198.

From Volumes to Views: An Approach to 3-D Object Recognition
S. Dickinson, A. Pentland, and A. Rosenfeld,
Computer Vision and Image Understanding, special issue on CAD-based vision, Vol. 55, No. 2, March 1992, pp 130--154.

From Volumes to Views: An Approach to 3-D Object Recognition
S. Dickinson, A. Pentland, and A. Rosenfeld,
Proceedings, IEEE Workshop on Directions in Automated ``CAD-Based'' Vision, Maui, HI, June, 1991, pp 85--96.

Qualitative 3-D Shape Reconstruction Using Distributed Aspect Matching
S. Dickinson, A. Pentland, and A. Rosenfeld,
Proceedings, Third IEEE International Conference on Computer Vision (ICCV), Osaka, Japan, December, 1990, pp 257--262.

Object Recognition using Saliency Maps

View-Based Object Recognition Using Saliency Maps
A. Shokoufandeh, I. Marsic, and S. Dickinson,
Image and Vision Computing, Volume 17, 1999, pp 445--460.

View-Based Object Matching
A. Shokoufandeh, I. Marsic, and S. Dickinson,
Proceedings, IEEE International Conference on Computer Vision (ICCV), Bombay, January 4--7, 1998, pp 588--595.

Object Recognition using Shock Graphs

Shock Graph
S. Dickinson, A. Shokoufandeh, and K. Siddiqi
In: Katsushi Ikeuchi (Ed.). Computer Vision: A Reference Guide, Springer, New York, NY, 2014, pp 729-737.

3-D Model Retrieval Using Medial Surfaces
K. Siddiqi, J. Zhang, D. Macrini, S. Dickinson, and A. Shokoufandeh,
in: Medial Representations: Mathematics, Algorithms and Applications,
K. Siddiqi and S. Pizer (eds.), Kluwer, Boston, 2008, pp 309--326.

Retrieving Articulated 3-D Models Using Medial Surfaces
K. Siddiqi, J. Zhang, D. Macrini, A. Shokoufandeh, S. Bioux, and S. Dickinson
Machine Vision and Applications (MVA), Vol. 19, No. 4, July, 2008, pp 261--275.

Retrieving Articulated 3-D Models Using Medial Surfaces and their Graph Spectra
J. Zhang, K. Siddiqi, D. Macrini, A. Shokoufandeh, and S. Dickinson,
Proceedings, International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), St. Augustine, FL, November, 2005.

Coarse-to-Fine Object Recognition using Shock Graphs
A. Bataille and S. Dickinson,
Proceedings, 5th IAPR-TC15 Workshop on Graph-Based Representations for Pattern Recognition, Poitiers, France, April 2005.

View-Based 3-D Object Recognition using Shock Graphs
D. Macrini, A. Shokoufandeh, S. Dickinson, K. Siddiqi, and S. Zucker,
Proceedings, International Conference on Pattern Recognition (ICPR), Quebec, August, 2002.

Spectral Methods for View-Based 3-D Object Recognition using Silhouettes
D. Macrini, A. Shokoufandeh, S. Dickinson, K. Siddiqi, and S. Zucker,
Proceedings, Joint IAPR International Workshop on Syntactical and Structural Pattern Recognition, Windsor, ON, August, 2002.

Shock Graphs and Shape Matching
K. Siddiqi, A. Shokoufandeh, S. Dickinson, and S. Zucker,
International Journal of Computer Vision, Volume 30, 1999, pp 1--24.

Shock Graphs and Shape Matching
K. Siddiqi, A. Shokoufandeh, S. Dickinson, and S. Zucker,
Proceedings, IEEE International Conference on Computer Vision (ICCV), Bombay, January 4--7, 1998, pp 222--229.

Object Recognition using Blobs and Ridges

The Representation and Matching of Categorical Shape
A. Shokoufandeh, L. Bretzner, D. Macrini, M.F. Demirci, C. Jonsson, and S. Dickinson,
Computer Vision and Image Understanding (CVIU), Volume 103, 2006, pp 139--154.

Object Recognition as Many-to-Many Feature Matching
F. Demirci, A. Shokoufandeh, Y. Keselman, L. Bretzner, and S. Dickinson,
International Journal of Computer Vision, Volume 69, Number 2, August, 2006, pp 203--222.

Many-to-Many Feature Matching in Object Recognition
A. Shokoufandeh, Y. Keselman, F. Demirci, D. Macrini, and S. Dickinson,
in H. Christensen and H.-H. Nagel (eds.), Cognitive Vision Systems: Sampling the Spectrum of Approaches, Springer-Verlag, Berlin, 2006, pp 107--125.

Many-to-Many Feature Matching Using Spherical Coding of Directed Graphs
M. Demirci, A. Shokoufandeh, S. Dickinson, Y. Keselman, and L. Bretzner,
Proceedings, European Conference on Computer Vision (ECCV), Prague, May, 2004.

On the Representation and Matching of Qualitative Shape at Multiple Scales
A. Shokoufandeh, S. Dickinson, C. Jonsson, L. Bretzner, and T. Lindeberg,
Proceedings, European Conference on Computer Vision (ECCV), Copenhagen, May, 2002.

Object Recognition using Top Points

The Representation and Matching of Images using Top Points
F. Demirci, B. Platel, A. Shokoufandeh, L. Florack, and S. Dickinson,
Journal of Mathematical Imaging and Vision, Vol. 35, No. 2, 2009, pp 103--116.

Discrete Representation of Top Points via Scale-Space Tessellation
B. Platel , M. F. Demirci, A. Shokoufandeh, L.M.J. Florack, F.M.W. Kanters, and S.J. Dickinson,
Proceedings, 5th International Conference on Scale Space and PDE Methods in Computer Vision, Hofgeismar, Germany, April 2005.

Object Recognition as Many-to-Many Feature Matching

Many-to-Many Graph Matching
F. Demirci, A. Shokoufandeh, and S. Dickinson
In: Katsushi Ikeuchi (Ed.). Computer Vision: A Reference Guide, Springer, New York, NY, 2014, pp 472-477.

Efficient Many-to-Many feature Matching under the L-1 Norm
M. Demirci, Y. Osmanlioglu, A. Shokoufandeh, and S. Dickinson,
Computer Vision and Image Understanding, special issue on Graph-Based Representations, Vol. 115, No. 7, July 2011, pp 976--983.

Object Recognition as Many-to-Many Feature Matching
F. Demirci, A. Shokoufandeh, Y. Keselman, L. Bretzner, and S. Dickinson,
International Journal of Computer Vision, Volume 69, Number 2, August, 2006, pp 203--222.

Many-to-Many Feature Matching in Object Recognition
A. Shokoufandeh, Y. Keselman, F. Demirci, D. Macrini, and S. Dickinson,
in H. Christensen and H.-H. Nagel (eds.), Cognitive Vision Systems: Sampling the Spectrum of Approaches, Springer-Verlag, Berlin, 2006, pp 107--125.

Object Categorization and the Need for Many-to-Many Matching
S. Dickinson, A. Shokoufandeh, Y. Keselman, F. Demirci, and D. Macrini,
Proceedings (invited paper), 27th DAGM - The Annual meeting of the German Association for Pattern Recognition, Vienna, Austria, August, 2005.

Many-to-Many Feature Matching Using Spherical Coding of Directed Graphs
M. Demirci, A. Shokoufandeh, S. Dickinson, Y. Keselman, and L. Bretzner,
Proceedings, European Conference on Computer Vision (ECCV), Prague, May, 2004.

Many-to-Many Graph Matching via Metric Embedding
Y. Keselman, A. Shokoufandeh, M. Demirci, and S. Dickinson,
Proceedings, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Madison, WI, June 2003.

Many-to-Many Matching of Scale-Space Hierarchies using Metric Embedding
M. Demirci, A. Shokoufandeh, Y. Keselman, S. Dickinson, and L. Bretzner,
Proceedings, Scale-Space '03, Skye, UK, June 10-12, 2003.

Learning Hierarchical Shape Models from Examples
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), St. Augustine, FL, November, 2005.

Object Tracking

Tracking is a form of object recognition in which the object you're searching for in an image is simply the same one you found in the previous frame, along with some degree of knowledge of how it may have moved in between. Whether or not a prior shape model exists for the object, whether such a model is object-centered or viewer-centered, the representational gap between the model and the tracked exemplar, whether or not the object can deform or articulate as it moves are all issues that we have addressed in developing a number of tracking frameworks below.

3-D Object Tracking using Networks of Active Contours

Using Aspect Graphs to Control the Recovery and Tracking of Deformable Models
S. Dickinson and D. Metaxas,
International Journal of Pattern Recognition and Artificial Intelligence, Vol. 11, No. 1, February, 1997, pp 115--142.

Integrating Qualitative and Quantitative Object Representations in the Recovery and Tracking of 3-D Shape
S. Dickinson and D. Metaxas,
in: L. Harris and M. Jenkin (eds.), Computational and Psychophysical Mechanisms of Visual Coding, Cambridge University Press, New York, NY, 1997, pp 221--248.

Qualitative Tracking of 3-D Objects Using Active Contour Networks
S. Dickinson, P. Jasiobedzki, G. Olofsson, and H. Christensen,
Proceedings, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, June 1994, pp 812--817.

Tracking 3-D Deformable Models in 2-D Images

Using Aspect Graphs to Control the Recovery and Tracking of Deformable Models
S. Dickinson and D. Metaxas,
International Journal of Pattern Recognition and Artificial Intelligence, Vol. 11, No. 1, February, 1997, pp 115--142.

Integrating Qualitative and Quantitative Object Representations in the Recovery and Tracking of 3-D Shape
S. Dickinson and D. Metaxas,
in: L. Harris and M. Jenkin (eds.), Computational and Psychophysical Mechanisms of Visual Coding, Cambridge University Press, New York, NY, 1997, pp 221--248.

Physics-Based Tracking of 3-D Objects in 2-D Image Sequences
M. Chan, D. Metaxas, and S. Dickinson,
Proceedings, 12th International Conference on Pattern Recognition (ICPR), Jerusalem, Israel, October, 1994, pp 432--436.

A new Approach to Tracking 3-D Objects in 2-D Image Sequences
M. Chan, D. Metaxas, and S. Dickinson,
Proceedings, National Conference on Artificial Intelligence (AAAI), Seattle, August, 1994, pp 960--965.

Incremental Deformable 3-D Model Estimation through Tracking

Incremental Model-Based Estimation using Geometric Constraints
C. Sminchisescu, D. Metaxas, and S. Dickinson,
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 27, Number 5, May 2005.

Improving the Scope of Deformable Model Shape and Motion Estimation
C. Sminchisescu, D. Metaxas and S. Dickinson,
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Kauai, Hawaii, December, 2001.

Detecting and Tracking the Shapes of Multiple Independently Moving Objects

Unsupervised Motion Segmentation Using Metric Embedding of Features
Y. Osmanloglu, S. Dickinson, and A. Shokoufandeh
Proceedings, 3rd International Workshop on Similarity-Based Pattern Analysis and Recognition (SIMBAD), Copenhagen, October 2015.

Video In Sentences Out
A. Barbu, A. Bridge, Z. Burchill, D. Coroian, S. Dickinson, S. Fidler, A. Michaux, S. Mussman, S. Narayanaswamy, D. Salvi, L. Schmidt, J. Shangguan, J. Siskind, J. Waggoner, S. Wang, J. Wei, Y. Yin, and Z. Zhang,
Proceedings, Conference on Uncertainty in Artificial Intelligence (UAI), Catalina, CA, August 2012.

Optimal Image and Video Closure by Superpixel Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
International Journal of Computer Vision (IJCV), Volume 100, Number 1, 2012, pp 99--119.

Spatiotemporal Contour Grouping using Abstract Part Models
P. Sala and S. Dickinson,
Proceedings, Asian Conference on Computer Vision (ACCV), Queenstown, New Zealand, November 2010.

Spatiotemporal Closure
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, Asian Conference on Computer Vision (ACCV), Queenstown, New Zealand, November 2010.

Integrating Region and Boundary Information for Spatially Coherent Object Tracking
J. Maclean, D. Chung, and S. Dickinson,
Image and Vision Computing, Volume 24, 2006, pp 680--692.

Integrating Region and Boundary Information for Improved Spatial Coherence in Object Tracking
D. Chung, W. Maclean, and S. Dickinson,
Proceedings, Workshop on Articulated and Nonrigid Motion, IEEE Conference on Computer Vision and Pattern Recognition, Washington, D.C., June 27, 2004

Content-Based Image Retrieval

I once heard Jitendra Malik say in a talk, "Takeo Kanade once said that robotics is where computer vision meets the real world, while I think content-based image retrieval is where object recognition meets the real world." I couldn't agree more, for searching images on the web (for example) simply does not permit recognition strategies that rely on exact modeling of geometry or appearance. There is no better venue for generic object recognition than semantic-level image retrieval. We have explored a number of problems in CBIR, which we outline below.

Querying fMRI Images using Earth Mover's Distance

A Generalized Family of Fixed-Radius Distribution-Based Distance Measures for Content-Based fMRI Image Retrieval
J. Novatnack, N. Cornea, A. Shokoufandeh, D. Silver, S. Dickinson, P. Kantor, and B. Bai,
Pattern Recognition Letters, Volume 29, 2008, pp 1726--1732.

Querying Dental Radiographs using the Qualitative Shape of Lesions

Shape-Based Indexing in a Medical Image Database
W. Zhang, S. Dickinson, S. Sclaroff, J. Feldman, and S. Dunn,
Proceedings, IEEE Workshop on Biomedical Image Analysis, Santa Barbara, CA, June 26--27, 1998, pp 221--230.

Viewpoint-Invariant Shape Indexing for Content-Based Image Retrieval

Viewpoint-Invariant Indexing for Content-Based Image Retrieval
S. Dickinson, A. Pentland, and S. Stevenson,
Proceedings, IEEE International Workshop on Content-based Access of Image and Video Databases, Bombay, January 3, 1998, pp 20--30.

3-D Model Retrieval using Medial Surfaces

3-D Model Retrieval Using Medial Surfaces
K. Siddiqi, J. Zhang, D. Macrini, S. Dickinson, and A. Shokoufandeh,
in: Medial Representations: Mathematics, Algorithms and Applications,
K. Siddiqi and S. Pizer (eds.), Kluwer, Boston, 2008, pp 309--326.

Retrieving Articulated 3-D Models Using Medial Surfaces
K. Siddiqi, J. Zhang, D. Macrini, A. Shokoufandeh, S. Bioux, and S. Dickinson
Machine Vision and Applications (MVA), Vol. 19, No. 4, July, 2008, pp 261--275.

Retrieving Articulated 3-D Models Using Medial Surfaces and their Graph Spectra
J. Zhang, K. Siddiqi, D. Macrini, A. Shokoufandeh, and S. Dickinson,
Proceedings, International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), St. Augustine, FL, November, 2005.

Activity Recognition

Representing an activity in support of activity recognition is no less challenging than representing an object in support of object recognition. Just as the number of parts of an object and the relationships between the parts may vary, so too can the number of "actors" in an activity and the relationships between the actors. Moreover, the identifies of the actors may vary (a "ball" or a "bat" may be "thrown"). The scope of within-class variation of an activity, in terms of the number, relationships, and motions of the "parts" is therefore typically larger than that of an object. On the other hand, the motions of the parts may make them easier to segment in a video than segmenting an object's parts in a static image. While there are strong similarities between these two problems, they typically draw on very different tools. Below, we look at some image-based activity recognition systems applied to different applications.

Monitoring the Workflow of Construction Vehicles

Server-customer interaction tracker (SCIT): a computer vision-based system to estimate dirt loading cycles
E. Rezazadeh Azar, S. Dickinson, and B. McCabe
Journal of Construction Engineering and Management, Volume 139, Issue 7, July, 2013, pp 785--794.

Recognizing the Activities of Humans in a Natural Setting

Recognizing Human Activities from Partially Observed Videos
Y. Cao, D. Barrett, A. Barbu, S. Narayanaswamy, H. Yu, A. Michaux, Y. Lin, S. Dickinson, J. Siskind, and S. Wang
Proceedings, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, Oregon, June 2013.

Video In Sentences Out
A. Barbu, A. Bridge, Z. Burchill, D. Coroian, S. Dickinson, S. Fidler, A. Michaux, S. Mussman, S. Narayanaswamy, D. Salvi, L. Schmidt, J. Shangguan, J. Siskind, J. Waggoner, S. Wang, J. Wei, Y. Yin, and Z. Zhang,
Proceedings, Conference on Uncertainty in Artificial Intelligence (UAI), Catalina, CA, August 2012.

Vision-Based Navigation

Landmark-based navigation is a recognition problem, but not necessarily a generic one. Granted, if I tell you to turn left at the next fire station, you need to recognize a fire station you've never seen before using some sort of generic model. However, it's not clear that on your next trip by the fire station, its representation as a visual landmark at which you turn right is the same. How do we represent landmarks? What constitutes a good landmark? How do we automatically acquire good landmarks? And how do we navigate by them? These are some of the issues we explored in the links below.

Navigation using a Linear Combination of Landmark Views

Navigation Based on a Network of 2-D Images
D. Wilkes, S. Dickinson, E. Rivlin, and R. Basri,
Proceedings, 12th International Conference on Pattern Recognition (ICPR), Jerusalem, Israel, October, 1994, pp 373--378.

Expert Vision Systems for ALV Road Following

Algorithms for Road Navigation
L. Davis, D. DeMenthon, S. Dickinson, and P. Veatch,
in: I. Masaki (ed.), Vision-Based Navigation, Springer-Verlag, New York, 1992, pp 83--110.

A Flexible Tool for Prototyping ALV Road Following Algorithms
S. Dickinson and L. Davis,
IEEE Transactions on Robotics and Automation, Vol. 6, No. 2, 1990, pp 232--242.

An Expert Vision System for Autonomous Land Vehicle Road Following
S. Dickinson and L. Davis,
Proceedings, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Ann Arbor, MI, June, 1988, pp 826--831.

Automatic Landmark Acquisition for Vision-Based Navigation

Landmark Selection for Vision-Based Navigation
P. Sala, R. Sim, A. Shokoufandeh, and S. Dickinson,
IEEE Transactions on Robotics, Vol. 22, No. 2, April 2006, pp 334--349.

Landmark Selection for Vision-Based Navigation
P. Sala, R. Sim, A. Shokoufandeh, and S. Dickinson,
Proceedings, International Conference on Intelligent Robots and Systems (IROS), Sendai, Japan, September/October, 2004.

Behaviour-Based Vision

During my dissertation work, I focused primarily on the problem of unexpected, or bottom-up object recognition, which assumed that you didn't know what object you were looking at but knew it must be contained in the database. As a postdoc, I realized that this was a rather narrow view of recognition and that an intelligent agent employed a collection of recognition "behaviours." For example, when the agent walks into a room, it discovers what objects are in the room, perhaps with no prior expectation. This is analagous to the unexpected object recognition problem. Alternatively, the agent may enter the room with the goal of finding and retrieving a particular object, say a cup. This is the target, or top-down recognition problem, in which knowledge of the target object should constrain how features are extracted and matched to the model. If the handle of the cup is facing away from the agent, the cup may look like a glass. To resolve the ambiguity, the agent must plan a viewpoint change to a position at which the identity of the object can be disambiguated. This is the active recognition problem. As the agent moves to the preferred viewpoint or moves closer to the object, it must track the object. When it gets close enough to grasp the cup, it must both localize the object and recover sufficient shape information to grasp the object. I felt that these 5-6 recognition behaviours must sit on top of a single representational framework to allow them to be interchangeable in response to a complex task. I spent several years unifying these recognition behaviours through a single representational framework, which is described below.

Unifying Recognition Behaviours using a Single Representational Framework

Using Aspect Graphs to Control the Recovery and Tracking of Deformable Models
S. Dickinson and D. Metaxas,
International Journal of Pattern Recognition and Artificial Intelligence, Vol. 11, No. 1, February, 1997, pp 115--142.

Integrating Qualitative and Quantitative Shape Recovery
S. Dickinson and D. Metaxas,
International Journal of Computer Vision, Vol. 13, No. 3, 1994, pp 1--20.

Integrating Task-Directed Planning with Reactive Object Recognition
S. Dickinson, S. Stevenson, E. Amdur, J. Tsotsos,
Proceedings, SPIE Intelligent Robotics and Computer Vision XII, Boston, MA, September, 1993, pp 212--224.

3-D Shape Recovery using Distributed Aspect Matching
S. Dickinson, A. Pentland, and A. Rosenfeld,
IEEE Transactions on Pattern Analysis and Machine Intelligence, special issue on Interpretation of 3-D Scenes, Vol. 14, No. 2, 1992, pp 174--198.

From Volumes to Views: An Approach to 3-D Object Recognition
S. Dickinson, A. Pentland, and A. Rosenfeld,
Computer Vision and Image Understanding, special issue on CAD-based vision, Vol. 55, No. 2, March 1992, pp 130--154.

A Representation for Qualitative 3-D Object Recognition Integrating Object-Centered and Viewer-Centered Models
S. Dickinson, A. Pentland, and A. Rosenfeld,
in: K. Leibovic (ed.), Vision: A Convergence of Disciplines, Springer Verlag, NY, 1990, pp 398--421.

Vision-Based Aids for the Disabled

The multi-behaviour recognition model described above came to me while working on the PLAYBOT project at the University of Toronto, where I was a postdoc. PLAYBOT was the brain child of John Tsotsos, who envisioned a computer vision system that could help severely disabled children play with toys. The project brought together researchers from the University of Toronto and York University. Each of the behaviours described in the previous section had a corresponding behaviour in PLAYBOT's constrained world, and we came up with novel approaches to each of the subproblems. It also provided an ideal platform on which I could explore the unification of these recognition behaviours. Links describing the PLAYBOT system, along with our thoughts on task-driven vs. reactive beaviours are found below

PLAYBOT: A Robotic Vision System to Allow Disabled Children to Play with Toys

PLAYBOT: A Visually-Guided Robot to Assist Physically Disabled Children in Play
J. Tsotsos, G. Verghese, S. Dickinson, M. Jenkin, A. Jepson, E. Milios, F. Nuflo,
S. Stevenson, M. Black, D. Metaxas, S. Culhane, Y. Ye, and R. Mann,
Image and Vision Computing, special issue on Vision for the Disabled, Vol. 16, 1998, pp 275--292.

Integrating Task-Directed Planning with Reactive Object Recognition
S. Dickinson, S. Stevenson, E. Amdur, J. Tsotsos,
Proceedings, SPIE Intelligent Robotics and Computer Vision XII, Boston, MA, September, 1993, pp 212--224.

Integrating Vision and Language

Every time I built a recognition system, I'd always type in some label for an object model entered into the database. I began to wonder if there was a way I could somehow automatically learn the semantics (or at least the label) of a shape model. Could I build a system that exploited associations in web documents between the nouns in figure captions and the generic shapes found in their corresponding images? This would certainly require a powerful generic shape segmentation/matching engine that would have to deal with segmentation errors, occlusion, and significant within-class shape deformation. The representational gap alluded to earlier wreaks havoc here, for "salient" features, such as segmented regions often cannot be directly mapped to words. In the case of oversegmentation, such regions must be grouped, while for undersegmentation, such regions must be split. We have developed a new approach that can associate nouns and generic shape models in the presence of segmentation errors.

Automatic Image Annotation of Poorly Segmented Objects

Towards a Framework for Learning Structured Shape Models from Text-Annotated Images
S. Wachsmuth, S. Stevenson, and S. Dickinson,
Proceedings, HLT-NAACL03 Workshop on Learning Word Meaning from Non-Linguistic Data, Edmonton, June 2003.

Image-Guided Word-Sense Disambiguation

Unsupervised Disambiguation of Image Captions
W. May, S. Fidler, A. Fazly, S. Stevenson, and S. Dickinson,
Proceedings, First Joint Conference on Lexical and Computational Semantics (*SEM), Montreal, Canada, June 2012.

Language-Driven Perceptual Grouping

Discovering Hierarchical Object Models from Captioned Images
M. Jamieson, Y. Eskin, A. Fzaly, S. Stevenson, and S. Dickinson,
Computer Vision and Image Understanding, Volume 116, 2012, pp 842--853.

Learning categorical Shape from Captioned Images
T. Lee, S. Fidler, A. Levinshtein, and S. Dickinson,
Proceedings, Canadian Conference on Computer and Robot Vision (CRV), Toronto, ON, May 2012.

Discovering Multipart Appearance Models from Captioned Images
M. Jamieson, Y. Eskin, A. Fazly, S. Stevenson, and S. Dickinson,
Proceedings, European Conference on Computer Vision (ECCV), Crete, Greece, September 2010.

Using Language to Learn Structured Appearance Models for Image Annotation
M. Jamieson, A. Fazly, S. Stevenson, S. Dickinson, and S. Wachsmuth,
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 32., No. 1, January 2010, pp 148--164.

Learning Visual Compound Models from Parallel Image-Text Datasets
J. Moringen, S. Wachsmuth, S. Dickinson, and S. Stevenson,
30th Annual Symposium of the German Association for Pattern Recognition (DAGM), Munich, June 2008.

Learning Structured Appearance Models from Captioned Images of Cluttered Scenes
M. Jamieson, A. Fazly, S. Dickinson, S. Stevenson, and S. Wachsmuth
Proceedings, International Conference on Computer Vision (ICCV), Rio de Janeiro, October, 2007.

Using Language to Drive the Perceptual Grouping of Local Features
M. Jamieson, S. Dickinson, S. Stevenson, and S. Wachsmuth,
Proceedings, IEEE Conference on Computer Vision and Pattern Recognition, New York, NY, June 2006.

Learning the Motion Semantics of Verbs

Learning the Abstract Motion Semantics of Verbs from Captioned Videos
S. Mathe, S. Dickinson, S. Stevenson, and A. Fazly,
Proceedings, 3rd International Workshop on Semantic Learning and Applications in Multimedia (SLAM), Anchorage, Alaska, June 27, 2008.

American Sign Language Video Analysis

Detecting Reduplication in Videos of American Sign Language
Z. Gavrilov, S. Sclaroff, C. Neidle, and S. Dickinson,
Proceedings, Eighth International Conference on Language Resources and Evaluation (LREC), Istanbul, May 2012.

Generating Sentential Descriptions of Videos

Video In Sentences Out
A. Barbu, A. Bridge, Z. Burchill, D. Coroian, S. Dickinson, S. Fidler, A. Michaux, S. Mussman, S. Narayanaswamy, D. Salvi, L. Schmidt, J. Shangguan, J. Siskind, J. Waggoner, S. Wang, J. Wei, Y. Yin, and Z. Zhang,
Proceedings, Conference on Uncertainty in Artificial Intelligence (UAI), Catalina, CA, August 2012.

Space Robotics

We have been working with MD Robotics, developers of the NASA Space Shuttle Canadarm and the International Space Station (ISS) robotic arms, to develop a "visual supervisor" for spaceborne safety monitoring for the ISS. From a low-resolution, wide field of view camera, the system draws on our object tracking and recognition algorithms to detect the silhouette boundaries of multiple independently moving objects (against moving background), identify the objects' categories, compare the motions and identities of the objects to an active task library, and finally to detect anomalous behaviours. The system provides a "visual sanity check" of a space environment, and directs task-specific resources to further investigate anomalous behaviours. The system is described below:

A Computer Vision System for Spaceborne Safety Monitoring
F. Qureshi, D. Macrini, D. Chung, J. Maclean, S. Dickinson, and P. Jasiobedzki,
Proceedings, 8th International Symposium on Artificial Intelligence, Robotics and Automation in Space (iSAIRAS), Munich, September 2005, e-proceedings - no page numbers.

Vision and Learning

Learning can play an important role in generic object modeling. Given a set of exemplars belonging to a single, known object class, can we automatically learn a prototypical, possibly hierarchical description for the class? Or, in a collection of images with captions, in which there are references in the captions to objects in the image, can we automatically learn the names of the shapes? These are some of the learning problems we're exploring.

Learning Abstract Model Descriptions from Examples

A Framework for Symmetric Part Detection in Cluttered Scenes
T. Lee, S. Fidler, A. Levinshtein, C. Sminchisescu, and S. Dickinson
Symmetry, Volume 7, 2015, pp 1333-1351.

3-D Volumetric Shape Abstraction from a Single 2-D Image
P. Sala and S. Dickinson
Proceedings, 5th International IEEE Workshop on 3D Representation and Recognition (3dRR-15), Santiago, Chile, December 17, 2015.

Detecting Curved Symmetric Parts using a Deformable Disc Model
T. Lee, S. Fidler, and S. Dickinson
Proceedings, International Conference on Computer Vision (ICCV), Sydney, Australia, December 2013.

Multiscale Symmetric Part Detection and Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson
International Journal of Computer Vision (IJCV), Volume 104, Number 2, 2013, pp 117--134.

Contour Grouping and Abstraction Using Simple Part Models
P. Sala and S. Dickinson,
Proceedings, European Conference on Computer Vision (ECCV), Crete, Greece, September 2010.

Spatiotemporal Contour Grouping using Abstract Part Models
P. Sala and S. Dickinson,
Proceedings, Asian Conference on Computer Vision (ACCV), Queenstown, New Zealand, November 2010.

Multiscale Symmetric Part Detection and Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, International Conference on Computer Vision (ICCV), Kyoto, Japan, September 2009.

Skeletal Shape Abstraction from Examples
F. Demirci, A. Shokoufandeh, and S. Dickinson,
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 31, No. 5, May 2009, pp 944--952.

Generic Model Abstraction from Examples
Y. Keselman and S. Dickinson,
IEEE Transactions on Pattern Analysis and Machine Intelligence, special issue on Syntactic and Structural pattern Recognition, Volume 27, Number 7, July 2005.

Bridging the Representation Gap Between Models and Exemplars
Y. Keselman and S. Dickinson,
Proceedings, IEEE Computer Society Workshop on Models versus Exemplars in Computer Vision, Kauai, Hawaii, December, 2001.

Generic Model Abstraction from Examples
Y. Keselman and S. Dickinson,
Proceedings, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Kauai, Hawaii, December, 2001.

Learning Semantic Labels for Image Objects

Discovering Hierarchical Object Models from Captioned Images
M. Jamieson, Y. Eskin, A. Fzaly, S. Stevenson, and S. Dickinson,
Computer Vision and Image Understanding, Volume 116, 2012, pp 842--853.

Discovering Multipart Appearance Models from Captioned Images
M. Jamieson, Y. Eskin, A. Fazly, S. Stevenson, and S. Dickinson,
Proceedings, European Conference on Computer Vision (ECCV), Crete, Greece, September 2010.

Using Language to Learn Structured Appearance Models for Image Annotation
M. Jamieson, A. Fazly, S. Stevenson, S. Dickinson, and S. Wachsmuth,
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 32., No. 1, January 2010, pp 148--164.

Learning Visual Compound Models from Parallel Image-Text Datasets

J. Moringen, S. Wachsmuth, S. Dickinson, and S. Stevenson,
30th Annual Symposium of the German Association for Pattern Recognition (DAGM), Munich, June 2008.

Learning Structured Appearance Models from Captioned Images of Cluttered Scenes
M. Jamieson, A. Fazly, S. Dickinson, S. Stevenson, and S. Wachsmuth
Proceedings, International Conference on Computer Vision (ICCV), Rio de Janeiro, October, 2007.

Using Language to Drive the Perceptual Grouping of Local Features
M. Jamieson, S. Dickinson, S. Stevenson, and S. Wachsmuth,
Proceedings, IEEE Conference on Computer Vision and Pattern Recognition, New York, NY, June 2006.

Towards a Framework for Learning Structured Shape Models from Text-Annotated Images
S. Wachsmuth, S. Stevenson, and S. Dickinson,
Proceedings, HLT-NAACL03 Workshop on Learning Word Meaning from Non-Linguistic Data, Edmonton, June 2003.

Learning the Motion Semantics of Verbs

Learning the Abstract Motion Semantics of Verbs from Captioned Videos
S. Mathe, S. Dickinson, S. Stevenson, and A. Fazly,
Proceedings, 3rd International Workshop on Semantic Learning and Applications in Multimedia (SLAM), Anchorage, Alaska, June 27, 2008.

Learning Decompositional Models from Examples

Learning Hierarchical Shape Models from Examples
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), St. Augustine, FL, November, 2005.

Graph Algorithms in Computer Vision

My interest in generic object recognition led to various abstract shape representations -- structural models with primitives and spatial relations and often organized in a hierarchy or a scale space. I quickly discovered that graphs provide a powerful abstraction for representing shape structures in computer vision. Consequently, the problems of shape indexing and matching (together comprising object recognition), can be formulated as graph indexing and matching problems. The graph algorithms community is a mature one, and has much to offer vision researchers working with graphs. We have worked extensively with graphs, whether directed or undirected, hierarchical or flat. Moreover, we have explored both one-to-one and many-to-many matching strategies. Below you'll find some links to our work on the convergence of graph algorithms and object recognition. A nice collection of papers on the topic can be found in a special issue of PAMI that I co-edited (with Marcello Pelillo and Ramin Zabih), which appeared in October, 2001/2002 (Volume 23, Number 10).

General Issues

Introduction to the Special Section on Graph Algorithms in Computer Vision
S. Dickinson, M. Pelillo, and R. Zabih,
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 23, Number 10, October 2001, pp 1049--1052.

Motion Segmentation as a Metric Embedding Problem

Unsupervised Motion Segmentation Using Metric Embedding of Features
Y. Osmanloglu, S. Dickinson, and A. Shokoufandeh
Proceedings, 3rd International Workshop on Similarity-Based Pattern Analysis and Recognition (SIMBAD), Copenhagen, October 2015.

Part Recovery as an Undirected Graph Covering Problems

3-D Shape Recovery using Distributed Aspect Matching
S. Dickinson, A. Pentland, and A. Rosenfeld,
IEEE Transactions on Pattern Analysis and Machine Intelligence, special issue on Interpretation of 3-D Scenes, Vol. 14, No. 2, 1992, pp 174--198.

From Volumes to Views: An Approach to 3-D Object Recognition
S. Dickinson, A. Pentland, and A. Rosenfeld,
Computer Vision and Image Understanding, special issue on CAD-based vision, Vol. 55, No. 2, March 1992, pp 130--154.

Multi-Scale Shape Matching as a Directed Acyclic Graph Matching Problem

Graph-Theoretical Methods in Computer Vision
A. Shokoufandeh and S. Dickinson,
Springer-Verlag Heidelberg Lecture Notes in Computer Science, Volume 2292, 2002, pp 148--174.

The Representation and Matching of Categorical Shape
A. Shokoufandeh, L. Bretzner, D. Macrini, M.F. Demirci, C. Jonsson, and S. Dickinson,
Computer Vision and Image Understanding (CVIU), Volume 103, 2006, pp 139--154.

On the Representation and Matching of Qualitative Shape at Multiple Scales
A. Shokoufandeh, S. Dickinson, C. Jonsson, L. Bretzner, and T. Lindeberg,
Proceedings, European Conference on Computer Vision (ECCV), Copenhagen, May, 2002.

A Low-Dimensional Encoding of Hierarchical Shape using Spectral Graph Theory

Indexing Hierarchical Structures using Graph Spectra
A. Shokoufandeh, D. Macrini, S. Dickinson, K. Siddiqi, and S. Zucker,
IEEE Transactions on Pattern Analysis and Machine Intelligence, special issue on Syntactic and Structural pattern Recognition, Volume 27, Number 7, July 2005.

Shock Graphs and Shape Matching
K. Siddiqi, A. Shokoufandeh, S. Dickinson, and S. Zucker,
International Journal of Computer Vision, Volume 30, 1999, pp 1--24.

Visual Landmark Selection as a Graph Covering Problem

Landmark Selection for Vision-Based Navigation
P. Sala, R. Sim, A. Shokoufandeh, and S. Dickinson,
IEEE Transactions on Robotics, Vol. 22, No. 2, April 2006, pp 334--349.

Landmark Selection for Vision-Based Navigation
P. Sala, R. Sim, A. Shokoufandeh, and S. Dickinson,
Proceedings, International Conference on Intelligent Robots and Systems (IROS), Sendai, Japan, September/October, 2004.

Hierarchical Shape Indexing as a Graph Indexing Problem

Indexing Hierarchical Structures using Graph Spectra
A. Shokoufandeh, D. Macrini, S. Dickinson, K. Siddiqi, and S. Zucker,
IEEE Transactions on Pattern Analysis and Machine Intelligence, special issue on Syntactic and Structural pattern Recognition, Volume 27, Number 7, July 2005.

Indexing using a Spectral Encoding of Topological Structure
A. Shokoufandeh, S. Dickinson, K. Siddiqi, and S. Zucker,
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Fort Collins, CO, June 1999, pp 491--497.

Hierarchical Shape Matching as a Tree Matching Problem

Shock Graphs and Shape Matching
K. Siddiqi, A. Shokoufandeh, S. Dickinson, and S. Zucker,
International Journal of Computer Vision, Volume 30, 1999, pp 1--24.

Shock Graphs and Shape Matching
K. Siddiqi, A. Shokoufandeh, S. Dickinson, and S. Zucker,
Proceedings, IEEE International Conference on Computer Vision (ICCV), Bombay, January 4--7, 1998, pp 222--229.

Hierarchical Shape Matching as a Directed Acyclic Graph Matching Problem

The Representation and Matching of Categorical Shape
A. Shokoufandeh, L. Bretzner, D. Macrini, M.F. Demirci, C. Jonsson, and S. Dickinson,
Computer Vision and Image Understanding (CVIU), Volume 103, 2006, pp 139--154.

On the Representation and Matching of Qualitative Shape at Multiple Scales
A. Shokoufandeh, S. Dickinson, C. Jonsson, L. Bretzner, and T. Lindeberg,
Proceedings, European Conference on Computer Vision (ECCV), Copenhagen, May, 2002.

View-Based Object Recognition Using Saliency Maps
A. Shokoufandeh, I. Marsic, and S. Dickinson,
Image and Vision Computing, Volume 17, 1999, pp 445--460.

View-Based Object Matching
A. Shokoufandeh, I. Marsic, and S. Dickinson,
Proceedings, IEEE International Conference on Computer Vision (ICCV), Bombay, January 4--7, 1998, pp 588--595.

Many-to-Many Graph Matching

Many-to-Many Graph Matching
F. Demirci, A. Shokoufandeh, and S. Dickinson
In: Katsushi Ikeuchi (Ed.). Computer Vision: A Reference Guide, Springer, New York, NY, 2014, pp 472-477.

Skeletal Shape Abstraction from Examples
F. Demirci, A. Shokoufandeh, and S. Dickinson,
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 31, No. 5, May 2009, pp 944--952.

Object Recognition as Many-to-Many Feature Matching
F. Demirci, A. Shokoufandeh, Y. Keselman, L. Bretzner, and S. Dickinson,
International Journal of Computer Vision, Volume 69, Number 2, August, 2006, pp 203--222.

Many-to-Many Feature Matching in Object Recognition
A. Shokoufandeh, Y. Keselman, F. Demirci, D. Macrini, and S. Dickinson,
in H. Christensen and H.-H. Nagel (eds.), Cognitive Vision Systems: Sampling the Spectrum of Approaches, Springer-Verlag, Berlin, 2006, pp 107--125.

Object Categorization and the Need for Many-to-Many Matching
S. Dickinson, A. Shokoufandeh, Y. Keselman, F. Demirci, and D. Macrini,
Proceedings (invited paper), 27th DAGM - The Annual meeting of the German Association for Pattern Recognition, Vienna, Austria, August, 2005.

Many-to-Many Feature Matching Using Spherical Coding of Directed Graphs
M. Demirci, A. Shokoufandeh, S. Dickinson, Y. Keselman, and L. Bretzner,
Proceedings, European Conference on Computer Vision (ECCV), Prague, May, 2004.

Many-to-Many Graph Matching via Metric Embedding
Y. Keselman, A. Shokoufandeh, M. Demirci, and S. Dickinson,
Proceedings, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Madison, WI, June 2003.

Many-to-Many Matching of Scale-Space Hierarchies using Metric Embedding
M. Demirci, A. Shokoufandeh, Y. Keselman, S. Dickinson, and L. Bretzner,
Proceedings, Scale-Space '03, Skye, UK, June 10-12, 2003.

A Unified Approach to Hierarchical Shape Indexing and Matching using Spectral Graph Theory

3-D Model Retrieval Using Medial Surfaces
K. Siddiqi, J. Zhang, D. Macrini, S. Dickinson, and A. Shokoufandeh,
in: Medial Representations: Mathematics, Algorithms and Applications,
K. Siddiqi and S. Pizer (eds.), Kluwer, Boston, 2008, pp 309--326.

Retrieving Articulated 3-D Models Using Medial Surfaces
K. Siddiqi, J. Zhang, D. Macrini, A. Shokoufandeh, S. Bioux, and S. Dickinson
Machine Vision and Applications (MVA), Vol. 19, No. 4, July, 2008, pp 261--275.

Retrieving Articulated 3-D Models Using Medial Surfaces and their Graph Spectra
J. Zhang, K. Siddiqi, D. Macrini, A. Shokoufandeh, and S. Dickinson,
Proceedings, International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), St. Augustine, FL, November, 2005.

A Unified Framework for Indexing and Matching Hierarchical Shape Structures
A. Shokoufandeh and S. Dickinson,
Proceedings, 4th International Workshop on Visual Form, Capri, Italy, May 28--30, 2001.

View-Based 3-D Object Recognition as a Graph Indexing/Matching Problem

View-Based 3-D Object Recognition using Shock Graphs
D. Macrini, A. Shokoufandeh, S. Dickinson, K. Siddiqi, and S. Zucker,
Proceedings, International Conference on Pattern Recognition (ICPR), Quebec, August, 2002.

Spectral Methods for View-Based 3-D Object Recognition using Silhouettes
D. Macrini, A. Shokoufandeh, S. Dickinson, K. Siddiqi, and S. Zucker,
Proceedings, Joint IAPR International Workshop on Syntactical and Structural Pattern Recognition, Windsor, ON, August, 2002.

Shape Matching as a Bipartite Graph Matching Problem

Applications of Bipartite Matching to Problems in Object Recognition
A. Shokoufandeh and S. Dickinson,
Proceedings, ICCV Workshop on Graph Algorithms and Computer Vision, September 21, 1999.

Shape Matching as a Graph Embedding Problem

Object Recognition as Many-to-Many Feature Matching
F. Demirci, A. Shokoufandeh, Y. Keselman, L. Bretzner, and S. Dickinson,
International Journal of Computer Vision, Volume 69, Number 2, August, 2006, pp 203--222.

Learning Hierarchical Shape Models from Examples
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), St. Augustine, FL, November, 2005.

Many-to-Many Feature Matching Using Spherical Coding of Directed Graphs
M. Demirci, A. Shokoufandeh, S. Dickinson, Y. Keselman, and L. Bretzner,
Proceedings, European Conference on Computer Vision (ECCV), Prague, May, 2004.

Many-to-Many Graph Matching via Metric Embedding
Y. Keselman, A. Shokoufandeh, M. Demirci, and S. Dickinson,
Proceedings, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Madison, WI, June 2003.

Many-to-Many Matching of Scale-Space Hierarchies using Metric Embedding
M. Demirci, A. Shokoufandeh, Y. Keselman, S. Dickinson, and L. Bretzner,
Proceedings, Scale-Space '03, Skye, UK, June 10-12, 2003.

Perceptual Grouping as a Graph Cut Problem

A Framework for Symmetric Part Detection in Cluttered Scenes
T. Lee, S. Fidler, A. Levinshtein, C. Sminchisescu, and S. Dickinson
Symmetry, Volume 7, 2015, pp 1333-1351.

A Framework for Symmetric Part Detection in Cluttered Scenes
T. Lee, S. Fidler, A. Levinshtein, C. Sminchisescu, and S. Dickinson
Symmetry, Volume 7, 2015, pp 1333-1351.

Learning to Combine Mid-level Cues for Object Proposal Generation
T. Lee, S. Fidler, and S. Dickinson
Proceedings, International Conference on Computer Vision (ICCV), Santiago, Chile, December, 2015.

Multi-Cue Mid-Level Grouping
T. Lee, S. Fidler, and S. Dickinson
Proceedings, Asian Conference on Computer Vision (ACCV), Singapore, November 2014.

Optimal Image and Video Closure by Superpixel Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
International Journal of Computer Vision (IJCV), Volume 100, Number 1, 2012, pp 99--119.

Spatiotemporal Closure
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, Asian Conference on Computer Vision (ACCV), Queenstown, New Zealand, November 2010.

Optimal Contour Closure by Superpixel Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, European Conference on Computer Vision (ECCV), Crete, Greece, September 2010.

Segmentation and Perceptual Grouping

Part abstraction first requires the segmentation and grouping of features that belong to an object. I have looked at the use of weak shape priors in the generation of superpixels, a form of region oversegmentation. On the perceptual grouping side, I have looked at the use of intermediate-level shape priors for perceptual grouping and abstraction of image contours and superpixels for both static and dynamic scenes.

Region Segmentation

Learning to Combine Mid-level Cues for Object Proposal Generation
T. Lee, S. Fidler, and S. Dickinson
Proceedings, International Conference on Computer Vision (ICCV), Santiago, Chile, December, 2015.

Multi-Cue Mid-Level Grouping
T. Lee, S. Fidler, and S. Dickinson
Proceedings, Asian Conference on Computer Vision (ACCV), Singapore, November 2014.

Optimal Image and Video Closure by Superpixel Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
International Journal of Computer Vision (IJCV), Volume 100, Number 1, 2012, pp 99--119.

Optimal Contour Closure by Superpixel Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, European Conference on Computer Vision (ECCV), Crete, Greece, September 2010.

TurboPixels: Fast Superpixels using Geometric Flows
A. Levinshtein, A. Stere, K. Kutulakos, D. Fleet, S. Dickinson, and K. Siddiqi,
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 31, No. 12, December 2009, pp 2290--2297.

Perceptual Grouping

AMAT: Medial Axis Transform for Natural Images
S. Tsogkas and S. Dickinson
Proceedings, International Conference on Computer Vision (ICCV), Venice, Italy, October, 2017.
Code

2017 ICCV Challenge: Detecting Symmetry in the Wild
C. Funk, S. Lee, M. Oswald, S. Tsogkas, W. Shen, A. Cohen, S. Dickinson and Y. Liu
Proceedings, International Conference on Computer Vision (ICCV) Workshop on Detecting Symmetry in the Wild, Venice, Italy, October 28, 2017.

3-D Volumetric Shape Abstraction from a Single 2-D Image
P. Sala and S. Dickinson
Proceedings, 5th International IEEE Workshop on 3D Representation and Recognition (3dRR-15), Santiago, Chile, December 17, 2015.

Learning to Combine Mid-level Cues for Object Proposal Generation
T. Lee, S. Fidler, and S. Dickinson
Proceedings, International Conference on Computer Vision (ICCV), Santiago, Chile, December, 2015.

Unsupervised Motion Segmentation Using Metric Embedding of Features
Y. Osmanloglu, S. Dickinson, and A. Shokoufandeh
Proceedings, 3rd International Workshop on Similarity-Based Pattern Analysis and Recognition (SIMBAD), Copenhagen, October 2015.

Multi-Cue Mid-Level Grouping
T. Lee, S. Fidler, and S. Dickinson
Proceedings, Asian Conference on Computer Vision (ACCV), Singapore, November 2014.

Detecting Curved Symmetric Parts using a Deformable Disc Model
T. Lee, S. Fidler, and S. Dickinson
Proceedings, International Conference on Computer Vision (ICCV), Sydney, Australia, December 2013.

Multiscale Symmetric Part Detection and Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson
International Journal of Computer Vision (IJCV), Volume 104, Number 2, 2013, pp 117--134.

The Role of Mid-Level Shape Priors in Perceptual Grouping and Image Abstraction
S. Dickinson, A. Levinshtein, P. Sala, and C. Sminchisescu
In Shape Perception in Human and Computer Vision: An Interdisciplinary Perspective, S. Dickinson and Z. Pizlo (Eds.), Springer Verlag, in press.

Perceptual Grouping using Superpixels
S. Dickinson, A. Levinshtein, and C. Sminshisescu,
Invited (plenary talk) paper, Proceedings, 4th Mexican Conference on Pattern Recognition (MCPR), Huatulco, Mexico, June 2012.

Optimal Image and Video Closure by Superpixel Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
International Journal of Computer Vision (IJCV), Volume 100, Number 1, 2012, pp 99--119.

Superedge Grouping for Object Localization by Combining Appearance and Shape Information
Z. Zhang, S. Fidler, J. Waggoner, Y. Cao, S. Dickinson, J. Siskind, and S. Wang,
Proceedings, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, June 2012.

Spatiotemporal Contour Grouping using Abstract Part Models
P. Sala and S. Dickinson,
Proceedings, Asian Conference on Computer Vision (ACCV), Queenstown, New Zealand, November 2010.

Spatiotemporal Closure
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, Asian Conference on Computer Vision (ACCV), Queenstown, New Zealand, November 2010.

Contour Grouping and Abstraction Using Simple Part Models
P. Sala and S. Dickinson,
Proceedings, European Conference on Computer Vision (ECCV), Crete, Greece, September 2010.

Optimal Contour Closure by Superpixel Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, European Conference on Computer Vision (ECCV), Crete, Greece, September 2010.

Multiscale Symmetric Part Detection and Grouping
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Proceedings, International Conference on Computer Vision (ICCV), Kyoto, Japan, September 2009.

Model-Based Perceptual Grouping and Shape Abstraction
P. Sala and S. Dickinson,
Proceedings, Sixth IEEE Computer Society Workshop on Perceptual Organization in Computer Vision (POCV), Anchorage, Alaska, June 23, 2008.

Qualitative 3D Surface Reconstruction from Images
A. Levinshtein, C. Sminchisescu, and S. Dickinson,
Snowbird Learning Workshop, Snowbird, Utah, April 2008.


Page created: Dec 1, 2000      
Last modified: Nov 1, 2018
Maintained by: Sven Dickinson