Publications

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted or reproduced in any way, in whole or in part, without the explicit permission of the copyright holder.


Refereed Journal Publications

Deep insights into convolutional architectures for video recognition (with C. Feichtenhofer, A. Pinz and A. Zisserman). International Journal of Computer Vision 128, 430-437, 2020. link

Dynamic scene recognition with complementary spatiotemporal features (with C. Feichtenhofer and A. Pinz). IEEE Transactions on Pattern Analysis and Machine Intelligence 38 (12), 2389-2401, 2016. pdf

Spacetime stereo and 3D flow via binocular spatiotemporal orientation analysis (with M. Sizintsev). IEEE Transactions on Pattern Analysis and Machine Intelligence 36 (11), 2241-2254, 2014. pdf

The applicability of spatiotemporal oriented energy features to region tracking (with K. Cannons). IEEE Transactions on Pattern Analysis and Machine Intelligence 36 (4), 784-796, 2014. pdf

Action spotting and recognition based on a spatiotemporal orientation analysis (with K. Derpanis, M. Sizintsev and K. Cannons). IEEE Transactions on Pattern Analysis and Machine Intelligence 35 (3), 527-540, 2013. pdf

Spacetime texture representation and recognition based on a spatiotemporal orientation analysis (with K. Derpanis). IEEE Transactions on Pattern Analysis and Machine Intelligence 34 (6), 1193-1205, 2012. pdf

Spatiotemporal stereo and scene flow via stequel matching (with M. Sizintsev). IEEE Transactions on Pattern Analysis and Machine Intelligence 34 (6), 1206-1219, 2012. pdf

The structure of multiplicative motions in natural imagery (with K. Derpanis). IEEE Transactions on Pattern Analysis and Machine Intelligence 32 (7), 1310-1316, 2010. pdf

Course-to-fine stereo vision with accurate 3D boundaries (with M. Sizintsev). Image and Vision Computing 28, 352-366, 2010. pdf

Detecting motion patterns via direction maps with application to surveillance (with J. Gryn and J. Tsotsos). Computer Vision and Image Understanding 113 (2), 291-307, 2009. pdf

Definition and recovery of kinematic features for recognition of American sign language movements (with K. Derpanis and J. Tsotsos). Image and Vision Computing 26 (12), 1650-1662, 2008. pdf

Selectivity for speed gradients in human area {MT/V5} (with J. C. Martinez-Trujillo, J. K. Tsotsos, E. Simine, M. Pomplun, S. Treue, H. J. Heinze and J. M. Hopf). Neuroreport 16 (5), 435-438, 2005.

A stereo confidence metric using single view imagery with comparison to five alternative approaches (with G. Egnal and M. Mintz). Image and Vision Computing 22, 943-957, 2004.

Detecting binocular half-occlusions: Empirical comparisons of five approaches (with G. Egnal). IEEE Transactions on Pattern Analysis and Machine Intelligence 24 (8), 1127-1133, 2002. pdf

Aerial video surveillance and exploitation (with R. Kumar, H. Sawhney, S. Samasekera, S. Hsu, H. Tao, Y. Guo, K. Hanna, A. Pope, D. Hirvonen, M. Hansen and P. Burt). Proceedings of the IEEE 89 (10), 1518-1539, 2001.

Recovering estimates of fluid flow from image sequence data (with M. Amabile, A. Lanzillotto and T. Leu). Computer Vision and Image Understanding 80, 246-266, 2000. pdf

Automated iris recognition: An emerging biometric technology. Proceedings of the IEEE 85 (9), 1348-1363, 1997. Awarded IEEE Donald G. Fink Prize Paper Award. pdf

A machine vision system for iris recognition (with J. Asmuth, G. Green, S. Hsu, R. Kolczynski, J. Matey and S. McBride). Machine Vision and Applications 9, 1-8, 1996.

Direct recovery of three-dimensional scene geometry from binocular stereo disparity. IEEE Transactions on Pattern Analysis and Machine Intelligence 13 (8), 721-735, 1991. pdf

Refereed Conference Publications

Graph neural net using analytical graph filters and topological optimization (with W. Su, G. Cheung and C.-W. Lin). In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020.

On diverse asynchronous activity anticipation (with H. Zhao). In In Proceedings of the European Conference on Computer Vision (ECCV), 2020.

Spatiotemporal feature residual propgation for video prediction (with H. Zhao). In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2019

A new large scale dynamic texture dataset with application to convnet understanding (with I. Hadji). In Proceedings of the European Conference on Computer Vision (ECCV), 2018. pdf

What have we learned from deep represenations for action recognition? (with C. Feichtenhofer, A. Pinz and A. Zisserman). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. pdf

A spatiotemporal oriented energy network for dynamic texture recognition (with I. Hadji). In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017. pdf

Spatiotemporal multiplier networks for video action recognition (with C. Feichtenhofer and A. Pinz). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. pdf

Temporal residual networks for dynamic scene recognition (with C. Feichtenhofer and A. Pinz). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. pdf

Spatiotemporal residual networks for video action recognition (with C. Feichtenhofer and A. Pinz). In Proceedings of the Conference on Neural Information Processing Systems (NIPS), 2016. pdf

Dynamically encoded actions based on spacetime saliency (with C. Feichtenhofer and A. Pinz). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. pdf

Bags of spacetime energies for dynamic scene recognition (with C. Feichtenhofer and A. Pinz). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. pdf

Egomotion estimation using binocular spatiotemporal oriented energy (with H. Zhong). In Proceedings of the British Machine Vision Conference (BMVC), 2013. pdf

Spacetime forests with complementary features for dynamic scene recognition (with C. Feichtenhofer and A. Pinz). In Proceedings of the British Machine Vision Conference (BMVC), 2013. pdf

Dynamic scene understanding: The role of orientation features in space and time in scene classification (with K. Derpanis, M. Lecce and K. Daniilidis). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012. pdf

Spatiotemporal Salience via Centre-Surround Comparison of Visual Spacetime Orientations (with A. Zaharescu). In Proceedings of the Asian Conference on Computer Vision (ACCV), 2012. pdf

Classification of traffic video based on a spatiotemporal orientation analysis (with K. Derpanis). In Proceedings of the IEEE Workshop on Applications of Computer Vision (WACV), 2011. pdf

Spatiotemporal oriented energies for spacetime stereo (with M. Sizintsev). In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2011. pdf

Anomalous behaviour detection using spatiotemporal oriented energies, subset inclusion histogram comparison and event-driven processing (with A. Zaharescu). In Proceedings of the European Conference on Computer Vision (ECCV), 2010. pdf

Dynamic texture recognition based on distributions of spacetime oriented structure (with K. Derpanis). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010. pdf

Efficient action spotting based on a spacetime oriented structure representation (with K. Derpanis, M. Sizintsev and K. Cannons). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2010. pdf

Visual tracking using a pixelwise spatiotemporal oriented energy representation (with K. Cannons and J. Gryn). In Proceedings of the European Conference on Computer Vision (ECCV) , 2010. pdf

Detecting spatiotemporal structure boundaries: Beyond motion discontinuities (with K. Derpanis). In Proceedings of the Asian Conference on Computer Vision (ACCV), 2009. pdf

Early spatiotemporal grouping with a distributed oriented energy representation (with K. Derpanis). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009. pdf

Spatiotemporal stereo via spatiotemporal quadric element (stequel) matching (with M. Sizintsev). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009. pdf

Spatiotemporal oriented energy features for visual tracking (with K. Cannons). In Proceedings of the Asian Computer Vision Conference (ACCV), 532-543, 2007. pdf

Efficient stereo with accurate 3-D boundaries (with M. Sizintsev). In Proceedings of the British Machine Vision Conference (BMVC), 237-246, 2006.

Detecting motion patterns via direction maps with application to surveillance (with J. Gryn and J. Tsotsos). In Proceedings of the IEEE Workshop on Applications of Computer Vision (WACV), 202-209, 2005.

Iris recognition at a distance (with C. Fancourt, L. Bogoni, J. Hanna, Y. Guo, N. Takahashi and U. Jain). In Proceedings of the IAPR Conference on Audio and Video Based Biometric Person Authentication, 1-13, 2005.

Unified target detection and tracking using motion coherence (with M. Enzweiler and R. Herpers). In Proceedings of the IEEE Workshop on Motion and Video Computing, 66-71, 2005.

Hand gesture recognition within a linguistics-based framework (with K. Derpanis and J. Tsotsos). In Proceedings of the European Conference on Computer Vision (ECCV), 282-296, 2004.

Reliable and fast eye finding in close-up images (with T. Camus). In Proceedings of the IEEE International Conference on Pattern Recognition (ICPR), 389-394, 2002. pdf

A stereo confidence metric using single view imagery (with G. Egnal and M. Mintz). In Proceedings of the International Conference on Vision Interface, 162-169, 2002. pdf

Real-time video georegistration (with B. Matei, S. Hsu, W. Lehman, D. Hirvonen, R. Kumar, W. Zhao and M. Hansen). In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), demo pages, 2001.

Video to reference alignment in the presence of sparse features and appearance change (with D. Hirvonen, B. Matei and S. Hsu). In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 366-373, 2001.

Video georegistration: Algorithm and quantitative evaluation (with D. Hirvonen, S. Hsu, R. Kumar, W. Lehman, B. Matei and W. Zhao). In Proceedings of IEEE International Conference on Computer Vision (ICCV), 343-350, 2001. pdf

Detecting binocular half-occlusions: Empirical comparisons of four approaches (with G. Egnal). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 466-473, 2000.

Qualitative spatiotemporal analysis using an oriented energy representation (with J. Bergen). In Proceedings of the European Conference on Computer Vision (ECCV), 768-784, 2000. gzipped PostScript

A measure of motion salience for surveillance applications. In Proceedings of the IEEE International Conference on Image Processing (ICIP), 183-187, 1998.

Physically based fluid flow recovery from image sequences (with M. Amabile, A. Lanzillotto and T. Leu). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 969-975, 1997.

Applications of x-ray micro-imaging, visualization and motion analysis techniques to fluidic microsystems (with M. Amabile, J. Dunsmuir, A. Lanzillotto and T. Leu). In Proceedings of the International Conference on Solid-State Sensors and Actuators, 123-126, 1996.

Singularities of the visual motion field: Rotation or translation. In Proceedings of the IEEE International Conference on Pattern Recognition (ICPR), 633-636, 1994.

A system for automated iris recognition (with J. Asmuth, G. Green, S. Hsu, R. Kolczynski, J. Matey and S. McBride). In Proceedings of the IEEE Workshop on Applications of Computer Vision (WACV), 121-128, 1994.

On the qualitative structure of temporally evolving visual motion fields. In Proceedings of the AAAI National Conference, 844-849, 1993. pdf

An analysis of stereo disparity for the recovery of three-dimensional scene geometry. In Proceedings of the IEEE Workshop on Interpretation of 3D Scenes, 2-8, 1989.

Refereed Presentations and Abstracts

Convolutional network approach to modelling allocentric landmark impact on target localization (with S. Salimian and J. D. Crawford). Presented by S. Salimian at Vision Sciences Society, 2018.

The contribution of binocular and monocular texture elements to depth ordering (with L. Wilcox, D. Lakra and R. Spengler). Presented by L. Wilcox at Vision Sciences Society, 2005.

A human cortical specialization for the processing of velocity gradients in moving stimuli (with J. Martinez-Trujillo, J. Hopf, S. Treue, E. Simine, H. Heinze and J. Tsotsos). Presented by J. Martinez-Trujillo at Vision Sciences Society, 2004.

Depth ordering in natural stereoscopic images: The role of monocular occlusion (with L. Wilcox and D. Lakra). Poster presented by L. Wilcox at Vision Sciences Society, 2003.

Flow experiments in MEMS (with M. Amabile, A. Lanzillotto, J. Leu and R. Samtaney). Bulletin of the American Physical Society 42 (11), 2240, 1997.

Real-time, 3-D micro-imaging, visualization and analysis of fluid transport in MEMS. (with M. Amabile, A. Lanzillotto, J. Leu and M. Sawicki) Paper presented by A. Lanzillotto at International Conference on Solid-State Sensors and Actuators, 1995.

Application of singularity theory to understanding the visual motion field. Paper presented at The International Conference on Pure and Applied Differential Geometry, 1995.

Folds and cusps of the visual motion field. Optical Society of America Technical Digest 46, 69, 1993.

Three-dimensional surface curvature from binocular stereo disparity II. Optical Society of America Technical Digest 25, 58, 1990.

Three-dimensional surface curvature from binocular stereo disparity. Optical Society of America Technical Digest 18, 62, 1989.

Human estimation of light source position. Investigative Ophthalmology and Visual Science Supplement, 29, 252, 1988.

Projective differences and three-dimensional surface discontinuities. Proceedings of the AAAI Spring Symposium, 1988.

Recovering view and world geometry from stereo disparities. Optical Society of America Technical Digest, 11, 170, 1988.

Grouping processes in texture segmentation (with J. Beck and R. Ivry). Paper presented by J. Beck at The American Psychological Association Conference, 1984.

Patents

T. Camus and R. P. Wildes, Method and apparatus for providing a robust object finder. U.S. Patent #7,599,524, 2009.

R. Kumar, S. C. Hsu, K. Hanna, S. Samarasekera, R. P. Wildes, D. J. Hirvonen, T. E Klinedinst, W. B. Lehman, B. Matei, W. Zhao and B. Levienaise-Obadia, Method and apparatus for performing geo-spatial registration of imagery. U.S. Patent #6,597,818, 2003.

R. P. Wildes and J. R. Bergen, Method and apparatus for qualitative spatiotemporal data processing. U.S. Patent #6,535,620, 2003.

R. P. Wildes, K. J. Hanna, S. C. Hsu, R. J. Kolczynski, J. R. Matey and S. E. McBride, Automated, non-invasive iris recognition system and method. U.S. Patent #5,751,836, 1998.

R. P. Wildes, J. C. Smith, K. J. Hanna, S. C. Hsu, R. J. Kolczynski, J. R. Matery and S. E. McBride, Automated, non-invasive iris recognition system and method. U.S. Patent #5,572,596, 1996.

Unrefereed Publications

What do understand about convolutional networks? (with I. Hadji). arXiv e-print, arXiv:1803:08834v1, 2018.

Review of action recognition and detection methods (with S. M. Kang). arXiv e-print, arXiv:1610.06906, 2016.

Background Image Modelling for Change Detection (with H. Gao). Technical Report CSE-2016-01, Department of Electrical Engineering and Computer Science, York University, Toronto, Ontario, 2016.

The n-Distribution Bhattacharyya Coefficient (with S. Kang). Technical Report CSE-2015-02, Department of Electrical Engineering and Computer Science, York University, Toronto, Ontario, 2015.

A Unifying Theoretical Framework for Region Tracking (with K. Cannons). Technical Report CSE-2013-04, Department of Computer Science and Engineering, York University, Toronto, Ontario, 2013.

Stereoscopic Datasets and Algorithm Evaluation for Driving Scenarios (with M. Sizintsev). Technical Report CSE-2013-06, Department of Computer Science and Engineering, York University, Toronto, Ontario, 2013.

Video-to-reference image indexing (with Vitaly Zholudev). In K. Niall (Ed.) Vision and Displays for Military and Security Applications, New York: Springer, 2010.

Spatiotemporal Stereo via Spatiotemporal Quadric Element Matching (with M. Sizintsev). Technical Report CSE-2008-04, Department of Computer Science and Engineering, York University, Toronto, Ontario, 2008.

Computational Analysis of Binocular Half-Occlusions (with M. Sizintsev). In L. Harris and M. Jenkin (Eds.) Computational Vision in Neural and Machine Systems, Cambridge, UK: Cambridge University Press, 2007.

Spatiotemporal Oriented Energy Features for Visual Tracking (with K. Cannons). Technical Report CSE-2007-02, Department of Computer Science and Engineering, York University, Toronto, Ontario, 2007.

Stereo-vision based 3D modeling of space structures (with S. Se and P. Jasiobedzki). In Proceedings of the SPIE Conference on Sensors and Systems for Space Applications , 2007.

Coarse-to-Fine Stereo Vision with Accurate 3-D Boundaries (with M. Sizintsev). Technical Report CS-2006-07, Department of Computer Science, York University, Toronto, Ontario, 2006.

Toward Video to Geospatial Reference Image Indexing (with V. Zholudev). Technical Report CS-2006-03, Department of Computer Science, York University, Toronto, Ontario, 2006.

Iris recognition. Chapter 3 in J. Wayman, A. Jain, D. Maltoni and D. Maio (Eds.) Biometric Authentication: Technologies, Systems, Evaluations and Legal Issues, London: Springer, 2005.

Computational Analysis of Binocular Half-Occlusions (with M. Sizintsev). Technical Report CS-2005-12, Department of Computer Science, York University, Toronto, Ontario, 2005.

Vision Based Gesture Recognition within a Linguistics Framework (with K. Derpanis and J. Tsotsos). Technical Report CS-2004-02, Department of Computer Science, York University, Toronto, Ontario, 2004.

Robust video georegistration (with B. Matei, S. Hsu, R. Kumar, S. Samarasekera, H. Sawhney and K. Hanna). Chapter 9 in M. Shah and R. Kumar (Eds.) Video Registration, Boston: Kluwer, 2003.

Real-time, automatic precision video georegistration (with P. Burt, M. Hansen, S. Hsu, R. Kumar, B. Lehman, B. Matei, D. Mishra, Y. Shan and W. Zhao). In Proceedings of the Association for Unmanned Vehicle Systems Symposium, 2001.

Detecting salient motion using spatiotemporal filters and optical flow (with L. Wixson). In Proceedings of the DARPA Image Understanding Workshop, 349-356, 1998.

Experiments with an algorithm for recovering fluid flow from video imagery (with M. Amabile, A. Lanzillotto and T. Leu). In Proceedings of the DARPA Image Understanding Workshop, 185-192, 1997.

Synchrotron microtomography: System design and application to fluids in small channels (with J. H. Dunsmuir, M. Zhou, B. P. Flannery, M. J. Amabile, A. M. Lanzillotto, T. Leu and R. Samtaney). In Proceedings of the SPIE Conference on Developments in X-Ray Tomography, 82-89, 1997.

An investigation of microstructure and microdynamics of fluid flow in MEMS (with M. Amabile, A. Lanzillotto and T. Leu). In Proceedings of the American Society of Mechanical Engineers Conference, 789-796, 1996.

Change Detection in Serial Mammograms for the Early Detection of Breast Cancer (with J. Asmuth, D. Hunter, D. Kopans and R. Moore). Technical Report FR-0008, National Information Display Laboratory, Princeton, New Jersey, 1996.

Automated iris recognition (with J. Asmuth, G. Green, S. Hsu, R. Kolczynski, J. Matey and S. McBride). In Proceedings of the Biometric Consortium Meeting, 101-123, 1995.

A dynamic image energy with applications (with K. Dana). In Proceedings of the ARPA Image Understanding Workshop, 1611-1618, 1994.

A qualitative analysis of the visual motion field. In Proceedings of the Stockholm Workshop on Computational Vision, 1993.

Robotics. In A. Ralston and E. Reilly (Eds.) Encyclopedia of Computer Science and Engineering, 3rd edition, New York, New York: Van Nostrand Reinhold Company, 1993.

Iris Recognition for Security Access Control (with J. Asmuth, G. Green, S. Hsu, R. Kolczynski, J. Matey and S. McBride). Technical Report FR-0001, National Information Display Laboratory, Princeton, New Jersey, 1992.

Computational vision with reference to binocular stereo vision. Chapter 11 in K. N. Leibovic (Ed.) The Science of Vision, Berlin: Springer-Verlag, 1990.

Qualitative 3D shape from stereo. In Proceedings of the SPIE Conference on Intelligent Robots and Computer Vision IX, 453-463, 1990.

Surface orientation from binocular stereo orientational disparity. In Proceedings of the SPIE Conference on Intelligent Robots and Computer Vision VIII, 309-317, 1989.

On Interpreting Stereo Disparity. Technical Report 1112, Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, Massachusetts, 1989.

Recovering material properties from sounds (with W. Richards). Chapter 25 in W. Richards (Ed.) Natural Computation, Cambridge: MIT Press, 1988.