Larry S. Davis

Larry S. Davis is a Professor in the Institute for Advanced Computer Studies and the Department of Computer Science. He is affiliated with the Computer Vision Laboratory of the Center for Automation Research, for which he served as the head from 1981-1986.  He has been the Chair of the Department of Computer Science since 1999.

COURSE MATERIALS

  1. Data structures . This page contains the syllabus for CMSC 420, a senior level course on data structures, project descriptions and pointers to pdf files that contain the viewgraphs used for the course.
  2. Computer Vision . This is a senior level introductory course on computer vision. This page contains the course syllabus, presentation materials and project descriptions.

Our sponsors:

RESEARCH STAFF

Research Scientists

Current Ph. D. Students

Alumni

 

 

(MOSTLY RECENT) PAPERS

 

Background subtraction

 

 

Human detection and appearance matching

  • Zhe Lin and Larry S. Davis, "A Pose-Invariant Descriptor for Human Detection and Segmentation," 10th European Conference on Computer Vision (ECCV 2008), Marseille, France, 2008. (pdf)
  • Zhe Lin and Larry S. Davis, "Learning Pairwise Dissimilarity Profiles for Appearance Recognition in Visual Surveillance," 4th International Symposium on Visual Computing (ISVC 2008), Las Vegas, Nevada, 2008, (Best Paper Award). (pdf)
  • Wael Abd-Almageed and Larry Davis, Human Detection using Iterative Feature Selection and Logistic Principal Component Analysis,” International Conference Robotics and Automation, 2008
  • W. Abd-Almageed, M. Hussein, M. Abdelkader and L. Davis, Real-Time Human Detection and Tracking from Mobile Vehicles,” International Conference on Intelligent Transportation Systems, 2007
  • W. Abd-Almageed and L. Davis, "Robust Appearance Modeling for Pedestrain and Vehicle Tracking," Springer's Lecture Notes in Computer Science, 2007 (4122).
  • Zhe Lin, Larry S. Davis, David Doermann, Daniel DeMenthon, "Hierarchical Part-Template Matching for Human Detection and Segmentation," IEEE International Conference on Computer Vision (ICCV 2007), Rio de Janeiro, Brazil, 2007.pdf
  • Zhe Lin, Larry S. Davis, David Doermann, Daniel DeMenthon, "An Interactive Approach to Pose-Assisted and Appearance-based Segmentation of Humans," ICCV Workshop on Interactive Computer Vision (ICV 2007), Rio de Janeiro, Brazil, 2007.pdf
  • Zhe Lin, Larry S. Davis, David Doermann, Daniel DeMenthon, "Simultaneous Appearance Modeling and Segmentation for Matching People under Occlusion," Asian Conference on Computer Vision (ACCV 2007), Tokyo, Japan, 2007.pdf
  • V. S. N. Prasad, L. S. Davis, S. D. Tran and A. Elgammal, Edge Affinities for Pose-Contour Matching. J. Computer Vision and Image Understanding (CVIU), 104(1): 36-47, Oct. 2006, (pdf)
  • Y. Yacoob and L. Davis, Detection and Analysis of Hair, IEEE PAMI, (28)7,2006, 1164-1169.
  • Mohamed Hussein, Wael Abd-Almageed, Yang Ran and Larry Davis, “A Real-Time System for Human Detection, Tracking and Verification from a Moving Camera,” IEEE International Conference on Computer Vision Systems, 2006.
  • Vinay D. Shet, Jan Neumann, Visvanathan Ramesh and Larry S. Davis, Bilattice based Logical Reasoning for Human Detection, IEEE Computer Vision and Pattern Recognition (CVPR), 2007, Minneapolis, MN, USA [pdf]
  • Yang Ran, Qinfen Zheng, Isaac Weiss and Larry Davis Wael Abd Almageed, Pedestrian Classification from Moving Platforms using Cyclic Motion Patterns,” IEEE International Conference on Image Processing, 2005.
  • Y. Yacoob and L. Davis, Smiling Faces are Better for Face Recognition. in International Conference on Face Recognition and Gesture Analysis, Washington-DC, 2002, 59-64
  • I.Haritaoglu, D.Harwood, and L.Davis, Ghost: A Human Body Part Labeling System Using Silhouettes  [PS],[PDF]  Fourteenth International Conference on Pattern Recognition, Brisbane, August 1998.
  • I.Haritaoglu, D.Harwood, and L.Davis.W4S: A Real Time System for Detecting and Tracking People in 2.5 D  [PS],[PDF]  Fifth European Conference on Computer Vision, Freiburg, June 1998

 

Tracking

 

Camera networks

 

  • Hazem El-Alfy, David Jacobs and Larry Davis, “Multi-Scale Video Cropping,” in Proceedings of the 15th ACM International Conference on Multimedia (MM’07), pp. 97-106, Augsburg, Bavaria, Germany, September 23–28, 2007. pdf
  • Ryan Farrell, David Doermann, Larry Davis, "Learning Higher-order Transition Models in Medium-scale Camera Networks", OMNIVIS 2007.   
  • Abhinav Gupta, Anurag Mittal and Larry S. Davis, COST*: An Approach for Camera Selection and Multi-Object Inference Ordering in Dynamic Scenes, In ICCV 2007 (PDF)
  • Anurag Mittal and Larry S. Davis.  Visibility Analysis and Sensor Planning in Dynamic Environments.  In 8th European Conference on Computer Vision (ECCV), Prague, Czech Republic, May, 2004.
  • Ser-Nam Lim, Larry Davis, Anurag Mittal, “Task Scheduling in Large Camera Network”, ACCV 2007, Tokyo, Japan.(pdf)
  • Ser-Nam Lim, Larry S. Davis, Anurag Mittal, "Constructing Task Visibility Intervals for a Surveillance System", ACM Multimedia System Journal, Special Issue on Multimedia Surveillance System, Vol. 12, No. 3, Dec 2006. (pdf)
  • Ser-Nam Lim, Anurag Mittal, Larry Davis, "Constructing Task Visibility Intervals for Surveillance Systems", VSSN 2005, Nov 11-12, Singapore. (pdf)
  • Ser-Nam Lim, Ahmed Elgammal and Larry S. Davis, "Image-based Pan-tilt Camera Control in a Multi-Camera Surveillance Environment", IEEE ICME 2003, Special Session on Visual Surveillance, Jul 6-9, Baltimore, Maryland. (pdf)

 

 

Human movement modeling

 

  • S. N. Vitaladevuni, V. Kellokumpu and L. S. Davis, "Action Recognition using Ballistic Dynamics; accepted at Conf. on Computer Vision and Pattern Rec. (CVPR) 2008 (PDF).
  • V. S. N. Prasad, V. Kellokumpu and L. S. Davis, "Ballistic Hand Movements", Proc. Conf. Articulated Motion and Deformable Objects (AMDO) 2006, July 2006.(PDF)
  • V. D. Shet, V. S. N. Prasad, A. Elgammal, Y. Yacoob and L. S. Davis, "Multi-cue Exemplar-based Nonparametric Model for Gesture Recognition", in Proc. Indian Conf. Computer Vision, Graphics and Image Processing (ICVGIP) 2004, Dec. 2004.(PDF)
  • Ahmed Elgammal, Vinay D. Shet, Yaser Yacoob and Larry Davis, Learning Dynamics for Exemplar based Gesture Recognition, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) Wisconsin 2003 [pdf]
  • A. Sepheri, Y. Yacoob and L. Davis, Employing the Hand as an Interface Device, Journal of Multimedia, (1)7, 2006, 18-29

 

3D Human Motion Capture

 

  • Abhinav Gupta, Trista Chen, Francine Chen, Don Kimber and Larry S. Davis, Context and Observation Driven Latent Variable Model for Human Pose Estimation, Accepted in CVPR 2008, (PDF)
  • Abhinav Gupta, Anurag Mittal and Larry S. Davis, Constraint Integration for Multiview Pose Estimation of Humans with Self-Occlusions, 3DPVT 2006 (PDF)
  • Anurag Mittal, Liang Zhao and Larry Davis., Human Body pose Estimation by Shape Analysis of Silhouettes.   IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Orlando, Florida, July 2003.
  • T. Horparasert, I. Haritaoglu, D. Harwood, L. Davis, C. Wren, A. Pentland  Real-time 3D Motion Capture. [PS],[PDF]  Second Workshop on Perceptual Interfaces, San Francisco, November 1998
  • K. Ebihara, L.S. Davis, J. Kurumisawa, T. Horprasert, R.I. Haritaoglu, T. Sakaguchi and J. Ohya, Shall We Dance? -Real Time 3D Control of a CG Puppet, SIGGRAPH98 Conference Abstract and Applications, Orlando, July 1998.
  • D. M. Gavrila and L. S. Davis, 3D Model-based Tracking of Humans in Action: a Multi-view Approach, Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 73-80, San Francisco, U.S.A., 1996.

 

Object/Action Recognition

 

  • Abhinav Gupta and Larry S. Davis, Objects in Action: An Approach for Combining Action Understanding and Object Perception, In CVPR 2007 (PDF)
  • Abhinav Gupta, Jianbo Shi and Larry S. Davis, A "Shape Aware" Model for semi-supervised Learning of Objects and its Context, To Appear in NIPS 2008
  • Abhinav Gupta and Larry S. Davis, Beyond nouns: Exploiting prepositions and comparative adjectives for learning visual classifiers, Accepted in ECCV 2008 (pdf)

 

 

Event modeling and recognition

 

  • Son Tran and Larry Davis, Visual Event Modeling and Recognition using Markov Logic Networks ECCV’08. 2008. (pdf )
  • Vinay D. Shet, David Harwood and Larry S. Davis, Multivalued Default Logic for Identity Maintenance in Visual Surveillance, 9th European Conference on Computer Vision (ECCV), 2006, Graz, Austria [pdf]
  • Vinay D. Shet, David Harwood and Larry S. Davis, Top-Down, Bottom-up Multivalued Default Reasoning for Identity Maintenance, 4th ACM International Workshop on Video Surveillance & Sensor Networks (VSSN) in conjunction with ACM Multimedia Santa Barbara, CA, USA, 2006 [pdf]
  • Vinay D. Shet, David Harwood and Larry S. Davis, VidMAP: Video Monitoring of Activity with Prolog, IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS), Como, Italy, September 2005 [pdf]
  • Nagia Ghanem, Daniel DeMenthon, David Doermann and Larry Davis, Representation and Recognition of Events in Surveillance Video Using Petri Nets.. Second IEEE Workshop on Event Mining 2004, CVPR2004

 

 

Miscellaneous