NEW: I finished my Ph.D. in May 2009 at the University of Maryland at College Park. Currently, I am working at Adobe's Advaced Technology Labs at
San Jose, California.
Office: 3364 A.V.Williams Bldg., Dept. of ECE, Univ. of Maryland, College Park, MD 20742 Home: 6100 Westchester Park Dr., Apt. 512, College Park,
MD, 20740 E-mail: zhelin AT umiacs.umd.edu
Overall GPA: 4.0/4.0, PhD Qualifying Written and Oral Exam (Pass, May 2006)
PhD Defense (Pass, March 2009), Graduation/Degree (May 2009)
Research
Areas of Interests
Object Detection, Recognition and Categorization
Pattern Classification and Machine Learning
Feature Extraction, Image and Object Segmentation
Image/Video Retrieval, Tracking and Motion Analysis
Vision-based Robot Localization and Navigation
Current Research
Human Action Localization and Recognition
Developed a fast action recognition system achieving state of the art performance on two public datasets. (ongoing work)
Human Detection and Pose Segmentation
Introduced a pose-adaptive descriptor for simultaneous human detection and pose segmentation. (see our ECCV 2008 paper for details)
Appearance Matching and Recognition
Developed pairwise discriminative learning-based techniques to appearance-based person recognition to better handle the scalability
problem, i.e. recognition of large number of categories. Also developed algorithms for matching appearances under occlusion. The approach
is tested on 61 person Honeywell appearance dataset, and 50 person multiview, multipose Keck lab (UMD) dataset.
Part of this work is delivered to Panasonic Inc. Princeton, NJ
Multiple Occluded Human Detection, Segmentation and Tracking
Developed algorithms for detecting and segmenting humans under occlusion. The detection
is performed by a part-template shape matching method and the segmentation is done by
pose-assisted appearance-based segmentation which simultaneously estimates human poses and
segmentation. We are currently applying these approaches to multi-target tracking system for
visual surveillance applications.
"Modeling shape, appearance and motion for human movement analysis," PhD Thesis, 2009.3.
"Robust local invariant features for real-time object recognition," Master's Thesis, 2004.6.
"Development of robo-cup soccer robot vision system," Bachelor's Thesis, 2002.6.
Journal
Zhe Lin, Gang Hua, and Larry S. Davis, "Learning Multiple Instance Features with Shared Descriptor Representation for Part-based Object Detection," International Journal of
Computer Vision (IJCV), Nov. 2009, submitted for review.
Zhuolin Jiang, Zhe Lin, and Larry S. Davis, "Recognizing Human Actions by Learning and Matching Shape-Motion Prototype Trees," IEEE Transactions on Pattern
Analysis and Machine Intelligence (TPAMI), Oct. 2009, submitted for review.
Zhe Lin and Larry S. Davis, "Shape-based Human Detection and Segmentation via Probabilistic Hierarchical Part-Template Matching," IEEE Transactions on Pattern
Analysis and Machine Intelligence (TPAMI), Oct. 2008, under minor revision.
Zhe Lin and In So Kweon, "Robust invariant features for object recognition, pose estimation and topological
navigation," International Journal on Human Friendly Welfare Robotic Systems (IJHWRS), Volume 6, No. 1, Mar. 2005.
Conference
Zhe Lin, Zhuolin Jiang, and Larry S. Davis, "Recognizing Actions by Shape-Motion Prototype Trees," IEEE International Conference on Computer Vision (ICCV 2009),
Kyoto, Japan. (poseter presentation)pdf
A project page with Keck gesture dataset and a demo video: UMD Keck Gesture Dataset and A Demo Video
Zhe Lin, Gang Hua, and Larry S. Davis, "Multiple Instance Feature for Robust Part-based Object Detection," IEEE Conference on Computer Vision and Pattern Recognition (CVPR
2009), Miami, Florida, 2009. (poster presentation)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. (oral presentation), Best Paper Award. pdf
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. (poster presentation)pdf
Source codes are available now! Please visit PidUMD Human Detection C++ Codes
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. (oral presentation)pdf
Annotated 404 pedestrian silhouettes (selected from INRIA person dataset): download
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. (poster presentation)pdf
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. (poster presentation)pdf
Part-template-tree model: download
Dataset (200 frames from Caviar data and 200 frames from Munich Airport data) with
annotation: download
Son Tran, Zhe Lin, David Harwood, Larry Davis, "UMD_VDT, an Integration of Detection and Tracking Methods for Multiple Human Tracking,"
Classification of Events, Activities and Relationships Workshop (CLEAR 2007). Came out the best in 2D person tracking. pdf
Zhe Lin, Sungho Kim, In So Kweon, "Object recognition and indoor topological navigation using robust invariant
features," 2005 IEEE/RSJ Conference on Intelligent Robots and Systems (IROS 2005), Edmonston, Canada, 2005. (oral presentation)pdf
Zhe Lin, Sungho Kim, In So Kweon, "Robust invariant features for object recognition and mobile robot navigation," 2005 IAPR
Conference on Machine Vision Applications (MVA 2005), Tsukuba Science City, Japan, 2005. (poster presentation)pdf
Zhe Lin and In So Kweon, "Robust invariant feature extraction for object recognition and natural landmark based
autonomous navigation," First International Conference on Ubiquitous and Intelligent Robot (ICUIR 2004), The Korea
International Robot Week, COEX, Seoul, Nov. 2004. (poster presentation)
Sungho Kim, Zhe Lin, Wangheon Lee and In So Kweon, "3D object recognition system based on the robust properties
of human visual system," First International Conference on Ubiquitous and Intelligent Robot (ICUIR 2004), The Korea
International Robot Week, COEX, Seoul, Nov. 2004. (poster presentation)
Zhe Lin and In So Kweon, "A novel scale-invariant feature for object recognition and mobile robot navigation,"
Proceedings of the 11th IEEE International Conference on Mechatronics and Machine Vision in Practice
(M2VIP 2004), Macau, 2005. (oral presentation)
