Zhiding Yu 禹之鼎
5000 Forbes Ave, Pittsburgh, PA 15213
Email: yzhiding AT andrew.cmu.edu
I am currently a Ph.D. candidate at the Department of Electrical and Computer Engineering, Carnegie Mellon University. Before that I obtained the M.Phil. degree from the Department of Electrical and Computer Engineering, The Hong Kong University of Science and Technology. I did my computer vision research intern at Adobe in the summer of 2013.
My current research interests mainly focus on learning discriminative unary potentials in graphical models, fomulating relative relative relationships between unary potentials and pairwise potentials as well as incorporating highlevel information for scene understanding. I'm also interested in problems related to graphical density estimation / mode seeking and image segmentation.
I am the awardee of the 2009-2010/2011-2012 HKTIIT Post-Graduate Excellence Scholarships and Carnegie Institute of Technology Dean's Tuition Fellowship.
Ph.D., Electrical and Computer Eng.,
Carnegie Mellon University 2012 - Present
Advisor: Prof. Vijayakumar Bhagavatula GPA: 4.0/4.0
M.Phil., Elec. and Computer
Eng., The Hong Kong Univ. of Sci. and Tech. 2009 - 2012
Advisor: Prof. Oscar C. Au
M. Sc., Electronic Eng., The Hong
Kong Univ. of Sci. and Tech. 2008 - 2009
Advisor: Prof. Bertram E. Shi
B. Eng., Info. Eng. (Talented Student Program), South China Univ. of Tech. 2005 - 2008
Research Intern, Computer Vision Group, Adobe Systems Inc. Jun. 2013 - Aug. 2013
Mentor: Gregg Wilensky, Brian Price, Scott Cohen, Walter Chang
Research Associate, Robotics Institute,
Carnegie Mellon University Aug.
2011 - Apr. 2012
Advisor: Prof. Fernando De la Torre
Research Intern, Multimedia Lab, Shenzhen
Institutes of Adv. Tech.
Nov. 2010 - Aug. 2011
Advisor: Dr. Chunjing Xu, Prof. Jianzhuang Liu
Zhiding Yu, “Graph Embedding and Arbitrarily Shaped Clustering for Unsupervised Image Segmentation,” Master of Philosophy Thesis, HKUST, 2012. [paper]
Zhiding Yu, Oscar C. Au, Ruobing Zou, Weiyu Yu and Jing Tian, “An Adaptive Unsupervised Approach toward Pixel Clustering and Color Image Segmentation,” Pattern Recognition, 2010, 43. [paper]
Zhiding Yu, Wende Zhang and B. V. K. Vijaya Kumar, “Robust Rear-View Ground Surface Detection with Hidden State Conditional Random Field and Confidence Propagation,” submitted to IEEE International Conference on Image Processing (ICIP) 2014, Paris, France.
Zhiding Yu, Chunjing Xu, Deyu Meng et al., “Transitive Distance Clustering with K-Means Duality,” to appear in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, USA, 2014.
Wenbo Liu, Zhiding Yu, Deyu Meng, “Joint Recognition / Segmentation with Cascaded Multi-level Feature Classification and Confidence Propagation,” IEEE International Conference on Multimedia & Expo (ICME) 2013, San Jose, USA.
Zhiding Yu, Ang Li, Oscar C. Au and Chunjing Xu, “Bag of Textons for Image Segmentation via Soft Clustering and Convex Shift,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, Rhode Island, USA, 2012. [paper] [poster] (24%)
Wenxiu Sun, Oscar C. Au, Lingfeng Xu, Yujun Li, Wei Hu and Zhiding Yu, “Texture Optimization for Seamless View Synthesis Through Energy Minimization,” ACM Multimedia (ACM-MM) 2012, Nara, Japan. (30%)
Zhiding Yu, Oscar C. Au, Ketan Tang and Chunjing Xu, “Nonparametric Density Estimation on A Graph: Learning Framework, Fast Approximation and Application in Image Segmentation,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, USA, 2011. [paper] (22.5%)
Zhiding Yu, Chunjing Xu, Jianzhuang Liu, Oscar C. Au and Xiaoou Tang, “Automatic Object Segmentation from Large Scale 3D Urban Point Clouds through Manifold Embedded Mode Seeking,” ACM Multimedia (ACM-MM), Scottsdale, Arizona, USA, 2011. [paper] [poster] (30%)
Zhiding Yu, Oscar C. Au, Ketan Tang, Lingfeng Xu, Wenxiu Sun and Yuanfang Guo, “Towards Robust and Efficient Segmentation: An Approach based on Inter-Region Contour and Intra-Region Content Analysis,” IEEE International Conference on Multimedia & Expo (ICME), Barcelona, Spain, 2011. [paper] (Top 15%)
Ketan Tang, Oscar C. Au, Lu Fang, Zhiding Yu, Yuanfang Guo, “Multi-scale Analysis of Color and Texture for Salient Object Detection,” IEEE International Conference of Image Processing (ICIP), Brussels, Belgium, 2011.
Ketan Tang, Lu Fang, Zhiding Yu, Yuanfang Guo and Oscar C. Au, “How Anti-Aliasing Filter Affects Image Contrast: An Analysis from Majorization Theory Perspective,” IEEE International Conference on Multimedia & Expo (ICME), Barcelona, Spain, 2011. (30%)
Wenxiu Sun, Oscar C. Au, Lingfeng Xu and Zhiding Yu, “Adaptive Depth Map Assisted Matting in 3D Video,” IEEE International Conference on Multimedia & Expo (ICME), Barcelona, Spain, 2011. (30%)
Chi Ho Yeung, Oscar C. Au, Ketan Tang and Zhiding Yu, “Compressing Similar Image Sets using Low Frequency Template Prediction,” IEEE International Conference on Multimedia & Expo (ICME), Barcelona, Spain, 2011. (Top 15%)
Ketan Tang, Oscar C. Au, Lu Fang, Zhiding Yu and Yuanfang Guo, "Image Interpolation Using Autoregressive Model and Gauss-Seidel Optimization," International Conference on Image and Graphics (ICIG), USTC, Hefei, China, 2011.
Zhiding Yu, Oscar C. Au, Ketan Tang, Jiali Li, Lingfeng Xu and Xingyu Zhang, “Graph Segmentation Revisited: Detailed Analysis and Density Learning based Implementation," IEEE International Conference on Multimedia & Expo (ICME), Singapore, 2010. (30%)
I am particularly interested in learning / inferencing discriminative unary potentials, and formulating them under some more generalized MRF/CRF models.
During the summer internship in 2013 at Adobe, I developed several new features for the PixelTone Project.
The purpose of this project is to mainly reinforce the image selection and editing ability of the PixelTone prototype. During the summer, several new features have been incorporated:
This project is under the main project between CMU and GM in an effort to develope fully autonomous vehicles for the future.
The purpose of doing Clear Path Detection (CPD) is to provide useful cues for subsequent vehicle guiding and planning operations. It serves an important complement for general object detectors and bypasses the complex problem of building detectors for every possible objects that could appear.
CPD typically suffers from strong shadows. we propose a shadow robust CPD scheme that can be formulated under a generalized Markov Random Field framework, where additional parameters are introduced to model the relative relationships between the unary potentials and pairwise potentials. We apply our proposed method to the challenging problem of rear-view CPD problems with only a monocular low quality camera.
A premitive result video is available here.
We present a novel framework for tree-structure embedded density estimation and its fast approximation for mode seeking. Given any undirected, connected and weighted graph, the density function is defined as a joint representation of the feature space and the distance domain on the graph’s spanning tree. Tree domain mode seeking can not be directly conducted by traditional mean shift. Thus we address this problem by introducing node shifting with force competition and its fast approximation.
This work appears in CVPR 2011.
We present a system that can automatically segment objects in large scale 3D point clouds obtained from urban ranging images. The system consists of three steps: The first one involves a ground detection process that can detect relatively complex terrain and separate it from other objects. The second step superpixelizes the remaining objects to speed up the segmentation process. In the final step, a manifold embedded mode seeking method is adopted to segment the point clouds. Even though the segmentation of urban objects is a challenging problem in terms of accuracy and problem scale, our system can efficiently generate very good segmentation results. The proposed manifold learning effectively improves the segmentation performance due to the fact that continuous artificial objects often have manifold-like structures.
This work appears in ACM-MM 2011.
Regarding the limit of mode seeking image segmentations, we propose several improvements in this project:
1. We show that for mean shift with a linear kernel, each kernel shift can actually be formulated in a convex form. This can be also genrealized for several convex metrics - e.g., KL divergence and Jeffrey divergence.
2. We propose an interactive segmentation algorithm based on mode seeking. We show this problem can be formulated as a convex problem
The project report is available here. An improved version of this work later appeared in CVPR 2012.
Carnegie Institute of Technology Dean's Tuition Fellowship, Carnegie Mellon University, 2012
2011-2012 HKTIIT Post-Graduate Excellence Scholarship, Hong Kong University of Science and Technology, 2012.
2009-2010 HKTIIT Post-Graduate Excellence Scholarship, Hong Kong University of Science and Technology, 2010.
HKUST Postgraduate Studentship
National Third Prize, 2007 National English Contest for College Students, May 2007.
Academic Annual Comprehensive Award of Academic Year 2006 – 2007, SCUT.
National Third Prize, 2006 National English Contest for College Students, May 2006.
Triple-A Student and Scholarship of Academic Year 2005 – 2006, SCUT.
National Silver Prize, 19th China Adolescents Science Technology Invention Contest, 2004.
Provincial Second Prize, 19th Guangdong Juvenile Activities of Science & Technology, 2004.
Prof. Deyu MENG
Prof. Oscar C. AU
Prof. Jianzhuang LIU
Dr. Chunjing XU
This page has been visited