Computer Science Signal Processing

**** **** ***, *** *** ***, Los Angeles, CA *****

Bo Yang E-mail: abpouh@r.postjobfree.com

Webpage: https://sites.google.com/site/boyanghome

Background Highlights

Almost seven years of research experience in computer vision and video analysis.

Cooperation and intern experience in influential industrial companies and research labs: Google Santa Monica, Microsoft

Research Asia (MSRA), Intel China Research Center (ICRC).

Publications in top conferences and journals, such as CVPR, ECCV, CVIU, and TOIS, with more than 180 citataions.

Co-inventor of an online video recommendation system patent.

Reviewer for important journals, including TPAMI, TIP, TMM, Pattern Recognition, JMM, Image and Vision Computing, etc.

Education

Ph.D in Computer Science University of Southern California, Aug. 2008 Aug. 2012, GPA 4.0/4.0

MS in Computer Science Tsinghua University, Beijing, Sep. 2006 Jul. 2008, GPA 90.9/100, ranked top 5%

BE in Computer Science Tsinghua University, Beijing, Sep. 2002 Jul. 2006, GPA 89.9/100, ranked top 5%

Experience

Aug. 2008 Aug. 2012 Research Assistant, Computer Vision Lab, University of Southern California

Multi-Target Tracking: automatic robust multi-target tracking in real crowded scenes.

-

a) Offline learned CRF tracking: a CRF framework that relaxes independent assumption in association based tracking,

and automatic learns appropriate weights of association cues for a static scene from pre-labeled ground truth data.

b) Online learned CRF tracking: an online learned CRF model that learns pair-wise motions and discriminative appear-

ance models between targets to consider camera motions and to better distinguish visually similar close targets.

c) Online learned knowledge from a static scene for tracking: online learning non-linear motion patterns, entry/exit

points, robust appearance models, and co-moving groups for robust tracking multiple targets in a static scene.

d) Online learned part-based appearance models for tracking: online learning part-based appearance models to distin-

guish different targets from each other and from the background.

NICRF Object Segmentation: segmenting objects of a known class under low resolution and poor contrast by novel

-

non-parametric inhomogeneous CRFs.

VCBT Human Detector: fast articulated human detection with up-to-date performance.

-

May 2011 Aug. 2011 Intern, Google Santa Monica

Design learning algorithms for automatic evaluating aesthetic qualities for photos.

-

Integrate quality evaluation service into Google s Thumbnailer system, and build it in Google s Lighthouse front end.

-

Jun. 2007 Jun. 2008 Research Team Leader, Tsinghua-Intel China Research Center (ICRC) Joint Lab

Responsible for task assignment, designs, and implementation of an automatic soccer video indexing and searching system.

-

Nov. 2006 May. 2007 Research Intern, Microsoft Research Asia (MSRA)

Free-shaped video collage: presenting a video by one personalized visually pleasing image.

-

Design searching algorithms for a web video recommendation system, which is part of MSRA Video Sense system.

-

Aug. 2005 Oct. 2006 Research Student, Tsinghua-Intel China Research Center (ICRC) Joint Lab

Design algorithms for soccer video analysis, including goalmouth detection, player detection & tracking, etc. It is part of

-

ICRC s Video Mining System.

Skills

Proficiency in C/C++, seven years of project experience using Microsoft Visual Studio

Experience in Matlab, C#, Java, Javascript, SQL

Use Perforce and SVN for version control and teamwork.

Selected Publications

Tracking

Bo Yang and Ram Nevatia. Online Learned Discriminative Part-Based Appearance Models for Multi-Human Tracking. In

-

Proceedings of European Conference on Computer Vision (ECCV), Firenze, Italy, Oct. 2012.

Bo Yang and Ram Nevatia. An Online Learned CRF Model for Multi-Target Tracking. In Proceedings of IEEE Computer

-

Vision and Pattern Recognition (CVPR), Providence, USA, Jun. 2012. (Oral presentation)

Bo Yang and Ram Nevatia. Multi-Target Tracking by Online Learning of Non-linear Motion Patterns and Robust Appear-

-

ance Models. In Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR), Providence, USA, Jun. 2012.

Bo Yang, Chang Huang, and Ram Nevatia. Learning Affinities and Dependencies for Multi-Target Tracking using a CRF

-

Model. In Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR), Colorado, USA, Jun. 2011.

Segmenation

Bo Yang, Chang Huang, and Ram Nevatia. Segmentation of Objects in a Detection Window by Nonparametric Inhomoge-

-

neous CRFs. In Computer Vision and Image Understanding (CVIU), vol. 115, no. 11, pp. 1473-1482, Nov. 2011.

Object Detection

Bo Yang, Pramod Sharma, and Ram Nevatia. Vehicle Detection from Low Quality Aerial LIDAR Data. In IEEE Computer

-

Society's Workshop on Applications of Computer Vision (WACV), Kona, USA, Jan. 2011.

Bo Yang, Chang Huang, and Ram Nevatia. Extensive Articulated Human Detection by Voting Cluster Boosted Tree. In

-

IEEE Computer Society's Workshop on Applications of Computer Vision (WACV), Snowbird, USA, Dec. 2009.

Video Collage

Tao Mei, Bo Yang, Shi-Qiang Yang, and Xian-Sheng Hua. Video collage: presenting a video sequence using a single image.

-

The Visual Computer, vol. 25, no. 1, pp. 39-51, Jan. 2009.

Video Recommendation

Tao Mei, Bo Yang, and Xian-Sheng Hua. Contextual Video Recommendation by Multimodal Relevance and User Feed-

-

back. In ACM Transactions on Information Systems (TOIS), vol. 29, no. 2, Apr. 2011.

Soccer Video Analysis

Bo Yang, Lifeng Sun, Fei Wang, Peng Wang, and Shi-Qiang Yang. Mid-Level Descriptors Extraction of Soccer Video with

-

Domain Knowledge. In Proceedings of IEEE International Conference on System, Man, and Cybernetics (ICSMC), Taiwan,

Oct. 2006.

Video Enhancement

Chao Wang, Li-Feng Sun, Bo Yang, Yi-Ming liu, and Shi-Qiang Yang. Video Enhancement Using Adaptive

-

Spatio-Temporal Connective Filter and Piecewise Mapping. EURASIP Journal on Advances in Signal Processing, vol.

2008, Article ID 165792, 13 pages, 2008. doi:10.1155/2008/165792.

Web Video Analysis

Lu Liu, Yong Rui, Li-Feng Sun, Bo Yang, Jianwei Zhang, and Shi-Qiang Yang. Topic Mining on Web-Shared Videos. In

-

Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Las Vegas, Nevada,

USA, Mar. 2008.

Full publication list please refer to https://sites.google.com/site/boyanghome/publications

Selected Honors and Awards

July 2008 Tsinghua Computer Science Outstanding Master Graduate Student Award

Tsinghua Outstanding Graduate Student Award (56 out of 3000 students)

July 2006

Tsinghua Excellent Undergraduate Thesis Award (ranked 1st out of 176 in CS dept)

July 2006

Contact this candidate