CONGCONG LI

School of Electrical and Computer Engineering http://chenlab.ece.cornell.edu/people/congcong/

Cornell University, Ithaca, NY 14850 Phone: 814-***-**** Email: abp0z7@r.postjobfree.com

OBJECTIVE: Full-time research position in computer vision, machine learning, and multimedia analysis.

EDUCATION

CORNELL UNIVERSITY Ithaca, NY Advisor: Tsuhan Chen

Ph.D. Candidate in Electrical and Computer Engineering, GPA: 4.30(A+) Sep. 2009 - May. 2012 (expected)

Minor in Computer Science

Thesis: Learning Contextual Cues for Holistic Scene Understanding

Thesis Committee: Tsuhan Chen(Advisor), Thorsten Joachims, Ashutosh Saxena, Alexander C. Loui

CARNEGIE MELLON UNIVERSITY Pittsburgh, PA Advisor: Tsuhan Chen

Ph.D. Candidate in Electrical and Computer Engineering, GPA: 4.00 Aug. 2007 - Aug. 2009 (transferred)

TSINGHUA UNIVERSITY Beijing, China Advisor: Guangda Su

M.S. in Electronic Engineering (Honorable Graduate), GPA: 3.80 Aug. 2005 - Jul. 2007

Thesis: Face Reconstruction and Recognition based on 2D Multi-images

TSINGHUA UNIVERSITY Beijing, China

B.E. Major in Electronic Engineering, Minor in English, GPA: 3.75 Sep. 2001 - Jul. 2005

RESEARCH EXPERIENCE

Holistic Scene Understanding Cornell University, 2009.10-present

Proposed a generic model (together with learning and inference techniques) to jointly optimize multiple scene

understanding tasks, while requiring only a `black-box' interface for each task. The model allows feedback in a

cascade, and can be applied to heterogeneous datasets. [NIPS 2010 / TPAMI 2012]

Evaluated the algorithm on six vision tasks (scene categorization, object detection, depth estimation, etc.), robotic

applications, and video surveillance applications. [ICIP 2011 / ICRA 2011 / ECCV 2010 Workshop]

Built a robotic assistive system with the proposed algorithm: http://www.youtube.com/watch?v=ZiSLHJHczvA

Project page: http://chenlab.ece.cornell.edu/projects/FECCM/

Contextual Modeling Cornell University, 2010.9-present

Proposed an efficient algorithm to automatically discover groups of objects that capture high-order interactions

between objects and better explain scenes. [CVPR 2012]

Proposed a granularity-adaptive contextual cue that exploits unlabeled regions in images, to capture different types

of contextual interactions (scene, inter-object, intra-object, etc.); formulated the context extraction as an object

detection problem, allowing the proposed cue to be extracted by any off-the-shelf object detection algorithm.

Project page: http://chenlab.ece.cornell.edu/projects/AdaptiveContext/ [ICCV 2011]

Proposed a Markov Random Field (MRF) over the parameters to capture the spatial and semantic interactions

between related classifiers. Achieved state-of-the-art performance in two settings: multi-class object detection and

multi-task scene understanding. [NIPS 2011]

Aesthetic Visual Quality Assessment of Digital Media Carnegie Mellon/Kodak/Cornell, 2007-present

Proposed computational features and attributes to represent the aesthetic visual quality of an image. [ICIP 2010]

Proposed a learning framework to assess the aesthetic visual quality of digital images. [IJSTSP / ICIP 2010]

Built a system that automatically assesses a photo s aesthetic quality, improves a photo s composition, and

performs photo album distillation. [Multimedia 2010] Demo: http://chenlab.ece.cornell.edu/projects/aesthetics/

abp0z7@r.postjobfree.com

CONGCONG LI

Key Frame Extraction, and Video Summarization Carnegie Mellon University, 2008.9-2008.12

Proposed a motion-focusing method to extract key frames and construct summary image for surveillance videos.

Provided a new method to visualize the spatial and temporal relationship between moving objects. [ICIP 2009]

Face Recognition Related Research Tsinghua University, 2005-2007

Implemented the image preprocessing module and the performance validation module in THU2005 Face

Recognition System (Gold Award in 15th China Invention Exhibition). [ICB 2006 / ICMLC 2005 / CIS 2005]

Proposed a face reconstruction and recognition algorithm based on multiple pose-variant face images, to solve the

pose variance problem in face recognition. [ICB 2007]

Proposed Gabor-Combined feature and Gray-Intensity feature Fusion (GCGIF) algorithm for face recognition.

[ICCV2007 AMFG Workshop]

Served in the drafting committee for a national standard: GA/T 893-2010 Terms for biometric recognition in

security and protection systems .

PUBLICATION

Book & Journal Papers:

Congcong Li, Tsuhan Chen. Visual Aesthetic Quality Assessment of Digital Images. Chapter in Book:

Perceptual Digital Image: Methods and Applications. To be published by CRC Press, in 2012.

Congcong Li, Adarsh Kowdle, Ashutosh Saxena, Tsuhan Chen. Towards Holistic Scene Understanding:

Feedback Enabled Cascaded Classification Models. To appear in IEEE Transactions on Pattern Analysis and

Machine Intelligence (TPAMI), 2012.

Congcong Li, Tsuhan Chen. Aesthetic Visual Quality Assessment of Paintings. IEEE Journal of Selected Topics

in Signal Processing (IJSTSP), vol. 3, no. 2, pp. 236-253, April, 2009.

Jun Zhou, Guangda Su, Chunhong Jiang, Yafeng Deng, Congcong Li. A face and s identity authentication system

based on multi-route detection. Neurocomputing, vol. 70, no. 4-6, pp. 922-931, 2007.

Conference Papers:

Congcong Li, Devi Parikh, Tsuhan Chen. Automatic Discovery of Groups of Objects for Scene Understanding.

In International Conference on Computer Vision & Pattern Recognition (CVPR 2012).

Congcong Li, Ashutosh Saxena, Tsuhan Chen. $\theta$-MRF: Capturing Spatial and Semantic Structure in the

Parameters for Scene Understanding. In Neural Information Processing Systems Conference (NIPS 2011).

Congcong Li, Devi Parikh, Tsuhan Chen. Exploiting Unlabeled Regions to Extract Adaptive Contextual Cues.

In International Conference on Computer Vision (ICCV 2011).

Congcong Li, Chih-Wei Lin, Shiaw-Shian Yu, Tsuhan Chen. Joint Optimization of Background Subtraction and

Object Detection for Night Surveillance. In IEEE International Conference on Image Processing (ICIP 2011).

Congcong Li, TP Wang, Norris Xu, Ashutosh Saxena. FeCCM for Scene Understanding: Helping the Robot to

Learn Multiple Tasks. In International Conference on Robotics and Automation (ICRA 2011).

Congcong Li, Adarsh Kowdle, Ashutosh Saxena, Tsuhan Chen. Towards Holistic Scene Understanding:

Feedback Enabled Cascaded Classification Models. In Neural Information Processing Systems Conference

(NIPS 2010).

Congcong Li, Alexander C. Loui, Tsuhan Chen. Towards Aesthetics: A Photo Quality Assessment and Photo

Selection System. In ACM Multimedia Conference 2010 (Multimedia 2010).

Congcong Li, Andrew Gallagher, Alexander C. Loui, Tsuhan Chen. Aesthetic Visual Quality Assessment of

Consumer Photos with Faces. In IEEE International Conference on Image Processing (ICIP 2010).

Congcong Li*, Adarsh Kowdle*, Ashutosh Saxena, Tsuhan Chen. A generic model to compose vision modules

for holistic scene understanding. In First International Workshop on Parts and Attributes (ECCV 2010

Workshop). [* indicates equal contribution]

Congcong Li, Tsuhan Chen. Motion-focusing Key Frame Extraction and Video Summarization for Lane

Surveillance System. In IEEE International Conference on Image Processing (ICIP 2009).

2

abp0z7@r.postjobfree.com

CONGCONG LI

Congcong Li, Guangda Su, Yan Shang, Yingchun Li, Yan Xiang. Face Recognition Based on Pose-Variant

Image Synthesis and Multi-level Multi-feature Fusion. In Third International Workshop on Analysis and

Modeling of Faces and Gestures (AMFG). (ICCV2007 Workshop).

Congcong Li, Guangda Su, Yan Shang, Yingchun Li. Frontal Face Synthesis Based on Multiple Pose-Variant

Images for Face Recognition. In IEEE International Conferences on Biometrics (ICB 2007).

Congcong Li, Guangda Su, Kai Meng, Jun Zhou. Technology Evaluations on TH-FACE Recognition System. In

IEEE International Conference on Biometrics (ICB 2006).

Wei Yu, Ahmed Bilal Ashraf, Yao-Jen Chang, Congcong Li, Tsuhan Chen. 3D Augmented Markov Random

Field for Object Recognition. In IEEE International Conference on Image Processing (ICIP 2010).

Kai Meng, Guangda Su, Congcong Li, Bo Fu, Jun Zhou. A High Performance Face Recognition System Based

on a Huge Face Database. In Fourth International Conference on Machine Learning and Cybernetics (ICMLC

2005).

Jun Zhou, Guangda Su, Yafeng Deng, Kai Meng, Congcong Li. A Dynamic Face and Fingerprint Fusion System

for Identity Authentication. In International Conference on Computational Intelligence and Security (CIS 2005).

Patent:

Guangda Su, Yan Xiang, Congcong Li. A Face Recognition System and Device based on the Part-based Feature

and Gabor-based Feature Fusion Algorithm . CN200810104401.6.

PROFESSIONAL EXPERIENCE

Summer Intern, Media Technology Laboratories, Gracenote Company, 2010. 6 2010. 8

Summer Intern, Kodak Research Laboratories, Eastman Kodak Company, 2009. 5 2009. 8

Summer Intern, Tsinghua Tongfang Company, Beijing, 2004. 6 2004. 8

Master Student Mentor, Cornell University, 2011. 8 present (Mentoring Chill Yi-I Chiu)

Undergraduate Mentor, Cornell University, 2010. 9 2011. 2 (Mentoring TP Wang and Norris Xu)

Research Assistant, Cornell University, 2009. 9 present

Research Assistant, Carnegie Mellon University, 2007. 8 2009. 8

Research Assistant, Tsinghua University, 2005. 8 2007. 7

Teaching Assistant, Tsinghua University, 2005. 9 2006. 1

Reviewer:

Journals: TIP, TMM, SPL, JMIV, JNCA.

Conferences: ICCV, CVPR, ICML, MMSP, ICME, ICIP, ECCV.

Membership: Student member of IEEE and ACM, member of SWE

SELECTED HONORS AND REWARDS

NIPS travel award, 2010

NSF travel award for Women in Machine Learning Workshop (WiML), 2010

McMullen Fellowship, Cornell University, Sep. 2009 - present

Dean s Fellowship, Carnegie Mellon University, Aug. 2007 - Aug. 2009

Honorable Master Graduate, Tsinghua University, Jul. 2007

Graduate Scholarship for Overall Excellence, Tsinghua University, 2005 2006

Undergraduate Scholarship for Academic Excellence, Tsinghua University, 2001, 2003

First-place out of 100,000+ in National College Entrance Exam in Guangxi Province, 2001

COMPUTER SKILLS

Programming: C/C++, Matlab

Tools: Matlab, Visual Studio, OpenCV, Photoshop

Operating System: Windows, Mac OSX

OTHER SKILLS

Language: Native in Cantonese, Mandarin; Fluent in English

Painting (specialize in Chinese Painting for 10 years)

3

Contact this candidate