Congcong's Curriculum Vitae

back to Congcong's homepage

Congcong Li

School of Electrical and Computer Engineering
Cornell University
(814) 441-5768
cl758@cornell.edu

Click here for a PDF Version

[Education]

CORNELL UNIVERSITY Ithaca, NY Ph.D. Candidate in Electrical and Computer Engineering GPA: 4.3 (A+) / 4.0	Sep. 2009 – 2012 (expected) Advisor: Prof. Tsuhan Chen
CARNEGIE MELLON UNIVERSITY Pittsburgh, PA Ph.D. Candidate in Electrical and Computer Engineering GPA: 4.0 / 4.0	Aug. 2007 – Aug. 2009 Advisor: Prof. Tsuhan Chen
Tsinghua University Beijing, China M.S. in Electronic Engineering (Honor Graduate) Thesis: “Face Reconstruction and Recognition based on 2D Multi-images”	Aug. 2005 – Jul. 2007 Advisor: Prof. Guangda Su
TSINGHUA UNIVERSITY Beijing, China B.E. in Electronic Engineering, Minor in English Thesis: “Research on Evaluations on Face Recognition Techniques”	Jul. 2005 Advisor: Prof. Guangda Su

[return]

RESEARCH INTERESTS

Computer Vision, Multimedia Analysis and Understanding, Machine Learning, Human Cognition
Click here for more details about current research projects.

[return]

PUBLICATIONS

A. Book & JOURNALS

[B1]. 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.
[J1]. 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.
[J2]. 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.
[J3]. Jun Zhou, Guangda Su, Chunhong Jiang, Yafeng Deng, Congcong Li. “A face and fingerprint identity authentication system based on multi-route detection”, Neurocomputing, vol. 70, no. 4-6, pp. 922-931, Januanry, 2007.

B. CONFERENCE PAPERS

Congcong Li, Devi Parikh, Tsuhan Chen. “Automatic Discovery of Groups of Objects for Scene Understanding.” In International Conference on Computer Vision and 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 Regions Void of Labels 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." To appear in IEEE International Conference on Image Processing (ICIP 2011).
Congcong Li, TP Wong, Norris Xu, Ashutosh Saxena. "FeCCM for Scene Understanding: Helping the Robot to Learn Multiple Tasks." In International Conference on Robotics and Automation 2011 (ICRA 2011).
Congcong Li, Adarsh Kowdle, Ashutosh Saxena, Tsuhan Chen. “Feedback Enabled Cascaded Classification Models for Scene Understanding.” In Neural Information Processing Systems Conference 2010 (NIPS 2010).
Congcong Li, Alexander C. Loui, Tsuhan Chen. "Towards Aesthetics: A Photo Quality Assessment and Photo Selection System." In ACM Multimedia Conference 2010 (MM 2010).
Congcong Li*, Adarsh Kowdle*, Ashutosh Saxena, Tsuhan Chen. "A generic model to compose vision modules for holistic scene understanding." Workshop on Parts and Attributes, European Conference on Computer Vision, 2010 (ECCV 2010). [* indicates equal contribution]
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).
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).
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).
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 Workshop on Analysis and Modeling of Faces and Gestures, International Conference on Computer Vision. (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 (ICB2007).
Congcong Li, Guangda Su, Kai Meng, Jun Zhou. “Technology Evaluations on TH-FACE Recognition System.” In IEEE International Conference on Biometrics (ICB 2006).
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).

C. TECHNICAL REPORTS

Congcong Li. “Motion-Fucusing Video Summarization.” Master thesis, Carnegie Mellon University, May 2009. Adivsor: Tsuhan Chen.
Yu-Hsiang Bosco Chiu, Congcong Li. “Context aware speaker recognition.” Final Project in Probabilistic Graphical Models, Dec 2008. Instructor: Carlos Guestrin.
Congcong Li, Shang-Yi Lin, Yimeng Zhang. “Expression Classification on Face Images .” Final Project in Pattern Recognition, May 2008. Instructor: Marios Savvides.
Congcong Li. “Face Reconstruction and Recognition based on 2D Multi-images.” Master thesis, Tsinghua University, June 2007. Advisor: Guangda Su.
Congcong Li. “Research on Evaluations on Face Recognition Techniques.” Undergraduate thesis, Tsinghua University, June 2005. Advisor: Guangda Su.

D. TALKS

Feedback Enabled Cascaded Classification Models: Algorithm and Applications. Cornell Artificial Intelligence Seminar, Spring, 2011.
A Generic Model for Combine Tasks for Video Mood Categorization. Gracenote Inc., August, 2010.
Aesthetic Visual Quality Assessment of Paintings. Kodak Research, June, 2009.

[return]

AWARDS & HONORS

2011	CRA-W Grad Cohort Scholarship
2010	NIPS traval award
2010	NSF travel award for Women in Machine Learning Workshop
2009 -- present	McMullen Fellowship, Cornell University
2007 -- 2009	Dean’s Fellowship, Carnegie Mellon University
2007	Honorable Master Graduate, Tsinghua University
2006	Graduate Scholarship for Overall Excellence, Tsinghua University
2004	Best Exhibition, Third prize in the 22nd “Challenge Cup” Technological Innovation Competition, Tsinghua University
2001 -- 2003	Undergraduate Scholarship for Academic Excellence, Tsinghua University
2001	1st in the National University Entrance Examination in Guangxi province (1/over 100,000)

[return]

RESEARCH EXPERIENCE

Holistic Scene Understanding
We propose a generic model (together with learning and inference techniques) for connecting different vision tasks in holistic understanding. The model does not require knowing the inner workings of each sub-task and can adapt to heterogeneous datasets for training. It treats each classifier for the relative sub-task as a ‘black box’. The proposed model is arranged in a cascade, by jointly optimizing the final outputs given the original inputs. The model considers intermediate outputs as hidden variables and allow communication from latter-layer classifiers to earlier ones. Experiments in six tasks show that our method, which uses one single model, significantly outperforms the state-of-theart classifiers, each of which is manually designed for the corresponding task..

Aesthetic Visual Quality Assessment of Digital Media
We proposed a learning scheme to assess the aesthetic visual quality of digital images. We conducted user surveys to study human’s preferences and concerns on the appeals of images. In the algorithm, we extracted a group of computational features to represent the aesthetic quality of an image, including technical features (e.g. color, lighting, etc.), perceptual features (e.g. symmetry, consistency, harmony, etc.), and social relationship features (e.g. relationship between people in the image, etc.). The ongoing direction for this project is to automatically discover high-level semantic attributes to represent the photo appeals. Applications for this algorithm include appeal-based image retrieval, photo album distillation, painting recommendation, etc. Demo: http://amp.ece.cornell.edu/projects/aesthetics/

Object Detection, Key Frame Extraction, and Video Summarization
We proposed a motion-focusing method to extract key frames and construct summary image for surveillance videos. With this algorithm, the generated summary image reflects the spatial and temporal relationship between moving objects, and the key frames provide detailed information for Region-of-Interest in the summary image.

Face Recognition Related Research
I worked on four projects under this topic: 1) worked on the image preprocessing module and the performance validation module in THU2005 Face Recognition System, which won the Gold Award in 15th China Invention Exhibition. 2) proposed a face reconstruction and recognition algorithm based on multiple pose-variant face images, aiming at solve the pose variance problem in face recognition. 3) proposed the Gabor-Combined feature and Gray-Intensity feature Fusion (GCGIF) algorithm for face recognition, based on which a face identification system is established. 4) participated in drafting a state standard on face recognition. Participated parts include: Format for face data interchange, Test database construction, and Performance evaluation on face recognition system.

[return]

PROPFESSIONAL EXPERIENCES

Research Assistant, Cornell University, 2009.9 - present
Research Assistant, Carnegie Mellon University, 2007.8 - 2009.8
Research Assistant, Tsinghua University, 2004.8 - 2007.7
Teaching Assistant, Tsinghua University, 2005.9 - 2006.1
Internship: Media Technology Lab, Gracenote Company. Emeryville, CA, 2010. 6 - 2010. 8
Internship: Kodak Research Lab, Eastman Kodak Research. Rochester, NY, 2009.5 - 2009.8
Internship: Tsinghua Tongfang Company. Beijing, China, 2004.6 - 2004.8
Reviewer:
- Journals: TIP, SPL, JMIV, JNCA.
- Conferences: ICCV 2009/2011, CVPR 2010/2011, ICML 2010, MMSP 2009, ICME 2010/2011, ICIP 2010/2011, ECCV 2010.
Membership: Student member of IEEE and ACM, member of SWE

[return]

HIGHLIGHT COURSES

Cornell University	CS 6780 Advanced Machine Learning CS 6784 Advanced Topics in Machine Learning
Carnegie Mellon University	CS 16720 Computer Vision CS 16708 Probabilistic Graphical Models ECE 18798 Image, Video and Multimedia ECE 18794 Probabilistic Graphical Models ECE 18752 Detection, Estimation and Identification
Tsinghua University	Probability and Statistics Stochastic Processes Numerical Analysis and Algorithms Image Analysis Digital Image Processing Content-based Visual Information Retrieval Digital Image Technique and Application

[return]

COMPUTER SKILLS

Programming: C/C++, Matlab
Tools: Matlab, Visual Studio, Photoshop
Operating System: Windows, Mac OSX

[return]

OTHER SKILLS

Language: Native in Cantonese, Mandarin; Fluent in English
Painting (specialize in Chinese Painting for 10 years)

[return]