Ahmed Elgammal



CBIM The Center for Computational Biomedicine Imaging and Modeling 

The Art & Artificial Intelligence  Lab

RUCCS Rutgers University Center for Cognitive Science


Dept. of Computer Science
Rutgers, the State University of New Jersey
110 Frelinghuysen Road
Piscataway, NJ 08854-8019 USA
Office: Core Building 316 – Busch Campus.

phone: 848-445-8316

elgammal          cs.rutgers.edu

I am an Associate Professor in the Department of Computer Science, Rutgers University


Areas of Interest

Research Focus: Computer Vision, Visual Learning, Data Science, Digital Humanities, Human motion analysis.

Wider interest: Multimedia Computing, Image and Video Processing, Image and Video Databases, Machine Learning, Neural Modeling and AI.

Research Statement

The focus of computer vision research is on recovering and understanding knowledge about the three-dimensional world from two-dimensional images. Such problems have proved to be extremely difficult. A central issue in computational vision is object and scene representation. Scientists have investigated different representations, varying from object-centered 3D geometric representations to viewer-centered representations. The problem is more challenging for dynamic objects. My research interest is on investigating representations of moving objects (articulated and deformable). In particular, I am interested in studying representations that explain the visual appearance of dynamic objects without the need for explicit 3D geometric models. My objective is to learn representations for the shape and the appearance of moving (dynamic) objects that support tasks such as synthesis, pose recovery, reconstruction and tracking. In particular, my research is focused on this problem within the human motion analysis context. Human motion analysis is a challenging problem with many potential applications such as visual surveillance, human-machine interface, video archival and retrieval, computer graphics animation, autonomous driving, virtual reality, etc. [Read more about my research…]


7/31/2015 The Washington Post writes for the second time about our work on quantifying creativity

7/31/2015 Check out my article on the conversation “Which paintings were the most creative of their time? An algorithm may hold the answers”, the article was reposted on the Times Magazine Idea’s section  and on the Newsweek opinion section .

7/15/2015 The New York Times reports on our research on art analysis and assessing of  creativity.  

6/18/2015 The Washington Post writes about our work on Creativity Assessment in Art Networks

6/11/2015 NBC News writes about our paper on quantifying creativity

6/9/2015 MIT Technology review reports on our work on quantifying creativity

Check out our new research results on Quantifying Creativity on Art Networks, to be published in the 6th International Conference on Computational Creativity 2015. This paper received global media coverage

I am serving as an Area Chair in ICCV 2015

5/11/2015 MIT Technology Review Report on our paper on large scale fine-art classification  

New paper in CVPR 2015 titled “Learning Hypergraph-regularized Attribute Predictors” with Eisen Sheng Huang and Mohamed Elhoseiny 

11/10/2014 The Washington Post writes about our work on Influence Discovery.

Announcing the establishment of the Digital Humanities Laboratories at Rutgers

October 2014: The Science News writes about our work on Influence Discovery.

Received an NSF award titled “IIS-Medium Write A Classifier: Learning Fine-Grained Visual Classifiers from Text and Images” in collaboration with Smaranda Muresan (Columbia University - CCLS) for a total of $1M for three years.

One paper in ECCV 2014 titled “Untangling Object-View Manifold for Multiview Recognition and Pose Estimation” with Amr Bakry

One paper in CVPR 2014 titled “Simultaneous Twin Kernel Learning using Polynomial Transformations for Structured Prediction” with Chetan Tonde

One paper in the 5th International Conference on Computational Creativity titled “Knowledge Discovery of Artistic Influences: A Metric Learning Approach” with Babak Saleh and Kana Abe.

I served as an Area Chair in CVPR 2014.

Two ICCV’13 papers: “Write a Classifier: Zero Shot Learning Using Purely Textual Descriptions” with Mohamed Elhoseiny and Babak Saleh; and “Online Motion Segmentation using Dynamic Label Propagation” with Ali Elqursh

Recently received an NSF award titled "Detecting Abnormality in Images", in collaboration with Professor Jacob Feldman from the Department of Psychology and Assistant Professor Ali Farhadi from the University of Washington. The total for Rutgers side of the award is $339,000

International Innovation North America Magazine has published a report about our NSF funded project on Generalized Separation of Style and Content for Human Motion Analysis, May 2013. “The Shapes of Motion” [pdf]

New Paper on AAAI 2013 titled “Joint Object and Pose Recognition Using Homeomorphic Manifold Analysis”

Two CVPR’13 papers: “Object-Centric Anomaly Detection by Attribute-Based Reasoning” with Babak Saleh, and “MKPLS: Manifold Kernel Partial Least Squares for Lipreading and Speaker identification”, with Amr Bakry.

Editor Choice Article published on the Image and Vision Computing Journal, April 2013. The article is titled "Homeomorphic Manifold Analysis (HMA): Generalized Separation of Style and Content on Manifolds", with Chan-Su Lee

New Algorithm for Moving Camera Background Subtraction - Online Moving Camera Background Subtraction Published in ECCV2012 - Watch Demos Here

I am serving as an area chair and publication chair in the 10th IEEE Conference on Automatic Face and Gesture Recognition FG2013.

Check out our approach for satellite image based GPS-free vehicle localization - Published in ICRA 2012 - Watch Demos Here

Book Chapter on Background Subtraction (Tutorial and Survey)  “Figure-ground segmentation - pixel-based” in “Guide to Visual Analysis of Humans: Looking at People” To be published in 2011 by Springer

Two CVPR’11 papers: “Line-based relative pose estimation” with Ali Elqursh and “Supervised Hypergraph Labeling” with Toufiq Parag

Two CVPR’10 papers: “Putting Local Features on a Manifold” and One-Shot Multi-Set Non-rigid Feature-Spatial Matching with Marwan Torki

A short tutorial on skin detection for face detection - to appear in Encyclopedia of Biometrics by Springer.

Three new journal papers to appear in early 2009 in PAMI, IJCV, and CVIU        

       -  “Tracking People on a Torus” - TPAMI - march 09

Book Chapter The Role of Manifold Learning in Human Motion Analysis Human Motion - Understanding, Modeling, Capture and Animation. Springer – Computational Imaging Series