Afshin Dehghan

PhD student (since Fall 2011)
Center for Research in Computer Vision (CRCV)
Supervised by Mubarak Shah
University of Central Florida

Email: adehghan8@cs.ucf.edu (Remove 8)
Office: Harris Corporation Engineering Center (HEC), Room 254
Research interests: Vision, Machine Learning

 


NEWS:
  • July 2014. Had a nice interview with American Physics Society.[ Interview link : Coming Soon]

  • June 2014. Who's Your Daddy Project on Local News.[Fox35 Interveiw]

  • June 2014. Press Release on Who's Your Daddy Project.[UCF News]

  • May 2014. Tracking result of 19 trackers and Fscore on individual sequence of ALOV dataset are released.

  • March 2014. Paper accepted in ICIP.

  • Feb 2014. 2 CVPR papers accepted.

  • Nov 2013. Paper "Visual Tracking: an Experimental Survey" got accepted in IEEE PAMI.
    [Project Page][Mirror Link:ALOV300++ Dataset][Mirror Link:ALOV300++ Groundtruth]

  • Oct 2013. PNNL Parking Lot 2 dataset as well as the tracking groundtruth are released.

  • Oct 2013. Code for CVPR13 paper is released.

  • Oct 2013. GMCP tracking code is being updated.


Projects:

 

ALADDIN: Automated Low-Level Analysis and Description of Diverse Intelligence Video

Abstract: The Automated Low-Level Analysis and Description of Diverse Intelligence Video (ALADDIN) Program seeks to combine the state-of-the-art in video extraction, audio extraction, knowledge representation, and search technologies in a revolutionary way to create a fast, accurate, robust, and extensible technology that supports the multimedia analytic needs of the future.

Contribution: UCF is a part of SRI-Sarnoff team and I've been leading UCF team since summer 2012. I have investigated the benefits of using concepts,attribute and objects in representating a video. I am also interested in problem of event detection using only few examplars.

 

Evaluation of Tracking Algorithms on ISIS Video Data for the Wide Area Surveillance Project:

Abstract: The project is a part of the Wide-Area Surveillance (WAS) project being implemented by the U.S. Department of Homeland Security (DHS) Science and Technology Directorate (S&T). This project targets the development and evaluation of desirable crowd tracking algorithm to be used in the (ISIS) context. ISIS is a camera system developed by Massachusetts Institute of Technology/Lincoln Laboratories (MIT/LL) and managed by Pacific Northwest National Laboratory (PNNL). The ISIS consists of a 100 Mpixel sensor (an array of image servers and associated hard drive storage array). While the ISIS camera can collect a large volume of video data for a wide area monitored, it demands an effective crowd tracking algorithm to be integrated with the ISIS software system supporting video viewing and analysis.[More Info]

Contribution: The first method that we proposed was a part-based greedy approach capable of detecting occluded part of a person and was published in CVPR2012.The second approach was based on a global data association method which we utilized and introduced Generalized Minimum Clique Graph to efficiently track each individual in video sequences provided. The later was published in ECCV2012.


Who's Your Daddy?

Abstract: In this project, our goal is to bridge computer vision research with findings in anthropological studies to answer several key questions:
-Do offspring resemble their parents?
-Do offspring resemble one parent more than the other?
-What parts of the face are more genetic?
-Do anthropologies' studies help learn better features?

Contribution: To answer these questions and address the problem of parent-offspring resemblance we propose an algorithm that fuses the features and metrics discovered via gated autoencoders with a discriminative neural network layer that learns the optimal, or what we call genetic, features for the task. For more information please check out the CVPR14 paper.[Press Release] [Fox35 Interview]

 

Publications:


Improving Semantic Concept Detection through the Dictionary of Visually-distinct Elements
Afshin Dehghan, Haroon Idrees and Mubarak Shah
in Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2014)
[PDF] [Video Spotlight] [Send Email for Code and Dataset]

Who Do I Look Like? Determining Parent-Offspring Resemblance via Gated Autoencoders
Afshin Dehghan, Enrique G. Ortiz, Ruben Vilegas and Mubarak Shah
in Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2014)
[PDF] [Video Spotlight] [Send Email for Code and Dataset]

Complex Event Recognition by Latent Temporal Models of Concepts
Ehsan Zare Borzeshi,Afshin Dehghan, Massimo Piccardi, and Mubarak Shah
in Proceedings of IEEE International Conference on Image Processing (ICIP 2014)
[PDF]

Visual Tracking: an Experimental Survey
Arnold W. M. Smeulders, Dung M. Chu, Rita Cucchiara, Simone Calderara, Afshin Dehghan and Mubarak Shah
In Proceeding of IEEE Transaction on Pattern Analysis and Machine Intelligence (PAMI'2013)
[PDF] [Project Page] [Mirror Link:ALOV300++ Groundtruth] [Mirror Link:ALOV300++ Dataset]

Visual Business Recognition - A Multimodal Approach
Amir Roshan Zamir, Afshin Dehghan and Mubarak Shah
In Proceeding of ACM International Conference on Multimedia (ACM MM'2013)
[PDF] [Project Page] [Data]

Improving an Object Detector and Extracting Regions using Superpixels
Guang Shu, Afshin Dehghan and Mubarak Shah
In proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR'13)
[PDF] [Project Page] [Data]

GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs
Amir Roshan Zamir, Afshin Dehghan and Mubarak Shah
In proceedings of European Conference on Computer Vision 2012 (ECCV'12)
[PDF] [Project Page] [Data]

 

Keynote: Automatic Detection and Tracking of Pedestrians in Videos with Various Crowd Densities
Afshin Dehghan, Haroon Idrees, Amir Roshan Zamir and Mubarak Shah
In Proceedings of PED, June 2012
[PDF] [Project Page] [Data]

 

Part-based Multiple-Person Tracking with Partial Occlusion Handling
Guang Shu, Afshin Dehghan, Omar Oreifej, Emily Hand, Mubarak Shah
In proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR'12)
[PDF] [Project Page] [Data]

 

SRI-Sarnoff AURORA System at TRECVID 2012 Multimedia Event Detection and Recounting
H. Cheng, J. Liu, S. Ali, O. Javed, Q. Yu,A. Tamrakar, A. Divakaran†, H. S. Sawhney, R. Manmatha, Ja. Allan, A. Hauptmann, M. Shah, S. Bhattacharya, A. Dehghan , G. Friedland, B. M. Elizalde, T. Darrell, M. Witbrock, J. Curtis, In Proceeding of Trecvid Video Retrieval Evaluation Workshop, NIST, Gaitherburg, Md, November 2012
[PDF] [Project Page] [Data]

A Multi-Agent Architecture for Tracking User Interactions in Browser-based Games
A.A. Bagherzadeh, S. Rezvankhah, S. Farahi, K. Khalvati, P. Mousavi, A. Dehghan, B. Ghaderi, L. Kashani, H. Moradi
In proceedings of IEEE International Conference On Digital Game And Intelligent Toy Enhanced Learning (DIGITEL12)
[PDF] [Project Page] [Data]