Home


Mohamed H. Elhoseiny, Ph.D., MSc (CS), MSc (CSys).

Postdoc Researcher in Computer Vision at Facebook AI Research      

Research interests: Computer Vision, Language & Vision,  Art & Vision, and Understanding of Deep  Learning, Art&AI.  

Resume https://sites.google.com/site/mhelhoseiny/ElhoseinyCV2013_3p.pdf  
linkedin , ResearchGate 
I co-organized the 1st Workshop on Closing the Loop between Vision and Language, held in conjunction with ICCV 2015 and  2nd Workshop on Closing the Loop between Vision and Language, held in conjunction with ICCV 2017. 
 
Affiliations(Rutgers, SRI International, Adobe Research, Facebook AI Research).





Headlight Projects 

Collaborators

  • Ahmed Elgammal,  Professor of Computer Science at Rutgers University:  MS&PhD advisor and co-author in more than published 15 conference papers, 2 journal papers
  • Yann LeCun,  Professor of Computer Scienc at NYU and Director of AI Research at Facebook.
  • Tinne Tuytelaars, Professor of Computer Science at KULauven.  
  • Dimitris Metaxas, Professor of Computer Science at Rutgers University: CBIM lab directors: co-author
  • Harpreet Sawhney(CTO SRI International): Mentor at SRI International,   co-author
  • Hui Cheng (Program Director, SRI International): Mentor at SRI International,   co-author
  • Jingen Liu (Senior Research Scientist, SRI International): Mentor at SRI International,   co-author
  • Xiaolei Huang (Associate Professor of Computer Science and Engineering at Lehigh University) co-author
  • Shaoting Zhang (Associate Professor of Computer Science at  UNC at Charlotte) co-author
  • Scott Cohen (Principal Scientist at Adobe Research)Mentor at Adobe Research,   co-author
  • Brian Price (Senior Research Scientist at Adobe Research):  Mentor at Adobe Research, co-author
  • Walter Chang (Principal Scientist at  Adobe Research)Mentor at Adobe Research, co-author
  • Sheng Huang, Chongqing University: co-author
  • Han Zhang, Rutgers Universityco-author
  • Tao Xu, Lehigh Universityco-author
  • Hossam Faheem (Ain Shams University, Egypt). 


Students, I co-advise

  • Ji Zhang, Rutgers
  • Ethan Zhu, Rutgers
  • Othman Sbai, University of Paris
  • Mennatullah Siam, University of Alberta


Profile

  • Research and Hands-on Experience on Computer Vision, Machine Learning, Multimedia, Natural Language Processing, and Deep Learning
  • Mentorship and Participation on various Artificial Intelligence Projects.
  • Six years of industry experience as a Research and Development Software Engineer.
  • Extensive programming, problem solving, integration and multidisciplinary engineering skills.

Education

PhD in Computer Science, Rutgers University  Supervisor: Prof. Ahmed Elgammal – Fall 2011-present– GPA 4.00   

                  Thesis: My research work is on Computer Vision, Machine Learning, Multimedia  and NLP.

M.Sc in Computer Science, Rutgers  University  Supervisor: Prof. Ahmed Egammal – 2014 – courses GPA 4.0

          MSc report, "Write a Classifier: Zero Shot Learning Using Purely Textual Descriptions", published at ICCV13

M.Sc in Computer Systems, Ain Shams University (ASU)  Supervisor: Prof. Taymour Nazmy – 2010 – courses GPA 3.55.

                  Thesis: “High Performance Activity Monitoring for Scenes including Multiple Agents”, research GPA 4.0

BSc in Computer SystemsAin Shams University (ASU)  Supervisor: Prof. Said ElGhoneimy – 2006 – GPA 3.96.


News

11/2017: Our paper "The Shape of Art History in the Eyes of the Machine" got accepted at AAAI 2018
09/2017: Program Committee member  CVPR18 
07/2017: In 2017, I have 2 CVPR (first/co-first author), 1 AAAI (first author), 1 TPAMI (first author), 1 ICCC, 1 book chapter 2017 (first author), 1 US patent, organizing closing the loop between vision and language 2017.
06/2017: US Patent accepted http://www.freepatentsonline.com/y2017/0132526.html
05/2017: We will be organizing the second workshop on Closing the loop between Vision and Language link
03/2017: Two papers accepted to CVPR17
03/2017: Program Commitee member in  Workshop of Large Scale Biometrics :  http://isse.cqu.edu.cn/lssb/
02/2017: 6DS (28K images) and LSC (814K images) datasets was released. That was part of the sherlock project. The trained model2 on LSC is also available. see https://sites.google.com/site/mhelhoseiny/sherlock_project
12/2016: code released, SMTGP (published at the Machine Learning Journal 2015) code released https://sites.google.com/site/mhelhoseiny/computer-vision-projects/structured-regression

11/2016: (first author) AAAI 2017 paper accepted for publication, "Sherlock: Scalable Fact Learning in Images"  
11/2016:  (first author) TPAMI paper accepted for publication
08/2016: ACL 2016 VL presentation of our work on collecting hundreds of thousands of high quality annotations from image-caption datasets.  "Automatic Annotation of structured Facts in Images". The evaluation shows that the precision is >80%.  Dataset released  link
07/2016: Received offers from Adobe Research, PostDocs at Stanford Univeristy, University of Torronto, and Facebook AI Research
06/2016: Visiting Facebook
06/2016:  Presenting our paper at ICML16, "A Comparative Analysis and Study of Multiview CNN Models for Joint Object Categorization and Pose Estimation"
05/2016: Talk and a Poster at the Mid-Atlantic Computer Vision Workshop (MACV), 2016 at JHU link 
04/2016: 1 paper accepted to ICML16 (first-author)!, acceptance rate 24.5%
04/2016: Visiting Disney Research Pittsburgh
04/2016: Visiting UC Berkeley EECS
04/2016: Attending ICLR16 (presenting 1 conference paper (co-first author) and 1 workshop presentation (first-author) ), conference acceptance rate 25%.
04/2016: Attending CVPR16 (presenting 1 conference paper and a Doctoral Consortium poster)
04/2016:  CVPR16  Doctoral Consortium  award!
04/2016:  ICLR16  Travel Award!
03/2016: 1 paper accepted to CVPR 2016, "SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-grained Recognition".
02/2016: 1 paper accepted to  ICLR 2016, "Digging Deep into the layers of CNNs: In Search of How CNNs Achieve View Invariance"
11/2015: 1 paper accepted to WACV 2016, "Joint Object Recognition and Pose Estimation using a Nonlinear View-invariant Latent Generative Model"
10/2015: 1 paper accepted to AAAI 2016, "Zero Shot Event Detection by Multimodal Distributional Semantic Embedding of Videos"

Honors and Awards 

  • Best Intern Award , Silver, SRI International, Vision and Learning Group  [2014]
  • CVPR16 Doctoral Consortium Award
  • ICLR 2016 Travel Award
  • Rutgers University Nominee for Google PhD Fellowship 2014
  • Nominated by the department of Computer Science at Rutgers University for Microsoft fellowship [2014].
  • 8/14 of the projects, I mentored from [2007] to [2011], received awards from Information Technology Industry Development Agency (ITIDA), Egypt.
  • Travel awards for my ICIP publications by Rutgers University 2013 and 2014, also for ICCV 2013 from PAMI-TC.
  •  Research-MSc fellowship by the Faculty of Computer and Information Sciences, Ain Shams university , [2007-2010].
  • Ranked 3rd in  the Computer Systems Bachelor Program and received the Honor degree, as indicated in my transcripts,  in [2006]. 
  • Ranked 1st in my High School class, in [2002] and received an honor-shield my rank.
Employment

Computer Vision Research Intern at Adobe Research, Vision Group, San Jose, CA under: Dr. Scott Cohen Liu, Walter Chang, and Brian Price– Summer 2015

Computer Vision Research Intern at SRI-International, Vision an Learning Group, Princeton, NJ under: Dr. Jingen Liu, Hui Cheng, and Harpreet Sawhney– Summer 2014

Computer Vision Research Intern at IPPLEX Corporation, LA, CA under: Dr. Jeremi Sudol and David McKinnon– Summer 2012

Research & Development Associate at Future Business Development, Cairo, Egypt– under Dr. Adnan Faqeeh – Summer 2011

Senior R&D Software Engineer  (part-time) at House of Invention (HOI) GROUP, Cairo, Egypt 2007-2011

Undergrad-Research Mentor & Teaching Assistant  at Computer Science Department, ASU, Cairo, Egypt2007-2011

Software Testing Engineer at Giza Systems, Cairo, Egypt  2006-2007

 


Services
Reviewer for IEEE TPAMI Journal
Reviewer for IEEE TMM Journal
Reviewer for IEEE TIP Journal
Reviewer for IEEE TNNLS 
Reviewer for CVPR, ICCV, ECCV conferences
Reviewer for BMVCW
Reviewer for MVA Journal Journal
Bio 

Mohamed Elhoseiny is a PhD candidate at the Department of  Computer  Science,  Rutgers,  the  State  University  of  New Jersey. He is also a member of the Center for Computational Biomedicine Imaging and Modeling (CBIM).  He has become very interested in Computer Vision and Machine Intelligence, and especially in Language & Vision problems for the sake of visual perception (PhD major work). Mohamed received the best intern award silver at SRI International Princeton in 2014 for his work on connecting videos to language. He co-organized the workshop on “Closing the Loop between Vision and Language”  at the International Conference on Computer Vision (ICCV), 2015.  He has authored 15 papers in premier Computer Vision and Machine Learning conferences and journals such as  ICML, ICCV, CVPR, AAAI, ICLR, MLJ, ICIP, MTAP, ISM.

Emails 

[mylastname][at]fb[dot]com, m.elhoseiny[at]cs[dot]rutgers[dot]edu, mhe19[at]cs[dot]rutgers[dot]edu,mohamed.elhoseiny[at]gmail[dot]com


 


Myself (bottom left) as part of the FAIR team

 ECML-PKDD 2015, Porto, Portugal




Receiving best intern award (silver) from Dr. Rakesh Kumar, President of SRI International, Princeton, NJ, August 15th 2014.


ICCV13, Sydney, Australia
 
                                                         


  
Old News

12/02/2015 We finalized the program for ICCV15 workshop on Closing the loop between Vision and Language, Chile, Dec 17, 2015. link

11/12/2015  Our paper "Zero Shot Event Detection by Distributional Semantic Embedding of Videos" has been accepted in AAAI-16.

10/22/2015 Our paper "Joint Object Recognition and Pose Estimation using a Nonlinear View-­Invariant Latent Generative Model" has been accepted in WACV16.
 
10/05/2015 Call for extended abstracts for ICCV15 workshop on Closing the loop between Vision and Language, Chile, Dec 17, 2015.  https://sites.google.com/site/clvlworkshop/. Tentative deadline for abstracts is 10/30/2015.

07/01/2015 Our paper "Overlapping Domain Cover for Scalable and Accurate Kernel Machines" got accepted in BMVC 2015 (oral)

06/10/2015 Our workshop proposal "Closing the Loop Between Language and Vision" got accepted at ICCV 2015. We are inviting full papers in this area. 

06/01/2015 Our paper "Weather Classification with Deep Convolutional Neural Networks" got accepted in ICIP 2015 (oral)

04/12/2015 Our manuscript  "Generalized Twin Gaussian Processes using Sharma-Mittal Divergencegot accepted in the International Machine Learning Journal, Springer. The manuscript will be presented at ECMLPKDD 2015 (Journal Track), Porto, Portugal. Journal Track of ECMLPKDD is usually <10% acceptance rate. 

03/02/2015 Our paper "Learning Hypergraph-regularized Attribute Predictors" got accepted in CVPR15

01/10/2015 Our manuscript  "Text to Multi-level MindMaps: A Novel Method for Hierarchical Visual Abstraction of Natural Language Text" got accepted in the International Journal of Multimedia Tools and Applications

08/15/2014 , Received a best Intern award, Silver at SRI International (below is a picture with Prof. Rakesh Kumar, the president of SRI-International, Princeton),             

08/01/2014, Received Travel Grant by my department for ICIP 2014

06/19/2014, An NSF proposal by my advisor based on our "Write a Classifier" ICCV13 results got accepted by NSF and we received  about 500,000$ from which my PhD thesis is funded this year. You can see that the proposal title has same name.  http://www.cs.rutgers.edu/news/articles/2014/06/19/prof-elgammal-awarded-nsf-grant/

06/01/2014, A paper has been accepted to ICIP14.

03/15/2014 , I am going to a summer intern for 2014 at SRI-International, Vision and Learning Group

10/30/2013, Travel Award by PAMI 450$ for ICCV13

 10/01/ 2013, A Workshop short paper at VisDA workshop at ICCV13

08/30/ 2013, A paper has been accepted in ICCV13

08/15/2013, Won the travel award from Rutgers to Melbourne to present my ICIP13 paper

A paper has been accepted in CVPRW, SISM, 04/27/ 2013, "MultiClass Object Classification in Video Surveillance Systems - Experimental Study", CVPRW,SISM, 2013

A paper has been accepted in ICIP, 2013, titled "Low-Bitrate benefits of JPEG Compression on SIFT Recognition"