Erkut Erdem


Erkut Erdem

Associate Professor

Computer Vision Laboratory (HUCVL)
Dept. of Computer Engineering
Hacettepe University


Office: 112
Address: Beytepe Campus, Ankara, Turkey TR-06800
e-mail: erkut at cs dot hacettepe dot edu dot tr
Phone: +90 312 780 7549
Fax: +90 (312) 297 7502



My research centers on the areas of computer vision and machine learning. I believe the right algorithms and representations are the ones that take into account the contextual influences. Thus, the research objective that my students and I pursue is to incorporate different kinds of context (spatial, temporal and/or cross-modal) into all levels of visual processing from low to intermediate and high-level vision.

Current research interests: Visual Saliency Prediction, Automatic Image Description, Video/Photoset Summarization, Image Filtering, Image Editing



Hacettepe University
Faculty Member
2010-now
Ecole Nationale
Supérieure des Télécommunications
Post-doctoral Researcher
2009-2010
Middle East Technical University
1997-2008
Ph.D., 2008
M.Sc., 2003
B.Sc., 2001
University of California
Los Angeles
Visiting Researcher
Oct. 2007 - Dec. 2007
Virginia Bioinformatics Institute, Virginia Tech
Visiting Researcher
Jul. 2004 - Aug. 2004

News and highlights

[March 2018]: Our joint project with Lucia Specia from the University of Sheffield on "A Multimodal and Multilingual Framework for Video Captioning" has received financial support from TUBITAK - British Council’s Newton-Katip Çelebi Fund Institutional Links Grant Programme.

[March 2018]: I am invited to Dagstuhl Seminar "Joint Processing of Language and Visual Data for Better Automated Understanding".

[February 2018]: Our joint work with ICON lab at UMRAM, Bilkent University on utilizing GANs for multi-contrast MRI synthesis is out on arXiv.

[January 2018]: New TUBITAK 1001 project on "Using Synthetic Data for Deep Person Re-Identification", in partnership with HUCG (Hacettepe University Computer Graphics and Game Studies) group.

[November 2017]: Our work on deep dynamic saliency prediction will be published in IEEE Transactions on Multimedia: "Spatio-Temporal Saliency Networks for Dynamic Saliency Prediction".

[October 2017]: I am awarded a hardware donation (a Quadro P5000 GPU) from NVIDIA for my research.

[September 2017]: New TUBITAK 1003 project on "Summarization Approaches Towards Interpreting Big Visual Data", in partnership with Somera.

[June 2017]: Our work on sampling-based image and video matting will be published in IEEE Transactions on Image Processing: "Alpha Matting with KL-Divergence Based Sparse Sampling".

[May 2017]: Slides from our "Adversarial Training and Generative Adversarial Networks" tutorial at SIU 2017 are now available online.

Curriculum Vitae (as of December 2017)

Projects

As Principal Investigator

A Multimodal and Multilingual Framework for Video Captioning

Project Duration: 2 years (2018-2020)
Sponsors: TUBITAK and British Council - Newton-Katip Çelebi Fund Institutional Links Grant Programme (Award# 217E054)
project page

Using Synthetic Data for Deep Person Re-Identification

Project Duration: 2 years (2018-2020)
Sponsors: TUBITAK 1001 - Support Program for Scientific and Technological Research Projects (Award# 217E029)
project page

Understanding Images and Visualizing Text: Semantic Inference and Retrieval by Integrating Computer Vision and Natural Language Processing

Project Duration: 3 years (2014-2017)
Sponsors: TUBITAK 1001 - Support Program for Scientific and Technological Research Projects (Award# 113E116) and European Union under European Cooperation in Science and Technology (COST) Programme (ICT COST IC1037 Action)
project page

The Use of Multiple Cues and Contextual Knowledge in Computer Vision

Project Duration: 3 years (2012-2015)
Sponsors: TUBITAK 3501 - Career Development Program (Award# 112E146)
project page

As Co-Investigator

Summarization Approaches Towards Interpreting Big Visual Data

Project Duration: 3 years (2017-2020)
Sponsors: TUBITAK 1003 - Primary Subjects R&D Funding Program (Award# 116E685)
project page

City-Wide Video Surveillance System

Project Duration: 3 years (2016-2019)
Sponsors: TUBITAK 1007 - Public Institutions Research Funding Program (Award# 114G028)
project page

Selected Publications

  • Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks,
    S. U. H. Dar, M. Yurt, L. Karacan, A. Erdem, E. Erdem, T. Cukur, arXiv preprint arXiv:1802.01221, February 2018
    :: pdf

  • Spatio-Temporal Saliency Networks for Dynamic Saliency Prediction,
    C. Bak, A. Kocak, E. Erdem and A. Erdem, IEEE Transactions on Multimedia, 20(7). pp. 1688-1698, July 2018.
    :: pdf

  • Alpha Matting with KL-Divergence Based Sparse Sampling,
    L. Karacan, A. Erdem and E. Erdem, IEEE Transactions on Image Processing, 26(9), pp. 4523-4536, September 2017
    :: pdf

  • Re-evaluating Automatic Metrics for Image Captioning,
    M. Kilickaya, A. Erdem, N. Ikizler-Cinbis and E. Erdem, The 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017), Valencia, Spain, April 2017
    :: pdf

  • Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts,
    L. Karacan, Z. Akata, A. Erdem and E. Erdem, arXiv preprint arXiv:1612.00215, December 2016
    :: pdf

  • Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts,
    L. Karacan, Z. Akata, A. Erdem and E. Erdem, arXiv preprint arXiv:1612.00215, December 2016
    :: pdf

  • An Objective Deghosting Quality Metric for HDR Images,
    O. T. Tursun, A. O. Akyuz, A. Erdem and E. Erdem, Computer Graphics Forum (Eurographics 2016), 35(2), pp. 139-152, May 2016
    :: project page (with code)
    :: pdf

  • Deformable Part-based Tracking by Coupled Global and Local Correlation Filters,
    Osman Akin, Erkut Erdem, Aykut Erdem, Krystian Mikolajczyk, Journal of Visual Communication and Image Representation, 38, pp. 763-773, July 2016
    :: pdf

  • Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures,
    R. Bernardi, R. Cakici, D. Elliott, A. Erdem, E. Erdem, N. Ikizler-Cinbis, F. Keller, A. Muscat, B. Plank, Journal of Artificial Intelligence Research, 55, pp. 409-442, February 2016
    :: pdf

  • Image Matting with KL-Divergence Based Sparse Sampling,
    L. Karacan, A. Erdem and E. Erdem, IEEE International Conference on Computer Vision (ICCV 2015),, Santiago, Chile, December 2015
    :: project page
    :: pdf

  • The State of the Art in HDR Deghosting: A Survey and Evaluation,
    O. T. Tursun, A. O. Akyuz, A. Erdem and E. Erdem, Computer Graphics Forum (Eurographics State-of-the-art Report (STAR) 2015), 34(2), pp. 683-707, May 2015
    :: pdf

  • Top down saliency estimation via superpixel-based discriminative dictionaries,
    A. Kocak, K. Cizmeciler, A. Erdem and E. Erdem, British Machine Vision Conference (BMVC) 2014, Nottingham, UK, September 2014
    :: project page (with code)
    :: pdf

  • Structure Preserving Image Smoothing via Region Covariances,
    L. Karacan, E. Erdem and A. Erdem, ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2013), Vol. 32, No. 6, November 2013
    :: project page (with code)
    :: pdf

  • Visual saliency estimation by nonlinearly integrating features using region covariances,
    E. Erdem and A. Erdem, Journal of Vision, Vol. 13, No. 4, pp. 1-20, March 2013
    :: project page (with code)
    :: pdf


For a full list of publications, please see the Publications page.

Students

Ph.D. Students

M.Sc. Students

Former Students

Teaching

Current

Graduate

Undergraduate

Past

Undergraduate

Graduate

image courtesy: iwdrm