Research

My research interests are in computer vision, deep (machine) learning and computational models of biological vision. In particular, I am interested in

• object detection and recognition,
• human pose estimation,
• deep learning,
• and biologically inspired computational models, in general.

Publications

• "Self-Supervised Learning of 3D Human Pose using Multi-view Geometry"
  Muhammed Kocabas, Salih Karagoz, Emre Akbas
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
  pdf | link | bibtex | code

• "MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network"
  Muhammed Kocabas, Salih Karagoz, Emre Akbas
  European Conference on Computer Vision (ECCV), 2018.
  pdf | link | bibtex | code | implementation by others: link
  

• "Localization Recall Precision (LRP): A New Performance Metric for Object Detection"
  Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan
  European Conference on Computer Vision (ECCV), 2018.
  pdf | link | bibtex | code

• "Object detection through search with a foveated visual system"
  Emre Akbas, Miguel P. Eckstein
  PLOS Computational Biology, 2017.
  pdf | link | bibtex | code
  ★ This work was selected as the cover of the October 2017 issue.
  

• "Humans but not deep neural networks miss giant targets in scenes"
  Miguel P. Eckstein, Kathryn Koehler, Lauren Welbourne, Emre Akbas
  Current Biology, 2017.
  pdf | link | bibtex
  ★ This work has appeared in UCSB press release, EurekAlert, ScienceDaily and The New York Times.
  

• "Could we create a training set for image captioning using automatic translation?" (in Turkish)
  Nermin Samet, Samet Hicsonmez, Pinar Duygulu, Emre Akbas
  25th Signal Processing and Communications Applications Conference (SIU), 2017.
  link
  

• "Decoding cognitive states using the bag of words model on fMRI time series"
  Güneş Sucu, Emre Akbaş, İlke Öztekin, Eda Mızrak, Fatoş Yarman Vural
  Intl. Workshop on Machine Learning for Understanding the Brain, in conj. with 24th Signal Processing and Communication Application Conference (SIU), 2016.
  pdf | link | bibtex
  

• "Optimal and human eye movements to clustered low value cues to increase decision rewards during search"
  Miguel P. Eckstein, Wade Schoonveld, Sheng Zhang, Stephen C. Mack, Emre Akbas
  Vision Research, 2015.
  pdf | link | bibtex
  

• "Low-level hierarchical segmentation statistics of natural images"
  Emre Akbas, Narendra Ahuja
  IEEE Transactions on Pattern Analysis Machine Intelligence (TPAMI), 2014.
  pdf | link | bibtex
  

• "The Front End for Mammalian Vision: a Detailed Model and Its Implications for Machine Learning"
  Emre Akbas, Aseem Wadha, Miguel Eckstein and Upamanyu Madhow
  52nd Annual Allerton Conference on Communication, Control, and Computing, University of Illinois at Urbana-Champaign, 2014.
  pdf | link | bibtex
  

• "Pedestrian recognition with a learned metric"
  Mert Dikmen, Emre Akbas, Thomas S. Huang, Narendra Ahuja
  Asian Conference in Computer Vision (ACCV), 2010.
  pdf | link | bibtex
  

• "Low-level segmentation based scene classification"
  Emre Akbas, Narendra Ahuja
  International Conference on Pattern Recognition (ICPR), 2010.
  pdf | link | bibtex
  

• "From ramp discontinuities to segmentation tree"
  Emre Akbas, Narendra Ahuja
  Asian Conference in Computer Vision (ACCV), 2009.
  pdf | link | bibtex
  

• "Automatic Image Annotation by Ensemble of Visual Descriptors"
  Emre Akbas, Fatos T. Yarman Vural
  Workshop on Semantic Learning Applications in Multimedia, Conference on Computer Vision and Pattern Recognition (CVPRW), 2007.
  pdf | link | bibtex
  

• "A Hierarchical Classification System Based on Adaptive Resonance Theory"
  Mutlu Uysal, Emre Akbas, Fatos T. Yarman Vural
  International Conference on Image Processing (ICIP), 2006.
  pdf | link | bibtex
  

• "Design of a Feature Set for Face Recognition Problem"
  Emre Akbas, Fatos T. Yarman Vural
  International Symposium on Computer and Information Sciences (ISCIS), 2006.
  pdf | link | bibtex
  

• "A Comparison of Feature Spaces for Face Recognition Problem" (in Turkish)
  Gulsah T. Ozyer, Emre Akbas, Fatos T. Yarman Vural
  IEEE Conference on Signal Processing and Communications Applications (SIU), 2006.
  pdf | link | bibtex
  

• "A Comparison of the Performances of Fuzzy ARTMAP and AdaBoost Classification Algorithms in Image Retrieval" (in Turkish)
  Emre Akbas, Ozge Ozcanli, Fatos T. Yarman Vural
  IEEE Conference on Signal Processing and Communications Applications (SIU), 2005.
  pdf | link | bibtex
  

Technical reports

• Emre Akbas and Miguel P. Eckstein, "Object Detection Through Exploration With A Foveated Visual Field," Vision and Image Understanding Lab, University of California Santa-Barbara, Aug 2014.
  [ pdf | link | bibtex ]
• Emre Akbas, Bernard Ghanem and Narendra Ahuja, "MIS-Boost: Multiple Instance Selection Boosting," Computer Vision and Robotics Lab, Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Sep 2011. [ pdf | link | bibtex ]

Thesis

• Emre Akbas, "Generation and analysis of segmentation trees for natural images," Ph.D. dissertation, University of Illinois at Urbana-Champaign Champaign, 2011. Supervised by Prof Narendra Ahuja. [ pdf | link | bibtex ]
• Emre Akbas, "Automatic Image Annotation By Ensemble Of Visual Descriptors," M.S. Thesis, Middle East Technical University, 2006. Supervised by Prof Fatos T. Yarman Vural. [ link | bibtex ]

Peer reviewed abstracts

• Arturo Deza, Emre Akbas, Miguel P. Eckstein, "Scene context reduces distractor set-size effects during search," Journal of Vision. 2015; 15(12):55-55. [ link ]
• Kathryn Koehler, Emre Akbas, Miguel P. Eckstein, "Relating peripheral processing ability to learning in a visual search task," Journal of Vision. 2013; 13(9):525-525. [ link ]
• Stephen C. Mack, Emre Akbas, Miguel P. Eckstein, "Optimal search by initially looking away from the target in the presence of remote cues," Journal of Vision. 2013; 13(9):533-533. [ link ]
• Emre Akbas, Kathryn Koehler, Miguel P Eckstein, "Learning of eye movements for human and optimal models during search in complex statistical environments," Journal of Vision. 2013; 13(9):242-242. [ link ]
• Kathryn Koehler, Emre Akbas, Matthew Peterson, Miguel P. Eckstein, "Human versus Bayesian Optimal Learning of Eye Movement Strategies During Visual Search," Journal of Vision. 2012; 12(9):1142-1142. [ link ]

Last updated on Mar 21, 2019. Created using TSPW and pandoc.