Ethem Can



I am a PhD candidate in the School of Computer Science, UMass Amherst. I am a member of CIIR lab. My main research focus includes; computer vision, multimedia informational retrieval, and social multimedia mining.

In particular, I work on multimedia event detection, action recognition, mining visual cues in twitter, concept-based video retrieval / event detection, and concept-dependencies for event detection. I am also interested in learning-to-rank problems, specifically relevance feedback for learning-to-rank problems, and query-specific models for learning-to-rank problems.

Earlier, I focused on word spotting, processing of historical manuscripts, text categorization, and text mining. I also spent approximately 2 years in industry and worked on the projects such as automatic license plate recognition, and people counting systems.

Publications


2014
[13]   Ethem F. Can, W. Bruce Croft, and R. Manmatha: Incorporating Query-Specific Feedback into Learning-to-Rank Models, SIGIR'14, pp.1035-1038
[12]   Ethem F. Can and R. Manmatha: Modeling Concept Dependencies for Event Detection, ICMR'14, pp.289-297
[11]   Venkatesh N. Murthy, Ethem F. Can, and R. Manmatha: A Hybrid Model for Automatic Image Annotation, ICMR'14, pp.369-377

2013
[10]   Ethem F. Can, F. Can, P. Duygulu, and M. Kalpakli: Automatic categorization of Ottoman poems, Glottotheory. Vol. 4, No. 2 (2013), pp. 40-57.
[9]   Ethem F. Can, H. Oktay, and R. Manmatha: Predicting Retweet Count Using Visual Cues, CIKM 2013, pp.1481-1484.
[8]   Ethem F. Can, R. Manmatha: Formulating Action Recognition as a Ranking Problem, CVPRW'13, pp.251-256

2012
[7]   Marc-Allen Cartright, Ethem F. Can, William Dabney, Jeff Dalton, Logan Giorda, Kriste Krstovski, Xiaoye Wu, Ismet Zeki Yalniz, James Allan, R. Manmatha, David A. Smith: A framework for manipulating and searching multiple retrieval types. SIGIR 2012: 1001
2011
[6]   Ismet Zeki Yalniz, Ethem F. Can, and R. Manmatha: Partial duplicate detection for large book collections. CIKM 2011: 469-474
[5]  Ethem F. Can, and Pinar Duygulu: A line-based representation for matching words in historical manuscripts. Pattern Recognition Letters 32(8): 1126-1138
[4]  Ethem F. Can, Fazli Can, Pinar Duygulu, Mehmet Kalpakli: Automatic Categorization of Ottoman Literary Texts by Poet and Time Period. ISCIS 2011: 51-57
[3]  Ceyhun Karbeyaz, Ethem F. Can, Fazli Can, Mehmet Kalpakli: A Content-Based Social Network Study of Evliya Çelebi's Seyahatname-Bitlis Section. ISCIS 2011: 271-275
2010
[2]   Ethem F. Can, Pinar Duygulu, Fazli Can, Mehmet Kalpakli: Redif Extraction in Handwritten Ottoman Literary Texts. ICPR 2010: 1941-1944
[1] Fazli Can, Ethem F. Can, Ceyhun Karbeyaz: Translation Relationship Quantification: A Cluster-Based Approach and its Application to Shakespeare's Sonnets. ISCIS 2010: 117-120

Education

09.2010-current       PhD, University of Massachusetts Amherst (UMASS), School of Computer Science
12.2009-09.2010       PhD, Bilkent University, Department of Computer Engineering
2007-2009       M.Sc, Bilkent University, Department of Computer Engineering
2006-2007       B.Sc, Bilkent University, Department of Computer Engineering
2005-2006       B.Sc, University of California at Davis (UCD), Department of Computer Engineering and Science: Exchange Program
2003-2005       B.Sc, Bilkent University, Department of Computer Engineering

Work Experience:

2013 Summer: SRI International ( PhD Intern)
2007-2009: Kade Systems, Inc. (RD Engineer)
2010-current: UMass-Amherst (RA)
2009-2010: Bilkent University, Ankara, Turkey (TA - RA)

Projects:

Training-test splits, accuracy tables and more information about the projects that I worked will be updated soon.

Bits and Pieces