/* Onur Kucuktunc */
"λ-Diverse Nearest Neighbors Browsing for Multi-dimensional Data" has been accepted to TKDE. ×
-
Sunset in Istanbul, Turkey New York from Empire State Building Santorini, Greece San Marco Square in Venice, Italy MNAC and Magic Fountain in Barcelona, Spain Chicago, The Bean at Millenium Park The Monte Carlo Casino Monaco San Francisco, Lombard Street Tenerife, Spain
-
Research Interests
My research interests include, but not limited to, the following topics:
Biclustering
Biclustering methods simultaneously cluster both genes and conditions of gene expression data. Mining gene expression data with biclustering can provide insights into gene functions and aid in the development and treatment of complex diseases.Sentiment Analysis
Our analysis starts with a large-scale study on the correlation of various features with the observed attitude and sentimentality. We investigate textual, topical, demographical, spatial, and temporal features.Tag Suggestion
We develop computer vision-based tag recommendation for photo sharing websites, such as Flickr.
Diversity Search
We investigate the concepts of diversity and diverse nearest neighbor search in various fields and application areas with different types of data, such spatial, high-dimensional, and time-series data. Although the definition of diversity will differ from field to field, we propose techniques without neglecting the general objective of diversification, which is to maximize the similarity of search results to the query, by minimizing the pairwise similarity between the results.Video Copy Detection
We propose a video copy detection framework that detects copy segments by fusing the results of three different techniques: facial shot matching, activity subsequence matching, and non-facial shot matching using low-level feature.
-
Journal Papers
- Onur Kucuktunc, H. Ferhatosmanoglu, λ-Diverse Nearest Neighbors Browsing for Multi-dimensional Data, (accepted to) IEEE TKDE.
- Onur Kucuktunc, M. Bastan, U. Gudukbay, O. Ulusoy, Video Copy Detection Using Multiple Visual Cues and MPEG-7 Descriptors, Journal of Visual Communication and Image Representation, vol.21, no.8, pp.838-849, Nov, 2010.
- S.G. Sevil, Onur Kucuktunc, P. Duygulu, F. Can, Automatic Tag Expansion using Visual Similarity for Photo Sharing Websites, Multimedia Tools and Applications, vol.49, no.1, pp. 81-99, Aug, 2010.
- Onur Kucuktunc, U. Gudukbay, O. Ulusoy, Fuzzy Color Histogram-based Video Segmentation, Computer Vision and Image Understanding, vol.114, no.1, pp.125-134, Jan, 2010.
- Onur Kucuktunc, U. Gudukbay, O. Ulusoy, A Natural Language Based Interface for Query Specification in a Video Database Management System, IEEE MultiMedia, vol.14, no.1, pp. 83-89, Jan-Mar, 2007.
International Conference Papers
- Onur Kucuktunc, B.B. Cambazoglu, I. Weber, H. Ferhatosmanoglu, A Large-Scale Sentiment Analysis for Yahoo! Answers, (accepted to) WSDM, 2012 (acceptance rate 20.7%).
- Onur Kucuktunc, D. Zamalieva, Fuzzy Color Histogram-based CBIR System, Proceedings of 1st International Fuzzy Systems Symposium (FUZZYSS'09), 2009.
- Onur Kucuktunc, M. Bastan, U. Gudukbay, O. Ulusoy, Bilkent University Multimedia Database Group at TRECVID 2008, In Proc. TREC Video Retrieval Evaluation (TRECVID'08), 2008.
- Onur Kucuktunc, S.G. Sevil, A.B. Tosun, H. Zitouni, P. Duygulu, F. Can, Tag Suggestr: Automatic Photo Tag Expansion using Visual Information for Photo Sharing Websites, Proceedings of 3rd International Conference on Semantic and Digital Media Technologies (SAMT 2008), Koblenz, Germany, December 3-5, 2008. Lecture Notes in Computer Science, vol.5392/2008, Springer Verlag, Berlin Heidelberg, pp.63-71, 2008.
- A. Bulbul, Onur Kucuktunc, B. Ozguc, Animation of Boiling Phenomena, 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video, 2008, pp.357-360, 28-30 May 2008.
Invited or Non-refereed Papers
Onur Kucuktunc, M. Bastan, U. Gudukbay, O. Ulusoy, Bilkent University Multimedia Database Group at TRECVID 2008, Proceedings of the TREC Video Retrieval Evaluation (TRECVID), Gaithersburg, MD, November 17-18, 2008.
Theses
Content-based Video Copy Detection Using Multimodal Analysis, Master's Thesis, Bilkent University, Ankara, Turkey, 2009.
Seminars and Talks Given
BilVideo: MPEG-7 Compliant Video Database Management System, MUSCLE Conference joint with VITALAS Conference (MCVC'08), Cannes, France, February 2008.
- CV
About
Onur Kucuktunc is a Ph.D. candidate in Computer Science and Engineering department at The Ohio State University, working with Umit V. Catalyurek.
He received his B.S. and M.S. degrees in Computer Engineering from Bilkent University, Ankara, Turkey in 2007 and 2009, respectively. During his masters, he worked on content-based video copy detection and visual similarity-based tag suggestion, participated in TRECVID'08.
Currently, his research interests include similarity and diversity search, sentiment analysis, opinion retrieval, and biclustering.
Biclustering.
Querying co-regulated genes on diverse gene expression datasets via biclustering
The rapid development and increasing popularity of gene expression microarrays have resulted in a number of studies on the discovery of co-regulated genes. One important way of discovering such co-regulations is the query-based search, since gene coexpressions may indicate a shared role in a biological process. Although there are promising query-driven search methods and biclustering-based techniques to identify a subset of conditions, they fail to capture many genes that function in the same biological pathway due to sensitivity to noise, or simply because microarray datasets are fraught with spurious samples or samples of diverse origin. Currently, several successful methods utilize Pearson Correlation Coefficient (PCC) based gene expression analysis, but due to issues of scalability, computational complexity, and accuracy, the problem of rank aggregation of genes among diverse datasets remains open.
×