Now showing items 21-40 of 46

    • The importance of context and semantic descriptions in object recognition: Studies in computer vision and human vision 

      Aksoy, S.; Boyaci H.; Gökçay, D. (2008)
      Object recognition and scene classification are among the main interests in computer vision which have been investigated for long. Automatic recognition and classification ofobjects and scenes is an important skill to be ...
    • Information-based approach to punctuation 

      Say, B. (AAAI, Menlo Park, CA, United States, 1997)
      This thesis analyzes, in an information-based framework, the semantic and discourse aspects of punctuation, drawing computational implications for Natural Language Processing (NLP) systems. The Discourse Representation ...
    • Integration of structural and semantic models for multimedia metadata management 

      Little, S.; Martinelli, M.; Salvetti O.; Güdükbay U.; Ulusoy, Ö.; De Chalendar G.; Grefenstette G. (2007)
      The management and exchange of multimedia data is challenging due to the variety of formats, standards and intended applications. In addition, production of multimedia data is rapidly increasing due to the availability of ...
    • Keyframe labeling technique for surveillance event classification 

      Şaykol, E.; Baştan M.; Güdükbay U.; Ulusoy, Ö. (S P I E - International Society for Optical Engineering, 2010)
      The huge amount of video data generated by surveillance systems necessitates the use of automatic tools for their efficient analysis, indexing, and retrieval. Automated access to the semantic content of surveillance videos ...
    • Learning bayesian classifiers for scene classification with a visual grammar 

      Aksoy, S.; Koperski, K.; Tusk, C.; Marchisio, G.; Tilton J. C. (IEEE, 2005)
      A challenging problem in image content extraction and classification is building a system that automatically learns high-level semantic interpretations of images. We describe a Bayesian framework for a visual grammar that ...
    • Learning translation templates for closely related languages 

      Altintas, K.; Güvenir, H. A. (Springer, 2003)
      Many researchers have worked on example-based machine translation and different techniques have been investigated in the area. In literature, a method of using translation templates learned from bilingual example pairs was ...
    • Matching ottoman words: An image retrieval approach to historical document indexing 

      Ataer, E.; Duygulu P. (2007)
      Large archives of Ottoman documents are challenging to many historians all over the world. However, these archives remain inaccessible since manual transcription of such a huge volume is difficult. Automatic transcription ...
    • Measuring and improving interpretability of word embeddings using lexical resources 

      Şenel, Lütfi Kerem (Bilkent University, 2019-08)
      As an ubiquitous method in natural language processing, word embeddings are extensively employed to map semantic properties of words into a dense vector representations. They have become increasingly popular due to their ...
    • Metadata extraction from text in soccer domain 

      Gokturk, Z.O.; Cicekli, N.K.; Cicekli I. (2008)
      Event detection is a crucial part for soccer video searching and querying. The event detection could be done by video content itself or from a structured or semi structured text files gathered from sports web sites. In ...
    • A novel array signal processing technique for multipath channel parameter estimation 

      Güldoǧan, M.B.; Arikan, O. (2007)
      In this paper, a new array signal processing technique, which make use of the cross ambiguity function calculation, is proposed. Developed technique estimates direction of arrival (DOA), time delay, Doppler shift and ...
    • An ontology-based approach to parsing Turkish sentences 

      Temizsoy, M.; Cicekli I. (Springer Verlag, 1998)
      The main problem with natural language analysis is the ambiguity found in various levels of linguistic information. Syntactic analysis with word senses is frequently not enough to resolve all ambiguities found in a sentence. ...
    • Performance analysis of cross ambiguity function-Direction finding technique in multipath environments 

      Güldoǧan, M.B.; Arikan, O. (2008)
      In this paper, recently proposed Cross Ambiguity Function Direction Finding (CAF-DF) array signal processing technique, which make use of the cross ambiguity function calculation, is compared with the MUltiple SIgnal ...
    • Querying web metadata: Native score management and text support in databases 

      Özsoyoǧlu, G.; Altingövde, I. S.; Al-Hamdani, A.; Özel, S. A.; Ulusoy, Ö.; Özsoyoǧlu, Z. M. (Association for Computing Machinery, 2004)
      In this article, we discuss the issues involved in adding a native score management system to object-relational databases, to be used in querying Web metadata (that describes the semantic content of Web resources). The Web ...
    • River: an intermediate language for stream processing 

      Soulé R.; Hirzel M.; Gedik, B.; Grimm, R. (John Wiley & Sons Ltd., 2016)
      Summary This paper presents both a calculus for stream processing, named Brooklet, and its realization as an intermediate language, named River. Because River is based on Brooklet, it has a formal semantics that enables ...
    • A rule-based video database system architecture 

      Dönderler, M. E.; Ulusoy, Ö.; Güdükbay U. (Elsevier, 2002)
      We propose a novel architecture for a video database system incorporating both spatio-temporal and semantic (keyword, event/activity and category-based) query facilities. The originality of our approach stems from the fact ...
    • Safe data parallelism for general streaming 

      Schneider S.; Hirzel M.; Gedik, B.; Wu, Kun-Lung (Institute of Electrical and Electronics Engineers, 2015)
      Streaming applications process possibly infinite streams of data and often have both high throughput and low latency requirements. They are comprised of operator graphs that produce and consume data tuples. General streaming ...
    • Scene classification for content-based image retrieval 

      Çavuş Ö.; Aksoy, S. (2008)
      Content-based image indexing and retrieval have become important research problems with the use of large databases in a wide range of areas. In this study, a content-based image retrieval system that is based on scene ...
    • Semantic argument frequency-based Multi-Document Summarization 

      Aksoy, C.; Bugdayci, A.; Gur, T.; Uysal I.; Can F. (2009)
      Semantic Role Labeling (SRL) aims to identify the constituents of a sentence, together with their roles with respect to the sentence predicates. In this paper, we introduce and assess the idea of using SRL on generic ...
    • Semantic scene classification for image annotation and retrieval 

      Çavuş Ö.; Aksoy, S. (2008)
      We describe an annotation and retrieval framework that uses a semantic image representation by contextual modeling of images using occurrence probabilities of concepts and objects. First, images are segmented into regions ...
    • Semantic similarity between Turkish and European languages using word embeddings 

      Sjenel, L. K.; Yucesoy, V.; Koc, A.; Cukur, T. (Institute of Electrical and Electronics Engineers Inc., 2017)
      Representation of words coming from vocabulary of a language as real vectors in a high dimensional space is called as word embeddings. Word embeddings are proven to be successful in modelling semantic relations between ...