Browsing by Subject "Semantics"

Now showing 1 - 20 of 52

Open Access
Attributes2Classname: a discriminative model for attribute-based unsupervised zero-shot learning
(IEEE, 2017-10) Demirel, B.; Cinbiş, Ramazan Gökberk; İkizler-Cinbiş, N.
We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names. However, this proves to be a difficult task due to dominance of non-visual semantics in underlying vector-space embeddings of class names. To address this issue, we discriminatively learn a word representation such that the similarities between class and combination of attribute names fall in line with the visual similarity. Contrary to the traditional zero-shot learning approaches that are built upon attribute presence, our approach bypasses the laborious attributeclass relation annotations for unseen classes. In addition, our proposed approach renders text-only training possible, hence, the training can be augmented without the need to collect additional image data. The experimental results show that our method yields state-of-the-art results for unsupervised ZSL in three benchmark datasets. © 2017 IEEE.
Open Access
Automated construction of fuzzy event sets and its application to active databases
(IEEE, 2001) Saygin, Y.; Ulusoy, Özgür
Fuzzy sets and fuzzy logic research aims to bridge the gap between the crisp world of math and the real world. Fuzzy set theory was applied to many different areas, from control to databases. Sometimes the number of events in an event-driven system may become very high and unmanageable. Therefore, it is very useful to organize the events into fuzzy event sets also introducing the benefits of the fuzzy set theory. All the events that have occurred in a system can be stored in event histories which contain precious hidden information. In this paper, we propose a method for automated construction of fuzzy event sets out of event histories via data mining techniques. The useful information hidden in the event history is extracted into a matrix called sequential proximity matrix. This matrix shows the proximities of events and it is used for fuzzy rule execution via similarity based event detection and construction of fuzzy event sets. Our application platform is active databases. We describe how fuzzy event sets can be exploited for similarity based event detection and fuzzy rule execution in active database systems.
Open Access
Automatic image captioning
(2004) Pan J.-Y.; Yang H.-J.; Duygulu, Pınar; Faloutsos, C.
In this paper, we examine the problem of automatic image captioning. Given a training set of captioned images, we want to discover correlations between image features and keywords, so that we can automatically find good keywords for a new image. We experiment thoroughly with multiple design alternatives on large datasets of various content styles, and our proposed methods achieve up to a 45% relative improvement on captioning accuracy over the state of the art.
Open Access
BilVideo: a video database management system
(IEEE, 2003) Dönderler, M. E.; Şaykol, E.; Ulusoy, Özgür; Güdükbay, Uğur
The BilVideo video database management system provides integrated support for spatiotemporal and semantic queries for video. BilVideo can support any application with video data searching needs. It's query language provides a simple way to extend the system's query capabilities. Users can add application-dependent rules and facts to the knowledge base.
Open Access
The BioPAX community standard for pathway data sharing
(Nature Publishing Group, 2010-09) Demir, Emek; Cary, M. P.; Paley, S.; Fukuda, K.; Lemer, C.; Vastrik, I.; Wu, G.; D'Eustachio, P.; Schaefer, C.; Luciano, J.; Schacherer, F.; Martinez-Flores, I.; Hu, Z.; Jimenez-Jacinto, V.; Joshi-Tope, G.; Kandasamy, K.; Lopez-Fuentes, A. C.; Mi, H.; Pichler, E.; Rodchenkov, I.; Splendiani, A.; Tkachev, S.; Zucker, J.; Gopinath, G.; Rajasimha, H.; Ramakrishnan, R.; Shah, I.; Syed, M.; Anwar, N.; Babur, Özgün; Blinov, M.; Brauner, E.; Corwin, D.; Donaldson, S.; Gibbons, F.; Goldberg, R.; Hornbeck, P.; Luna, A.; Murray-Rust, P.; Neumann, E.; Reubenacker, O.; Samwald, M.; Iersel, Martijn van; Wimalaratne, S.; Allen, K.; Braun, B.; Whirl-Carrillo, M.; Cheung, Kei-Hoi; Dahlquist, K.; Finney, A.; Gillespie, M.; Glass, E.; Gong, L.; Haw, R.; Honig, M.; Hubaut, O.; Kane, D.; Krupa, S.; Kutmon, M.; Leonard, J.; Marks, D.; Merberg, D.; Petri, V.; Pico, A.; Ravenscroft, D.; Ren, L.; Shah, N.; Sunshine, M.; Tang R.; Whaley, R.; Letovksy, S.; Buetow, K. H.; Rzhetsky, A.; Schachter, V.; Sobral, B. S.; Doğrusöz, Uğur; McWeeney, S.; Aladjem, M.; Birney, E.; Collado-Vides, J.; Goto, S.; Hucka, M.; Novère, Nicolas Le; Maltsev, N.; Pandey, A.; Thomas, P.; Wingender, E.; Karp, P. D.; Sander, C.; Bader, G. D.
Biological Pathway Exchange (BioPAX) is a standard language to represent biological pathways at the molecular and cellular level and to facilitate the exchange of pathway data. The rapid growth of the volume of pathway data has spurred the development of databases and computational tools to aid interpretation; however, use of these data is hampered by the current fragmentation of pathway information across many databases with incompatible formats. BioPAX, which was created through a community process, solves this problem by making pathway data substantially easier to collect, index, interpret and share. BioPAX can represent metabolic and signaling pathways, molecular and genetic interactions and gene regulation networks. Using BioPAX, millions of interactions, organized into thousands of pathways, from many organisms are available from a growing number of databases. This large amount of pathway data in a computable form will support visualization, analysis and biological discovery. © 2010 Nature America, Inc. All rights reserved.
Open Access
Carnap on the method of philosophy
(2020-05) Kaya, Hatice
This thesis examines Carnap’s view on the method of philosophy. More specifically, it examines his gradual inclusion of non-formal elements to an initially formal method of philosophy. In his early period, Carnap proposes merely a formal method of philosophy to which he calls rational reconstruction, logical analysis and logical syntax. However, in his late period with the addition of some non-formal features such as semantics and pragmatics Carnap’s method becomes less and less formal. The decrease in the formal aspects of Carnap’s method of philosophy indicates the inadequacy of formal methods on their own and the need for the non-formal features in the method of philosophy. It is argued that the non-formal aspect of philosophy is essential and philosophy and its method cannot be merely formal.
Open Access
Çokyollu kanal parametre kestirimi için yeni bir dizilim sinyal işleme tekniği
(IEEE, 2007-06) Güldoǧan, Mehmet Burak; Arıkan, Orhan
Bu bildiride, çarpraz belirsizlik işlevinin kullanıldığı yeni bir dizilim sinyal işleme tekniği önerilmektedir. Geliştirilen teknik bir algılayıcı dizilimine gelen sinyallerden herbirinin geliş yönünü (GY), zaman gecikmesini Doppler kaymasını ve genliğini dürümlü bir sekilde kestirir. Önerilen Çarpraz Belirsizlik İşlevi - Yön Bulma (ÇBI-YB) tekniği ile Çoklu Sinyal Sınıflandırması (MUSIC) algoritmasının performansları sentetik sinyaller kullanılarak kök Ortalama Karesel Hata (kOKH) cinsinden değişik işaret Gürültü Oranı (İGO) değerleri için karşılaştırılmıştır. Önerilen tekniğin başarımı kayıt edilmiş çokyollu yüksek-enlem iyonosfer verileri üzerinde irdelenmiştir. Elde edilen sonuçlar, düşük İGO değerlerinde dahi çokyollu sinyal kaynaklarını ayırmada önerilen ÇBİ-YB tekniğinin ciddi başarım artışı sağladığını göstermektedir.
Open Access
Çokyollu ortamda çapraz belirsizlik işlevi-yön bulma tekniğinin başarım analizi
(IEEE, 2008-04) Güldoǧan, Mehmet Burak; Arıkan, Orhan
Bu bildiride, Çapraz Belirsizlik İşlevi-Yön Bulma (CAFDF) tekniğinin çokyollu ortamlardaki sinyallerin zaman gecikmesi, Doppler kayması, geliş yönü(GY) ve genlik kestirimindeki başarımı ile yiiksek çözünürlüklü algoritmalar olan Uzay-Almaşan Genelleşmiş Beklenti-Enbüyüitme (SAGE) ve Çoklu Sinyal Sınıflandırılması(MUSIC)'in sentetik sinyaller iizerindeki başarımları kıyaslanmıştır. Algoritmalann performansları, kök Ortalama Karesel Hata (kOKH) cinsinden degişik işaret Gürültü Oranı (iGO) değerlerinde Monte Carlo denemelerine dayalı olarak sunulmuştur. Sentetik kanallarda istatiksel kıyaslama amaçlı Cramer-Rao alt sınırları eklenmiştir. Simülasyon sonuçları göstermektedir ki, orta ve düşük iGO değerlerinde CAF-DF diğer iki algoritmaya göre üstünlük sağlamaktadır.
Open Access
Comparison of the CAF-DF and sage algorithms in multipath channel parameter estimation
(IEEE, 2008-07) Güldoğan, M. Burak; Arıkan, Orhan
In this paper, performance of the recently proposed Cross Ambiguity Function - Direction Finding (CAF-DF) technique is compared with the Space Alternating Generalized Expectation Maximization (SAGE) technique. The CAF-DF, iteratively estimates direction of arrival (DOA), time-delay, Doppler shift and amplitude corresponding to each impinging signal onto an antenna array by utilizing the cross ambiguity function. On synthetic signals, based on Monte Carlo trials, performances of the algoritms are tested in terms of root Mean Squared Error (rMSE) at different Signal-to-Noise Ratios (SNR). Cramer-Rao lower bound is included for statistical comparisons. Simulation results indicate the superior performance of the CAF-DF technique over SAGE technique for low and medium SNR values. © 2008 IEEE.
Open Access
Conceptfusion: A flexible scene classification framework
(Springer, 2015-03-04) Saraç, Mustafa İlker; işcen, Ahmet; Gölge, Eren; Duygulu, Pınar
We introduce ConceptFusion, a method that aims high accuracy in categorizing large number of scenes, while keeping the model relatively simpler and efficient for scalability. The proposed method combines the advantages of both low-level representations and high-level semantic categories, and eliminates the distinctions between different levels through the definition of concepts. The proposed framework encodes the perspectives brought through different concepts by considering them in concept groups that are ensembled for the final decision. Experiments carried out on benchmark datasets show the effectiveness of incorporating concepts in different levels with different perspectives. © Springer International Publishing Switzerland 2015.
Open Access
Contextual learning for unit commitment with renewable energy sources
(IEEE, 2017) Lee, H. -S.; Tekin, Cem; Schaar, M.; Lee, J. -W.
In this paper, we study a unit commitment (UC) problem minimizing operating costs of the power system with renewable energy sources. We develop a contextual learning algorithm for UC (CLUC) which learns which UC schedule to choose based on the context information such as past load demand and weather condition. CLUC does not require any prior knowledge on the uncertainties such as the load demand and the renewable power outputs, and learns them over time using the context information. We characterize the performance of CLUC analytically, and prove its optimality in terms of the long-term average cost. Through the simulation results, we show the performance of CLUC and the effectiveness of utilizing the context information in the UC problem.
Open Access
COST292 experimental framework for TRECVID 2006
(National Institute of Standards and Technology, 2006) Ćalić J.; Krämer P.; Naci, U.; Vrochidis, S.; Aksoy, S.; Zhangk Q.; Benois-Pineau J.; Saracoglu, A.; Doulaverakis, C.; Jarina, R.; Campbell, N.; Mezaris V.; Kompatsiaris I.; Spyrou, E.; Koumoulos G.; Avrithis, Y.; Dalkilic, A.; Alatan, A.; Hanjalic, A.; Izquierdo, E.
In this paper we give an overview of the four TRECVID tasks submitted by COST292, European network of institutions in the area of semantic multimodal analysis and retrieval of digital video media. Initially, we present shot boundary evaluation method based on results merged using a confidence measure. The two SB detectors user here are presented, one of the Technical University of Delft and one of the LaBRI, University of Bordeaux 1, followed by the description of the merging algorithm. The high-level feature extraction task comprises three separate systems. The first system, developed by the National Technical University of Athens (NTUA) utilises a set of MPEG-7 low-level descriptors and Latent Semantic Analysis to detect the features. The second system, developed by Bilkent University, uses a Bayesian classifier trained with a "bag of subregions" for each keyframe. The third system by the Middle East Technical University (METU) exploits textual information in the video using character recognition methodology. The system submitted to the search task is an interactive retrieval application developed by Queen Mary, University of London, University of Zilina and ITI from Thessaloniki, combining basic retrieval functionalities in various modalities (i.e. visual, audio, textual) with a user interface supporting the submission of queries using any combination of the available retrieval tools and the accumulation of relevant retrieval results over all queries submitted by a single user during a specified time interval. Finally, the rushes task submission comprises a video summarisation and browsing system specifically designed to intuitively and efficiently presents rushes material in video production environment. This system is a result of joint work of University of Bristol, Technical University of Delft and LaBRI, University of Bordeaux 1.
Open Access
The COST292 experimental framework for TRECVID 2007
(National Institute of Standards and Technology, 2007) Zhang, Q.; Corvaglia, M.; Aksoy, Selim; Naci, U.; Adami, N.; Aginako, N.; Alatan, A.; Alexandre, L. A.; Almeida, P.; Avrithis, Y.; Benois-Pineau, J.; Chandramouli, K.; Damnjanovic, U.; Esen, E.; Goya, J.; Grzegorzek, M.; Hanjalic, A.; Izquierdo, E.; Jarina, R.; Kapsalas, P.; Kompatsiaris, I.; Kuba, M.; Leonardi, R.; Makris, L.; Mansencal, B.; Mezaris, V.; Moumtzidou, A.; Mylonas, P.; Nikolopoulos, S.; Piatrik, T.; Pinheiro, A. M. G.; Reljin, B.; Spyrou, E.; Tolias, G.; Vrochidis, S.; Yakın, G.; Zajic, G.
In this paper, we give an overview of the four tasks submitted to TRECVID 2007 by COST292. In shot boundary (SB) detection task, four SB detectors have been developed and the results are merged using two merging algorithms. The framework developed for the high-level feature extraction task comprises four systems. The first system transforms a set of low-level descriptors into the semantic space using Latent Semantic Analysis and utilises neural networks for feature detection. The second system uses a Bayesian classifier trained with a "bag of subregions". The third system uses a multi-modal classifier based on SVMs and several descriptors. The fourth system uses two image classifiers based on ant colony optimisation and particle swarm optimisation respectively. The system submitted to the search task is an interactive retrieval application combining retrieval functionalities in various modalities with a user interface supporting automatic and interactive search over all queries submitted. Finally, the rushes task submission is based on a video summarisation and browsing system comprising two different interest curve algorithms and three features.
Open Access
A critique of Davidsonian theories of Metaphor
(2022-01) Gürsoy, Zeynep
With their rich imagery and unique effects they generate, metaphors have been used in a variety of discourse. But what are their functions in language and communication? Which mechanisms govern the metaphorical interpretation? These fundamental questions fueled dissensus between different theories of metaphor in philosophical and linguistic frameworks. In the emergence of this ongoing debate, Davidson’s rejection of a special category of metaphorical meaning and his characterization of metaphor in terms of a special effect had an influential role. Lepore and Stone side with the Davidsonian tradition. By stressing the creativity of the user against the conventionality of content, they argue that metaphorical content is open-ended and semantically indeterminate. Moreover, Lepore and Stone ground these arguments in their distinction between imagination and convention, as well as in the notion of conversational record, which are fundamental to their inquiry-based model of language and communication. In this thesis, I present a critique of Davidsonian theories of metaphor, by particularly focusing on their argument from open-endedness. I argue that we must distinguish between two types of metaphors: poetic/creative and ordinary. I claim that ordinary metaphors are not open-ended in the way Lepore and Stone understand them to be. By offering a new interpretation of open-endedness, I illustrate how literal content can, in this regard, be similar to metaphorical. To solve potential challenges of my radical view, rather than providing a pragmatic or contextualist account, I turn to Fillmore’s notion of frames and illustrate the role of information, embedded in lexical items, on our understanding of literal and metaphorical content.
Open Access
A database model for querying visual surveillance videos by integrating semantic and low-level features
(Springer, Berlin, Heidelberg, 2005) Şaykol, Ediz; Güdükbay, Uğur; Ulusoy, Özgür
Automated visual surveillance has emerged as a trendy application domain in recent years. Many approaches have been developed on video processing and understanding. Content-based access to surveillance video has become a challenging research area. The results of a considerable amount of work dealing with automated access to visual surveillance have appeared in the literature. However, the event models and the content-based querying and retrieval components have significant gaps remaining unfilled. To narrow these gaps, we propose a database model for querying surveillance videos by integrating semantic and low-level features. In this paper, the initial design of the database model, the query types, and the specifications of its query language are presented. © Springer-Verlag Berlin Heidelberg 2005.
Restricted
Dilbilim açısından anlambilim
(1972) Dizdaroğlu, Hikmet
Open Access
Directionally selective fractional wavelet transform using a 2-d non-separable unbalanced lifting structure
(Springer, Berlin, Heidelberg, 2012) Keskin, Furkan; Çetin, A. Enis
In this paper, we extend the recently introduced concept of fractional wavelet transform to obtain directional subbands of an image. Fractional wavelet decomposition is based on two-channel unbalanced lifting structures whereby it is possible to decompose a given discrete-time signal x[n] sampled with period T into two sub-signals x 1[n] and x 2[n] whose average sampling periods are pT and qT, respectively. Fractions p and q are rational numbers satisfying the condition: 1/p+1/q=1. Filters used in the lifting structure are designed using the Lagrange interpolation formula. 2-d separable and non-separable extensions of the proposed fractional wavelet transform are developed. Using a non-separable unbalanced lifting structure, directional subimages for five different directions are obtained. © 2012 Springer-Verlag.
Open Access
Effects of color pairs on warmth perception in interiors
(Society for Imaging Science and Technology, 2016-09) Ulusoy, B.; Olguntürk, N.
Warmth perception is a physical, emotional, semantic, and sensorial bond between people and their environments. Although the effects of single colors have been explored, there has been no research on how paired colors affect warmth perception in interiors. Therefore, the main aim of this study is to investigate these effects of colors and color pairs. Each model was assessed by 32 participants, totaling 96 different participants assessed the color models (Red, White, Green, and their pairs) under controlled conditions, both on a seven-point semantic differential scale and through open-ended questions. The results show that both single colors and paired colors affect warmth perception in interiors. White, Green, and Red are warmer than each other, respectively. Red appears to increase and White appears to decrease the warmth perception of their pairs in interiors. Another important finding of the study is that there is no effect of color location in paired colors. © Society for Imaging Science and Technology 2016.
Open Access
Evaluation of ontology enhancement tools
(Springer, 2005-10) Spiliopoulou, M.; Schaal, Markus; Müller, R. M.; Brunzel, M.
Mining algorithms can enhance the task of ontology establishment but methods are needed to assess the quality of their findings. Ontology establishment is a long-term interactive process, so it is important to evaluate the contribution of a mining tool at an early phase of this process so that only appropriate tools are used in later phases. We propose a method for the evaluation of such tools on their impact on ontology enhancement. We model impact as quality perceived by the expert and as statistical quality computed by an objective function. We further provide a mechanism that juxtaposes the two forms of quality. We have applied our method on an ontology enhancement tool and gained some interesting insights on the interplay between perceived impact and statistical quality. © 2006 Springer-Verlag.
Open Access
Example-based retargeting of human motion to arbitrary mesh models
(Blackwell Publishing Ltd, 2015) Celikcan, U.; Yaz I.O.; Capin, T.
We present a novel method for retargeting human motion to arbitrary 3D mesh models with as little user interaction as possible. Traditional motion-retargeting systems try to preserve the original motion, while satisfying several motion constraints. Our method uses a few pose-to-pose examples provided by the user to extract the desired semantics behind the retargeting process while not limiting the transfer to being only literal. Thus, mesh models with different structures and/or motion semantics from humanoid skeletons become possible targets. Also considering the fact that most publicly available mesh models lack additional structure (e.g. skeleton), our method dispenses with the need for such a structure by means of a built-in surface-based deformation system. As deformation for animation purposes may require non-rigid behaviour, we augment existing rigid deformation approaches to provide volume-preserving and squash-and-stretch deformations. We demonstrate our approach on well-known mesh models along with several publicly available motion-capture sequences. We present a novel method for retargeting human motion to arbitrary 3D mesh models with as little user interaction as possible. Traditional motion-retargeting systems try to preserve the original motion, while satisfying several motion constraints. Our method uses a few pose-to-pose examples provided by the user to extract the desired semantics behind the retargeting process while not limiting the transfer to being only literal. Thus, mesh models with different structures and/or motion semantics from humanoid skeletons become possible targets. © 2014 The Eurographics Association and John Wiley & Sons Ltd.