Publications without Fulltext
Permanent URI for this collectionhttps://hdl.handle.net/20.500.14288/3
Browse
Publication Metadata only 3D articulated shape segmentation using motion information(Institute of Electrical and Electronics Engineers (IEEE), 2010) Department of Computer Engineering; N/A; Yemez, YĆ¼cel; Kalafatlar, Emre; Faculty Member; Master Student; Department of Computer Engineering; College of Engineering; Graduate School of Sciences and Engineering; 107907; N/AWe present a method for segmentation of articulated 3D shapes by incorporating the motion information obtained from time-varying models. We assume that the articulated shape is given in the form of a mesh sequence with fixed connectivity so that the inter-frame vertex correspondences, hence the vertex movements, are known a priori. We use different postures of an articulated shape in multiple frames to constitute an affinity matrix which encodes both temporal and spatial similarities between surface points. The shape is then decomposed into segments in spectral domain based on the affinity matrix using a standard K-means clustering algorithm. The performance of the proposed segmentation method is demonstrated on the mesh sequence of a human actor.Publication Metadata only 3D face recognition(Institute of Electrical and Electronics Engineers (IEEE), 2006) DutaĒ§aci, H.; Sankur, B.; Department of Computer Engineering; Yemez, YĆ¼cel; Faculty Member; Department of Computer Engineering; College of Engineering; 107907In this paper, we compare face recognition performances of various features applied on registered 3D scans of faces. The features we compare are DFT or DCT- based features, ICA-based features and NNMF-based features. We apply the feature extraction techniques to three different representations of registered faces: 3D point clouds, 2D depth images and 3D voxel representations. We also consider block-based DFT or DCT-based local features on 2D depth images and their fusion schemes. Experiments using different combinations of representation types and feature vectors are conducted on the 3D-RMA dataset. / Bu bildiride, kayıtlı 3B yĆ¼z taramalarında uygulanan ƧeÅitli ƶzelliklerin yĆ¼z tanıma performanslarını karÅılaÅtırıyoruz. KarÅılaÅtırdıÄımız ƶzellikler, DFT veya DCT tabanlı ƶzellikler, ICA tabanlı ƶzellikler ve NNMF tabanlı ƶzelliklerdir. Ćznitelik Ƨıkarma tekniklerini kayıtlı yĆ¼zlerin Ć¼Ć§ farklı temsiline uyguluyoruz: 3B nokta bulutları, 2B derinlik gƶrĆ¼ntĆ¼leri ve 3B voksel temsilleri. Ayrıca, 2D derinlik gƶrĆ¼ntĆ¼leri ve bunların fĆ¼zyon Åemaları Ć¼zerindeki blok tabanlı DFT veya DCT tabanlı yerel ƶzellikleri de dikkate alıyoruz. 3D-RMA veri seti Ć¼zerinde farklı temsil tĆ¼rleri ve ƶzellik vektƶrleri kombinasyonları kullanılarak deneyler yapılmıÅtır.Publication Metadata only 3D isometric shape correspondence(IEEE, 2010) Department of Computer Engineering; Yemez, YĆ¼cel; SahillioÄlu, Yusuf; Faculty Member; PhD Student; Department of Computer Engineering; College of Engineering; Graduate School of Sciences and Engineering; 107907; 215195We address the problem of correspondence between 3D isometric shapes. We present an automatic method that finds the optimal correspondence between two given (nearly) isometric shapes by minimizing the amount of deviation from isometry. We optimize the isometry error in two steps. In the first step, the 3D points uniformly sampled from the shape surfaces are transformed into spectral domain based on geodesic affinity, where the isometry errors are minimized in polynomial time by complete bipartite graph matching. The second step of optimization, which is well-initialized by the resulting correspondence of the first step, explicitly minimizes the isometry cost via an iterative greedy algorithm in the original 3D Euclidean space. Our method is put to test using (nearly) isometric pairs of shapes and its performance is measured via ground-truth correspondence information when available.Publication Metadata only 3D model retrieval using probability density-based shape descriptors(IEEE Computer Society, 2009) Akgul, Ceyhun Burak; Sankur, Buelent; Schmitt, Francis; Department of Computer Engineering; Yemez, YĆ¼cel; Faculty Member; Department of Computer Engineering; College of Engineering; 107907We address content-based retrieval of complete 3D object models by a probabilistic generative description of local shape properties. The proposed shape description framework characterizes a 3D object with sampled multivariate probability density functions of its local surface features. This density-based descriptor can be efficiently computed via kernel density estimation (KDE) coupled with fast Gauss transform. The nonparametric KDE technique allows reliable characterization of a diverse set of shapes and yields descriptors which remain relatively insensitive to small shape perturbations and mesh resolution. Density-based characterization also induces a permutation property which can be used to guarantee invariance at the shape matching stage. As proven by extensive retrieval experiments on several 3D databases, our framework provides state-of-the-art discrimination over a broad and heterogeneous set of shape categories.Publication Metadata only 3D object matching via multivariate shape distributions(Institute of Electrical and Electronics Engineers (IEEE), 2005) AkgĆ¼l, C.B.; Sankur, B.; Schmitt, F.; Department of Computer Engineering; Yemez, YĆ¼cel; Faculty Member; Department of Computer Engineering; College of Engineering; 1079073B nesne eÅleÅtirme literatĆ¼rĆ¼nde, problemi Åekil daÄılımlarının karÅılaÅtırılmasına indirgeyen yƶntemler bulunmaktadır. Åekil daÄılımı, 3B nesne yĆ¼zeyi Ć¼zerinde hesaplanan bir iÅlevin deÄerlerinin olasılık daÄılımı olarak tanımlanır. Bu ƧalıÅmada varolan yƶntemi, birden Ƨok iÅlevin getirdiÄi Åekil bilgisinden aynı anda yararlanacak Åekilde geniÅletiyoruz. Ćokboyutlu Åekil daÄılımları adını verdiÄimiz bu 3B nesne betimleyicilerini, ƶrnek bir 3B nesne veri tabanındaki nesneler iƧin parametrik olmayan yaklaÅımlarla kestiriyor, karÅılaÅtırmaları alternatif metrikler yoluyla yapıyoruz. Elde edilen kesinlik-geri getirme eÄrileri Ƨokboyutlu Åekil daÄılımlarının karÅılaÅtırılmasının yeni bir 3B nesne eÅleÅtirme paradigması olabileceÄini gƶstermektedir.Publication Metadata only 3D progressive compression with octree particles(Akademische Verlagsgesellsch Aka Gmbh, 2002) Schmitt, Francis; Department of Computer Engineering; N/A; Yemez, YĆ¼cel; Faculty Member; Department of Computer Engineering; College of Engineering; N/A; 107907; N/AThis paper improves the storage efficiency of the progressive particle-based modeling scheme presented in [14, 15] by using entropy coding techniques. This scheme encodes the surface geometry and attributes in terms of appropriately ordered oc-tree particles, which can then progressively be decoded and rendered by the-viewer by means of a fast direct triangulation technique. With the introduced entropy coding technique, the bitload of the multi-level representation for geometry encoding reduces to 9-14 bits per particle (or 4.5-7 bits per triangle) for 12-bit quantized geometry.Publication Metadata only 3D reconstruction of real objects with high resolution shape and texture(Elsevier, 2004) Schmitt, F; Department of Computer Engineering; Yemez, YĆ¼cel; Faculty Member; Department of Computer Engineering; College of Engineering; 107907We present a robust and accurate system for 3D reconstruction of real objects with high resolution shape and texture. Our reconstruction method is passive, the only information needed being 2D images obtained with a calibrated camera from different view angles as the object rotates on a turntable. The triangle surface model is obtained by a scheme combining octree construction and marching cubes algorithm, which is adapted to the shape from silhouette problem. We develop a texture mapping strategy based on surface particles to adequately address photography related problems such as inhomogeneous lighting, highlights and occlusion. Reconstruction results are included to demonstrate the attained quality.Publication Metadata only 3D shape correspondence by isometry-driven greedy optimization(IEEE Computer Soc, 2010) N/A; Department of Computer Engineering; SahillioÄlu, Yusuf; Yemez, YĆ¼cel; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; 215195; 107907We present an automatic method that establishes 3D correspondence between isometric shapes. Our goal is to find an optimal correspondence between two given (nearly) isometric shapes, that minimizes the amount of deviation from isometry. We cast the problem as a complete surface correspondence problem. Our method first divides the given shapes to be matched into surface patches of equal area and then seeks for a mapping between the patch centers which we refer to as base vertices. Hence the correspondence is established in a fast and robust manner at a relatively coarse level as imposed by the patch radius. We optimize the isometry cost in two steps. in the first step, the base vertices are transformed into spectral domain based on geodesic affinity, where the isometry errors are minimized in polynomial time by complete bipartite graph matching. the resulting correspondence serves as a good initialization for the second step of optimization in which we explicitly minimize the isometry cost via an iterative greedy algorithm in the original 3D Euclidean space. We demonstrate the performance of our method on various isometric (or nearly isometric) pairs of shapes for some of which the ground-truth correspondence is available.Publication Metadata only 3D Shape recovery and tracking from multi-camera video sequences via surface deformation(IEEE, 2006) Skala, V.; N/A; Department of Computer Engineering; SahillioÄlu, Yusuf; Yemez, YĆ¼cel; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; 215195; 107907This paper addresses 3D reconstruction and modeling of time-varying real objects using multicamera video. The work consists of two phases. In the first phase, the initial shape of the object is recovered from its silhouettes using a surface deformation model. The same deformation model is also employed in the second phase to track the recovered initial shape through the time-varying silhouette information by surface evolution. The surface deformation/evolution model allows us to construct a spatially and temporally smooth surface mesh representation having fixed connectivity. This eventually leads to an overall space-time representation that preserves the semantics of the underlying motion and that is much more efficient to process, to visualize, to store and to transmit.Publication Metadata only 3D shape recovery and tracking from multi-camera video sequences via surface deformation(Institute of Electrical and Electronics Engineers (IEEE), 2006) Skala, V.; N/A; Department of Computer Engineering; SahillioÄlu, Yusuf; Yemez, YĆ¼cel; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; 215195; 107907This paper addresses 3D reconstruction and modeling of time-varying real objects using multicamera video. The work consists of two phases. In the first phase, the initial shape of the object is recovered from its silhouettes using a surface deformation model. The same deformation model is also employed in the second phase to track the recovered initial shape through the time-varying silhouette information by surface evolution. The surface deformation/evolution model allows us to construct a spatially and temporally smooth surface mesh representation having fixed connectivity. This eventually leads to an overall space-time representation that preserves the semantics of the underlying motion and that is much more efficient to process, to visualize, to store and to transmit. / Bu makale, Ƨok kameralı video kullanarak zamanla deÄiÅen gerƧek nesnelerin 3B yeniden yapılandırılmasını ve modellenmesini ele almaktadır. ĆalıÅma iki aÅamadan oluÅmaktadır. Ä°lk aÅamada, nesnenin ilk Åekli, bir yĆ¼zey deformasyon modeli kullanılarak silĆ¼etlerinden kurtarılır. Aynı deformasyon modeli, ikinci aÅamada, yĆ¼zey evrimi yoluyla zamanla deÄiÅen siluet bilgisi yoluyla geri kazanılan ilk Åekli izlemek iƧin de kullanılır. YĆ¼zey deformasyonu/evrimi modeli, sabit baÄlantıya sahip uzamsal ve zamansal olarak pĆ¼rĆ¼zsĆ¼z bir yĆ¼zey aÄ temsili oluÅturmamıza izin verir. Bu, sonunda, altta yatan hareketin anlamını koruyan ve iÅlemesi, gƶrselleÅtirmesi, depolaması ve iletmesi Ƨok daha verimli olan genel bir uzay-zaman temsiline yol aƧar.Publication Metadata only A calculus of atomic actions(N/A, 2009) Qadeer, Shaz; N/A; Department of Computer Engineering; Elmas, Tayfun; TaÅıran, Serdar; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; N/AWe present a proof calculus and method for the static verification of assertions and procedure specifications in shared-memory concurrent programs. The key idea in our approach is to use atomicity as a proof tool and to simplify the verification of assertions by rewriting programs to consist of larger atomic actions. We propose a novel, iterative proof style in which alternating use of abstraction and reduction is exploited to compute larger atomic code blocks in a sound manner. This makes possible the verification of assertions in the transformed program by simple sequential reasoning within atomic blocks, or significantly simplified application of existing concurrent program verification techniques such as the Owicki-Gries or rely-guarantee methods. Our method facilitates a clean separation of concerns where at each phase of the proof, the user worries only about only either the sequential properties or the concurrency control mechanisms in the program. We implemented our method in a tool called QED.We demonstrate the simplicity and effectiveness of our approach on a number of benchmarks including ones with intricate concurrency protocols.Publication Metadata only A chain-binomial model for pull and push-based information diffusion(IEEE, 2006) Department of Mathematics; Department of Computer Engineering; ĆaÄlar, Mine; Ćzkasap, Ćznur; Faculty Member; Faculty Member; Department of Mathematics; Department of Computer Engineering; College of Sciences; College of Engineering; 105131; 113507We compare pull and push-based epidemic paradigms for information diffusion in large scale networks. Key benefits of these approaches are that they are fully distributed, utilize local information only via pair-wise interactions, and provide eventual consistency, scalability and communication topology-independence, which make them suitable for peer-to-peer distributed systems. We develop a chain-Binomial epidemic probability model for these algorithms. Our main contribution is the exact computation of message delivery latency observed by each peer, which corresponds to a first passage time of the underlying Markov chain. Such an analytical tool facilitates the comparison of pull and push-based spread for different group sizes, initial number of infectious peers and fan-out values which are also accomplished in this study. Via our analytical stochastic model, we show that push-based approach is expected to facilitate faster information spread both for the whole group and as experienced by each member.Publication Metadata only A classification and performance comparison of mobility models for ad hoc networks(Springer-Verlag Berlin, 2006) N/A; Department of Computer Engineering; Atsan, Emre; Ćzkasap, Ćznur; Master Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 113507In mobile ad hoc network research, simulation plays an important role in determining the network characteristics and measuring performance. On the other hand, unrealistic simulation conditions may be misleading, instead of being explanatory. For this reason, constructing simulation models closer to the real circumstances is very significant. Movement behavior of mobile entities is one of the most important concepts for the realistic simulation scenarios in mobile ad hoc networks. In this study, we first provide a survey and a new hybrid classification of existing mobility models in the literature. We implemented the random direction and boundless simulation area models on Scalable Wireless Ad Hoc Network Simulator (SWANS) and conducted simulations of Ad Hoc On-Demand Distance Vector (AODV) protocol for these as well as the random walk and random waypoint models. Our comparative results for the mobility models are discussed on a variety of simulation settings and parameters.Publication Metadata only A classification of concurrency bugs in java benchmarks by developer intent(Association for Computing Machinery (ACM), 2006) Department of Computer Engineering; Department of Computer Engineering; N/A; KeremoÄlu, M. Erkan; TaÅıran, Serdar; Elmas, Tayfun; Researcher; Faculty Member; PhD Student; Department of Computer Engineering; College of Engineering; College of Engineering; Graduate School of Sciences and Engineering; N/A; N/A; N/AThis work addresses the issue of selecting the formal correctness criterion for a concurrent Java program that best corresponds to the developer's intent. We study a set of concurrency-related bugs detected in Java benchmarks reported in the literature. On these programs, we determine whether race-freedom, atomicity or refinement is the simplest and most appropriate criterion for program correctness. Our purpose is to demonstrate empirically the fact that the appropriate fix for a concurrency error and the selection of a program analysis tool for detecting such an error must be based on the proper expression of the designer's intent using a formal correctness criterion.Publication Metadata only A combined interval and floating-point comparator/selector(IEEE Computer Soc, 2002) Department of Computer Engineering; AkkaÅ, Ahmet; Faculty Member; Department of Computer Engineering; College of Engineering; N/AInterval arithmetic provides a robust method for automatically monitoring numerical errors and can be used to solve problems that cannot be efficiently solved with floating-point arithmetic. This paper presents the design and implementation of a combined interval and floating-point comparator/selector, which performs interval intersection, hull, mignitude, magnitude, minimum, maximum, and comparisons, As well as floating-point minimum, maximum and comparisons. area and delay estimates indicate that the combined interval and floating-point comparator/selector has 98% more area and a worst case delay that is 42% greater than a conventional floating point comparator/selector. the combined interval and floating-point comparator/selector greatly improves the performance of interval selection operations.Publication Metadata only A combined interval and floating-point reciprocal unit(IEEE, 2005) N/A; N/A; Department of Computer Engineering; KĆ¼Ć§Ć¼kkabak, Umut; AkkaÅ, Ahmet; Master Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/AInterval arithmetic is one technique for accurate and reliable computing. Among interval arithmetic operations, division is the most time consuming operation. This paper presents the design and implementation of a combined interval and floating-point reciprocal unit. To compute the reciprocal of an operand, an initial approximation is computed first and then iterated twice by Newton-Raphson iteration. The combined interval and floating-point reciprocal unit computes the reciprocal of a double precision floating-point number in eleven clock cycles and the reciprocal of an interval in twenty-one clock cycles. The unit is implemented in VHDL and synthesized to estimate the area and the worst case delay. Simulation results showed that the least significant bit of the floating-point result cannot be guaranteed to be same for all cases compared to the result based on an infinite precision. For interval reciprocal, however, the true result is contained in the result interval.Publication Metadata only A comparison of data representation types, feature types and fusion techniques for 3D face biometry(European Association for Signal Processing, 2006) DutaĒ§aci, H.; Sankur, B.; Department of Computer Engineering; Yemez, YĆ¼cel; Faculty Member; Department of Computer Engineering; College of Engineering; 107907This paper focuses on the problems of person identification and authentication using registered 3D face data. The face surface geometry is represented alternately as a point cloud, a depth image or as voxel data. Various local or global feature sets are extracted, such as DFT/DCT coefficients, ICA- and NMF- projections, which results in a rich repertoire of representations/features. The identification and authentication performance of the individual schemes are compared. Fusion schemes are invoked, to improve the performance especially in the case when there are only few samples per subject.Publication Metadata only A computational-graph partitioning method for training memory-constrained DNNs(Elsevier, 2021) Wahib, Mohamed; Dikbayir, Doga; Belviranli, Mehmet Esat; N/A; Department of Computer Engineering; Qararyah, Fareed Mohammad; Erten, Didem Unat; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 219274Many state-of-the-art Deep Neural Networks (DNNs) have substantial memory requirements. Limited device memory becomes a bottleneck when training those models. We propose ParDNN, an automatic, generic, and non-intrusive partitioning strategy for DNNs that are represented as computational graphs. ParDNN decides a placement of DNN's underlying computational graph operations across multiple devices so that the devices' memory constraints are met and the training time is minimized. ParDNN is completely independent of the deep learning aspects of a DNN. It requires no modification neither at the model nor at the systems level implementation of its operation kernels. ParDNN partitions DNNs having billions of parameters and hundreds of thousands of operations in seconds to few minutes. Our experiments with TensorFlow on 16 GPUs demonstrate efficient training of 5 very large models while achieving superlinear scaling for both the batch size and training throughput. ParDNN either outperforms or qualitatively improves upon the related work.Publication Metadata only A containerized proof-of-concept implementation of LightChain system(Ieee, 2020) N/A; N/A; Department of Computer Engineering; N/A; Department of Computer Engineering; Department of Computer Engineering; Hassanzadeh-Nazarabadi, Yahya; Nayal, Nazir; Hamdan, Shadi Sameh; Ćzkasap, Ćznur; KĆ¼pĆ§Ć¼, Alptekin; PhD Student; Faculty Member; Master Student; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; N/A; N/A; 113507; 168060LightChain is the first Distributed Hash Table (DHT)-based blockchain with a logarithmic asymptotic message and memory complexity. In this demo paper, we present the software architecture of our open-source implementation of LightChain, as well as a novel deployment scenario of the entire LightChain system on a single machine aiming at results reproducibility.Publication Metadata only A corpus for computational research of Turkish makam music(Association for Computing Machinery, 2014) Uyar, Burak; Atli, Hasan Sercan; ÅentĆ¼rk, Sertan; Serra, Xavier; Department of Computer Engineering; Bozkurt, BarıÅ; Faculty Member; Department of Computer Engineering; College of Engineering; N/AEach music tradition has its own characteristics in terms of melodic, rhythmic and timbral properties as well as semantic understandings. To analyse, discover and explore these culture-specific characteristics, we need music collections which are representative of the studied aspects of the music tradition. For Turkish makam music, there are various resources available such as audio recordings, music scores, lyrics and Editorial material metadata. However, most of these resources are not typically suited for computational analysis, are hard to access, do not have sufficient quality or do not include adequate descriptive information. In this paper we present a corpus of Turkish makam music created within the scope of the CompMusic project. The corpus is intended for computational research and the primary considerations during the creation of the corpus reflect some criteria, namely, purpose, coverage, completeness, quality and re-usability. So far, we have gathered approximately 6000 audio recordings, 2200 music scores with lyrics and 27000 instances of Editorial material metadata related to Turkish makam music. The metadata include information about makams, recordings, scores, compositions, artists etc. as well as the interrelations between them. In this paper, we also present several test datasets of Turkish makam music. Test datasets contain manual annotations by experts and they provide ground truth for specific computational tasks to test, calibrate and improve the research tools. We hope that this research corpus and the test datasets will facilitate academic studies in several fields such as music information retrieval and computational musicology.