Research Outputs
Permanent URI for this communityhttps://hdl.handle.net/20.500.14288/2
Browse
312 results
Search Results
Publication Open Access 3D face recognition by projection based methods(Society of Photo-optical Instrumentation Engineers (SPIE), 2006) Dutaǧaci, Helin; Sankur, Bülent; Department of Computer Engineering; Yemez, Yücel; Faculty Member; Department of Computer Engineering; College of EngineeringIn this paper, we investigate recognition performances of various projection-based features applied on registered 3D scans of faces. Some features are data driven, such as ICA-based features or NNMF-based features. Other features are obtained using DFT or DCT-based schemes. We apply the feature extraction techniques to three different representations of registered faces, namely, 3D point clouds, 2D depth images and 3D voxel. We consider both global and local features. Global features are extracted from the whole face data, whereas local features are computed over the blocks partitioned from 2D depth images. The block-based local features are fused both at feature level and at decision level. The resulting feature vectors are matched using Linear Discriminant Analysis. Experiments using different combinations of representation types and feature vectors are conducted on the 3D-RMA dataset.
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, Yücel; 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 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; Özkasap, Öznur; Küpçü, 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 deep learning approach for data driven vocal tract area function estimation(IEEE, 2018) N/A; Department of Computer Engineering; Asadiabadi, Sasan; Erzin, Engin; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 34503In this paper we present a data driven vocal tract area function (VTAF) estimation using Deep Neural Networks (DNN). We approach the VTAF estimation problem based on sequence to sequence learning neural networks, where regression over a sliding window is used to learn arbitrary non-linear one-to-many mapping from the input feature sequence to the target articulatory sequence. We propose two schemes for efficient estimation of the VTAF; (1) a direct estimation of the area function values and (2) an indirect estimation via predicting the vocal tract boundaries. We consider acoustic speech and phone sequence as two possible input modalities for the DNN estimators. Experimental evaluations are performed over a large data comprising acoustic and phonetic features with parallel articulatory information from the USC-TIMIT database. Our results show that the proposed direct and indirect schemes perform the VTAF estimation with mean absolute error (MAE) rates lower than 1.65 mm, where the direct estimation scheme is observed to perform better than the indirect scheme.Publication Open Access A deep learning approach for data driven vocal tract area function estimation(Institute of Electrical and Electronics Engineers (IEEE), 2018) Department of Computer Engineering; Department of Electrical and Electronics Engineering; Erzin, Engin; Asadiabadi, Sasan; Faculty Member; Department of Computer Engineering; Department of Electrical and Electronics Engineering; College of Sciences; Graduate School of Sciences and Engineering; 34503; N/AIn this paper we present a data driven vocal tract area function (VTAF) estimation using Deep Neural Networks (DNN). We approach the VTAF estimation problem based on sequence to sequence learning neural networks, where regression over a sliding window is used to learn arbitrary non-linear one-to-many mapping from the input feature sequence to the target articulatory sequence. We propose two schemes for efficient estimation of the VTAF; (1) a direct estimation of the area function values and (2) an indirect estimation via predicting the vocal tract boundaries. We consider acoustic speech and phone sequence as two possible input modalities for the DNN estimators. Experimental evaluations are performed over a large data comprising acoustic and phonetic features with parallel articulatory information from the USC-TIMIT database. Our results show that the proposed direct and indirect schemes perform the VTAF estimation with mean absolute error (MAE) rates lower than 1.65 mm, where the direct estimation scheme is observed to perform better than the indirect scheme.Publication Open Access A gated fusion network for dynamic saliency prediction(Institute of Electrical and Electronics Engineers (IEEE), 2022) Kocak, Aysun; Erdem, Erkut; Department of Computer Engineering; Erdem, Aykut; Faculty Member; Department of Computer Engineering; College of Engineering; 20331Predicting saliency in videos is a challenging problem due to complex modeling of interactions between spatial and temporal information, especially when ever-changing, dynamic nature of videos is considered. Recently, researchers have proposed large-scale data sets and models that take advantage of deep learning as a way to understand what is important for video saliency. These approaches, however, learn to combine spatial and temporal features in a static manner and do not adapt themselves much to the changes in the video content. In this article, we introduce the gated fusion network for dynamic saliency (GFSalNet), the first deep saliency model capable of making predictions in a dynamic way via the gated fusion mechanism. Moreover, our model also exploits spatial and channelwise attention within a multiscale architecture that further allows for highly accurate predictions. We evaluate the proposed approach on a number of data sets, and our experimental analysis demonstrates that it outperforms or is highly competitive with the state of the art. Importantly, we show that it has a good generalization ability, and moreover, exploits temporal information more effectively via its adaptive fusion scheme.Publication Metadata only A novel economic-based scheduling heuristic for computational grids(Sage Publications Ltd, 2007) N/A; Department of Computer Engineering; Sönmez, Ömer Ozan; Gürsoy, Attila; Master Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 8745In the economic-based computational grids we need effective schedulers not only to minimize the makespan but also to minimize the costs that are spent for the execution of the jobs. in this work, A novel economy driven job scheduling heuristic is proposed and a simulation application is developed by using GridSim toolkit to investigate the performance of the heuristic. the simulation-based experiments demonstrate the effectiveness of the proposed heuristic both in terms of parameter sweep and sequential workflow type of applications.Publication Metadata only A novel test coverage metric for concurrently-accessed software components (A work-in-progress paper)(Springer-Verlag Berlin, 2006) N/A; Department of Computer Engineering; N/A; Department of Computer Engineering; Department of Computer Engineering; Taşıran, Serdar; Elmas, Tayfun; Bölükbaşı, Güven; Keremoğlu, M. Erkan; Faculty Member; PhD Student; Undergraduate Student; Reseacher; Department of Computer Engineering; College of Engineering; Graduate School of Sciences and Engineering; College of Engineering, College of Engineering; N/A; N/A; N/A; N/AWe propose a novel, practical coverage metric called "location pairs" (LP) for concurrently-accessed software components. The LP metric captures well common concurrency errors that lead to atomicity or refinement violations. We describe a software tool for measuring LP coverage and outline an inexpensive application of predicate abstraction and model checking for ruling out infeasible coverage targets.Publication Metadata only A prediction framework for fast sparse triangular solves(Springer International Publishing Ag, 2020) N/A; N/A; Department of Computer Engineering; Ahmad, Najeeb; Yılmaz, Buse; Erten, Didem Unat; PhD Student; N/A; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; N/A; College of Engineering; N/A; N/A; 219274Sparse triangular solve (SpTRSV) is an important linear algebra kernel, finding extensive uses in numerical and scientific computing. The parallel implementation of SpTRSV is a challenging task due to the sequential nature of the steps involved. This makes it, in many cases, one of the most time-consuming operations in an application. Many approaches for efficient SpTRSV on CPU and GPU systems have been proposed in the literature. However, no single implementation or platform (CPU or GPU) gives the fastest solution for all input sparse matrices. In this work, we propose a machine learning-based framework to predict the SpTRSV implementation giving the fastest execution time for a given sparse matrix based on its structural features. The framework is tested with six SpTRSV implementations on a state-of-the-art CPU-GPU machine (Intel Xeon Gold CPU, NVIDIA V100 GPU). Experimental results, with 998 matrices taken from the SuiteSparse Matrix Collection, show the classifier prediction accuracy of 87% for the fastest SpTRSV algorithm for a given input matrix. Predicted SpTRSV implementations achieve average speedups (harmonic mean) in the range of 1.4-2.7x against the six SpTRSV implementations used in the evaluation.