Creat membership Creat membership
Sign in

Forgot password?

  • Forgot password?
    Sign Up
  • Confirm
    Sign In
home > search

Now showing items 1 - 16 of 63

  • Recurrent Bag-of-Features for Visual Information Analysis

    Krestenitis, Marios   Passalis, Nikolaos   Iosifidis, Alexandros   Gabbouj, Moncef   Tefas, Anastasios  

    Download Collect
  • Complete Vector Quantization of Feedforward Neural Networks

    Floropoulos, Nikolaos   Tefas, Anastasios  

    Download Collect
  • Deep autoencoders for attribute preserving face de-identification

    Nousi, Paraskevi   Papadopoulos, Sotirios   Tefas, Anastasios   Pitas, Ioannis  

    Download Collect
  • Variance-preserving deep metric learning for content-based image retrieval

    Passalis, Nikolaos   Iosifidis, Alexandros   Gabbouj, Moncef   Tefas, Anastasios  

    Download Collect
  • Caricature generation utilizing the notion of anti-face

    Gogousis, Vlasis   Tefas, Anastasios  

    The production of caricatures is a particularly interesting field of art, because it aims to highlight the very essence of a given face. Caricature generation systems traditionally rely on two approaches: they either follow extracted rules through learning algorithms, or follow rules that were directly programmed by experts. This paper attempts to reduce the reliance on heuristic methods, by proposing a novel method that provides a set of well-defined rules, which can be put to use for the purpose of caricature generation. The method is based on the notion of anti-face in conjunction with unbiased distortions. In addition, we indicate the usefulness of the anti-face as a means to perceive, for our own sake, the degree to which our face seems peculiar to others. Finally, we deploy a reverse variant of the method in order to attain beautification.
    Download Collect
  • Dimensionality Reduction Using Similarity-Induced Embeddings

    Passalis, Nikolaos   Tefas, Anastasios  

    The vast majority of dimensionality reduction (DR) techniques rely on the second-order statistics to define their optimization objective. Even though this provides adequate results in most cases, it comes with several shortcomings. The methods require carefully designed regularizers and they are usually prone to outliers. In this paper, a new DR framework that can directly model the target distribution using the notion of similarity instead of distance is introduced. The proposed framework, called similarity embedding framework (SEF), can overcome the aforementioned limitations and provides a conceptually simpler way to express optimization targets similar to existing DR techniques. Deriving a new DR technique using the SEF becomes simply a matter of choosing an appropriate target similarity matrix. A variety of classical tasks, such as performing supervised DR and providing out-of-sample extensions, as well as, new novel techniques, such as providing fast linear embeddings for complex techniques, are demonstrated in this paper using the proposed framework. Six data sets from a diverse range of domains are used to evaluate the proposed method and it is demonstrated that it can outperform many existing DR techniques.
    Download Collect
  • Big Data Clustering with Kernel k-Means: Resources, Time and Performance

    Tsapanos, Nikolaos   Tefas, Anastasios   Nikolaidis, Nikolaos   Pitas, Ioannis  

    Data clustering is an unsupervised learning task that has found many applications in various scientific fields. The goal is to find subgroups of closely related data samples (clusters) in a set of unlabeled data. A classic clustering algorithm is the so-called k-Means. It is very popular, however, it is also unable to handle cases in which the clusters are not linearly separable. Kernel k-Means is a state of the art clustering algorithm, which employs the kernel trick, in order to perform clustering on a higher dimensionality space, thus overcoming the limitations of classic k-Means regarding the non-linear separability of the input data. With respect to the challenges of Big Data research, a field that has established itself in the last few years and involves performing tasks on extremely large amounts of data, several adaptations of the Kernel k-Means have been proposed, each of which has different requirements in processing power and running time, while also incurring different trade-offs in performance. In this paper, we present several issues and techniques involving the usage of Kernel k-Means for Big Data clustering and how the combination of each component in a clustering framework fares in terms of resources, time and performance. We use experimental results, in order to evaluate several combinations and provide a recommendation on how to approach a Big Data clustering problem.
    Download Collect
  • Femtojoule per MAC Neuromorphic Photonics: An Energy and Technology Roadmap

    Totovic, Angelina R.   Dabos, George   Passalis, Nikolaos   Tefas, Anastasios   Pleros, Nikos  

    Download Collect
  • Learning Neural Bag-of-Features for Large-Scale Image Retrieval

    Passalis, Nikolaos   Tefas, Anastasios  

    In this paper, the well-known bag-of-features (BoFs) model is generalized and formulated as a neural network that is composed of three layers: 1) a radial basis function (RBF) layer; 2) an accumulation layer; and 3) a fully connected layer. This formulation allows for decoupling the representation size from the number of used codewords, as well as for better modeling the feature distribution using a separate trainable scaling parameter for each RBF neuron. The resulting network, called retrievaloriented neural BoF (RN-BoF), is trained using regular back propagation and allows for fast extraction of compact image representations. It is demonstrated that the RN-BoF model is capable of: 1) increasing the object encoding and retrieval speed; 2) reducing the extracted representation size; and 3) increasing the retrieval precision. A symmetry-aware spatial segmentation technique is also proposed to further reduce the encoding time and the storage requirements and allows the method to efficiently scale to large datasets. The proposed method is evaluated and compared to other state-of-the-art techniques using five different image datasets, including the large-scale YouTube Faces database.
    Download Collect
  • Deep Reinforcement Learning for Controlling Frontal Person Close-up Shooting

    Passalis, Nikolaos   Tefas, Anastasios  

    Download Collect
  • Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks

    Passalis, Nikolaos   Tefas, Anastasios  

    Convolutional Neural Networks (CNNs) are well established models capable of achieving state-of-the-art classification accuracy for various computer vision tasks. However, they are becoming increasingly larger, using millions of parameters, while they are restricted to handling images of fixed size. In this paper, a quantization-based approach, inspired from the well-known Bag-of-Features model, is proposed to overcome these limitations. The proposed approach, called Convolutional BoF (CBoF), uses RBF neurons to quantize the information extracted from the convolutional layers and it is able to natively classify images of various sizes as well as to significantly reduce the number of parameters in the network. In contrast to other global pooling operators and CNN compression techniques the proposed method utilizes a trainable pooling layer that it is end-to-end differentiable, allowing the network to be trained using regular back-propagation and to achieve greater distribution shift invariance than competitive methods. The ability of the proposed method to reduce the parameters of the network and increase the classification accuracy over other state-of-the-art techniques is demonstrated using three image datasets.
    Download Collect
  • Discriminatively Trained Autoencoders for Fast and Accurate Face Recognition

    Nousi, Paraskevi   Tefas, Anastasios  

    Accurate face recognition is vital in person identification tasks and may serve as an auxiliary tool to opportunistic video shooting using Unmanned Aerial Vehicles (UAVs). However, face recognition methods often require complex Machine Learning algorithms to be effective, making them inefficient for direct utilization in UAVs and other machines with low computational resources. In this paper, we propose a method of training Autoencoders (AEs) where the low-dimensional representation is learned in a way such that the various classes are more easily discriminated. Results on the ORL and Yale datasets indicate that the proposed AEs are capable of producing low-dimensional representations with enough discriminative ability such that the face recognition accuracy achieved by simple, lightweight classifiers surpasses even that achieved by more complex models.
    Download Collect
  • Graph Embedded Extreme Learning Machine

    Iosifidis, Alexandros   Tefas, Anastasios   Pitas, Ioannis  

    In this paper, we propose a novel extension of the extreme learning machine (ELM) algorithm for single-hidden layer feedforward neural network training that is able to incorporate subspace learning (SL) criteria on the optimization process followed for the calculation of the network's output weights. The proposed graph embedded ELM (GEELM) algorithm is able to naturally exploit both intrinsic and penalty SL criteria that have been (or will be) designed under the graph embedding framework. In addition, we extend the proposed GEELM algorithm in order to be able to exploit SL criteria in arbitrary (even infinite) dimensional ELM spaces. We evaluate the proposed approach on eight standard classification problems and nine publicly available datasets designed for three problems related to human behavior analysis, i.e., the recognition of human face, facial expression, and activity. Experimental results denote the effectiveness of the proposed approach, since it outperforms other ELM-based classification schemes in all the cases.
    Download Collect
  • Visual Voice Activity Detection in the Wild

    Patrona, Foteini   Iosifidis, Alexandros   Tefas, Anastasios   Nikolaidis, Nikolaos   Pitas, Ioannis  

    The visual voice activity detection (V-VAD) problem in unconstrained environments is investigated in this paper. A novel method for V-VAD in the wild, exploiting local shape and motion information appearing at spatiotemporal locations of interest for facial video segment description and the bag of words model for facial video segment representation, is proposed. Facial video segment classification is subsequently performed using the state-of-the-art classification algorithms. Experimental results on one publicly available V-VAD dataset denote the effectiveness of the proposed method, since it achieves better generalization performance in unseen users, when compared to the recently proposed state-of-the-art methods. Additional results on a new unconstrained dataset provide evidence that the proposed method can be effective even in such cases in which any other existing method fails.
    Download Collect
  • Big Data Analysis for Media Production

    Blat, Josep   Evans, Alun   Kim, Hansung   Imre, Evren   Polok, Lukas   Ila, Viorela   Nikolaidis, Nikos   Zemcik, Pavel   Tefas, Anastasios   Smrz, Pavel   Hilton, Adrian   Pitas, Ioannis  

    A typical high-end film production generates several terabytes of data per day, either as footage from multiple cameras or as background information regarding the set (laser scans, spherical captures, etc). This paper presents solutions to improve the integration of the multiple data sources, and understand their quality and content, which are useful both to support creative decisions on-set (or near it) and enhance the postproduction process. The main cinema specific contributions, tested on a multisource production dataset made publicly available for research purposes, are the monitoring and quality assurance of multicamera set-ups, multisource registration and acceleration of 3-D reconstruction, anthropocentric visual analysis techniques for semantic content annotation, and integrated 2-D-3-D web visualization tools. We discuss as well improvements carried out in basic techniques for acceleration, clustering and visualization, which were necessary to deal with the very large multisource data, and can be applied to other big data problems in diverse application fields.
    Download Collect
  • Graph Embedded One-Class Classifiers for media data classification

    Mygdalis, Vasileios   Iosifidis, Alexandros   Tefas, Anastasios   Pitas, Ioannis  

    This paper introduces the Graph Embedded One-Class Support Vector Machine and Graph Embedded Support Vector Data Description methods. These methods constitute novel extensions of the One-Class Support Vectors Machines and Support Vector Data Description, incorporating generic graph structures that express geometric data relationships of interest in their optimization process. Local or global relationships between the training patterns can be expressed with single graphs or combinations of fully connected and kNN graphs. We show that the adoption of generic geometric class information acts as a regularizer to the solution of the original methods. Moreover, we prove that the regularized solutions for both. One-Class Support Vector Machine and Support Vector Data Description are equivalent to applying the original methods in a transformed (and shared) feature space. Qualitative and quantitative evaluation of the proposed methods shows that they compare favorably to the standard OC-SVM and SVDD classifiers, respectively. (C) 2016 Elsevier Ltd. All rights reserved.
    Download Collect
1 2 3 4


If you have any feedback, Please follow the official account to submit feedback.

Turn on your phone and scan

Submit Feedback