Página 15 dos resultados de 471 itens digitais encontrados em 0.070 segundos

Automated illustration of multimedia stories

Delgado, Diogo Miguel Melo
Fonte: Faculdade de Ciências e Tecnologia Publicador: Faculdade de Ciências e Tecnologia
Tipo: Dissertação de Mestrado
Publicado em //2010 Português
Relevância na Pesquisa
370.54918%
Submitted in part fulfillment of the requirements for the degree of Master in Computer Science; We all had the problem of forgetting about what we just read a few sentences before. This comes from the problem of attention and is more common with children and the elderly. People feel either bored or distracted by something more interesting. The challenge is how can multimedia systems assist users in reading and remembering stories? One solution is to use pictures to illustrate stories as a mean to captivate ones interest as it either tells a story or makes the viewer imagine one. This thesis researches the problem of automated story illustration as a method to increase the readers’ interest and attention. We formulate the hypothesis that an automated multimedia system can help users in reading a story by stimulating their reading memory with adequate visual illustrations. We propose a framework that tells a story and attempts to capture the readers’ attention by providing illustrations that spark the readers’ imagination. The framework automatically creates a multimedia presentation of the news story by (1) rendering news text in a sentence by-sentence fashion, (2) providing mechanisms to select the best illustration for each sentence and (3) select the set of illustrations that guarantees the best sequence. These mechanisms are rooted in image and text retrieval techniques. To further improve users’ attention...

An Iterative Framework for EEG-based Image Search: Robust Retrieval with Weak Classifiers

Ušćumlić, Marija; Chavarriaga, Ricardo; Millán, José del R.
Fonte: Public Library of Science Publicador: Public Library of Science
Tipo: Artigo de Revista Científica
Publicado em 20/08/2013 Português
Relevância na Pesquisa
370.54918%
We revisit the framework for brain-coupled image search, where the Electroencephalography (EEG) channel under rapid serial visual presentation protocol is used to detect user preferences. Extending previous works on the synergy between content-based image labeling and EEG-based brain-computer interface (BCI), we propose a different perspective on iterative coupling. Previously, the iterations were used to improve the set of EEG-based image labels before propagating them to the unseen images for the final retrieval. In our approach we accumulate the evidence of the true labels for each image in the database through iterations. This is done by propagating the EEG-based labels of the presented images at each iteration to the rest of images in the database. Our results demonstrate a continuous improvement of the labeling performance across iterations despite the moderate EEG-based labeling (AUC <75%). The overall analysis is done in terms of the single-trial EEG decoding performance and the image database reorganization quality. Furthermore, we discuss the EEG-based labeling performance with respect to a search task given the same image database.

NPSNET vehicle database: an object-oriented database in a real-time vehicle simulation

Borden Davis, Susan C.
Fonte: Monterey, California. Naval Postgraduate School Publicador: Monterey, California. Naval Postgraduate School
Tipo: Tese de Doutorado
Português
Relevância na Pesquisa
370.54918%
Approved for public release; distribution is unlimited.; The Naval Postgraduate School has actively explored the design and implementation of NPSNET, a real-time three-dimensional simulator on low-cost, readily accessible workstations. NPSNET involves a tremendous amount of interaction between vehicle, terrain, obstacle and ordnance objects in a dynamic simulation system. There exists a need for an organized, efficient storage structure that allows real-time retrieval of objects and their interactive relationships. This work concentrates on selection and design of a vehicle database model to maximize storage and real-time retrieval of data for the NPSNET visual simulator. The results of this effort can be applied to the overall system, NPSNET, in a distributed database management system.

Associative Memories Based on Multiple-Valued Sparse Clustered Networks

Jarollahi, Hooman; Onizawa, Naoya; Hanyu, Takahiro; Gross, Warren J.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 03/02/2014 Português
Relevância na Pesquisa
370.54918%
Associative memories are structures that store data patterns and retrieve them given partial inputs. Sparse Clustered Networks (SCNs) are recently-introduced binary-weighted associative memories that significantly improve the storage and retrieval capabilities over the prior state-of-the art. However, deleting or updating the data patterns result in a significant increase in the data retrieval error probability. In this paper, we propose an algorithm to address this problem by incorporating multiple-valued weights for the interconnections used in the network. The proposed algorithm lowers the error rate by an order of magnitude for our sample network with 60% deleted contents. We then investigate the advantages of the proposed algorithm for hardware implementations.; Comment: 6 pages, Accepted in IEEE ISMVL 2014 conference

Image Parsing with a Wide Range of Classes and Scene-Level Context

George, Marian
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 24/10/2015 Português
Relevância na Pesquisa
369.7336%
This paper presents a nonparametric scene parsing approach that improves the overall accuracy, as well as the coverage of foreground classes in scene images. We first improve the label likelihood estimates at superpixels by merging likelihood scores from different probabilistic classifiers. This boosts the classification performance and enriches the representation of less-represented classes. Our second contribution consists of incorporating semantic context in the parsing process through global label costs. Our method does not rely on image retrieval sets but rather assigns a global likelihood estimate to each label, which is plugged into the overall energy function. We evaluate our system on two large-scale datasets, SIFTflow and LMSun. We achieve state-of-the-art performance on the SIFTflow dataset and near-record results on LMSun.; Comment: Published at CVPR 2015, Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on

A Novel Approach for Video Temporal Annotation

Haghi, Hadi Restgou; Kangavari, Mohammadreza; QasemiZadeh, Behrang
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 17/04/2014 Português
Relevância na Pesquisa
370.54918%
Recent advances in computing, communication, and data storage have led to an increasing number of large digital libraries publicly available on the Internet. Main problem of content-based video retrieval is inferring semantics from raw video data. Video data play an important role in these libraries. Instead of words, a video retrieval system deals with collections of video records. Therefore, the system is confronted with the problem of video understanding. Because machine understanding of the video data is still an unsolved research problem, text annotations are usually used to describe the content of video data according to the annotator's understanding and the purpose of that video data. Most of proposed systems for video annotation are domain dependent. In addition, in many of these systems, an important feature of video data, temporality, is disregarded. In this paper, we proposed a framework for video temporal annotation. The proposed system uses domain knowledge and a time ontology to perform temporal annotation of input video.; Comment: Published in a Local Confrence, 2006

3D-Assisted Image Feature Synthesis for Novel Views of an Object

Su, Hao; Wang, Fan; Yi, Li; Guibas, Leonidas
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 26/11/2014 Português
Relevância na Pesquisa
369.7336%
Comparing two images in a view-invariant way has been a challenging problem in computer vision for a long time, as visual features are not stable under large view point changes. In this paper, given a single input image of an object, we synthesize new features for other views of the same object. To accomplish this, we introduce an aligned set of 3D models in the same class as the input object image. Each 3D model is represented by a set of views, and we study the correlation of image patches between different views, seeking what we call surrogates --- patches in one view whose feature content predicts well the features of a patch in another view. In particular, for each patch in the novel desired view, we seek surrogates from the observed view of the given image. For a given surrogate, we predict that surrogate using linear combination of the corresponding patches of the 3D model views, learn the coefficients, and then transfer these coefficients on a per patch basis to synthesize the features of the patch in the novel view. In this way we can create feature sets for all views of the latent object, providing us a multi-view representation of the object. View-invariant object comparisons are achieved simply by computing the $L^2$ distances between the features of corresponding views. We provide theoretical and empirical analysis of the feature synthesis process...

In-place associative permutation sort

Cetin, A. Emre
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 05/10/2012 Português
Relevância na Pesquisa
370.54918%
In-place associative integer sorting technique was developed, improved and specialized for distinct integers. The technique is suitable for integer sorting. Hence, given a list S of n integers S[0...n-1], the technique sorts the integers in ascending or descending order. It replaces bucket sort, distribution counting sort and address calculation sort family of algorithms and requires only constant amount of additional memory for storing counters and indices beside the input list. The technique was inspired from one of the ordinal theories of "serial order in behavior" and explained by the analogy with the three main stages in the formation and retrieval of memory in cognitive neuroscience: (i) practicing, (ii) storing and (iii) retrieval. In this study in-place associative permutation technique is introduced for integer key sorting problem. Given a list S of n elements S[0...n-1] each have an integer key in the range [0,m-1], the technique sorts the elements according to their integer keys in O(n) time using only O(1) amount of memory if m<=n. On the other hand, if m>n, it sorts in O(n+m) time for the worst, O(m) time for the average (uniformly distributed keys) and O(n) time for the best case using O(1) extra space.; Comment: 25 pages. arXiv admin note: substantial text overlap with arXiv:1209.0572...

Topic Graph Generation for Query Navigation: Use of Frequency Classes for Topic Extraction

Niwa, Yoshiki; Nishioka, Shingo; Iwayama, Makoto; Takano, Akihiko; Nitta, Yoshihiko
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 12/12/1997 Português
Relevância na Pesquisa
370.54918%
To make an interactive guidance mechanism for document retrieval systems, we developed a user-interface which presents users the visualized map of topics at each stage of retrieval process. Topic words are automatically extracted by frequency analysis and the strength of the relationships between topic words is measured by their co-occurrence. A major factor affecting a user's impression of a given topic word graph is the balance between common topic words and specific topic words. By using frequency classes for topic word extraction, we made it possible to select well-balanced set of topic words, and to adjust the balance of common and specific topic words.; Comment: 6 pages, 3 figures

Cell Stores

Fourny, Ghislain
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
370.54918%
Cell stores provide a relational-like, tabular level of abstraction to business users while leveraging recent database technologies, such as key-value stores and document stores. This allows to scale up and out the efficient storage and retrieval of highly dimensional data. Cells are the primary citizens and exist in different forms, which can be explained with an analogy to the state of matter: as a gas for efficient storage, as a solid for efficient retrieval, and as a liquid for efficient interaction with the business users. Cell stores were abstracted from, and are compatible with the XBRL standard for importing and exporting data. The first cell store repository contains roughly 200GB of SEC filings data, and proves that retrieving data cubes can be performed in real time (the threshold acceptable by a human user being at most a few seconds).; Comment: Technical report - 10 pages

A Logical Model and Data Placement Strategies for MEMS Storage Devices

Kim, Yi-Reun; Whang, Kyu-Young; Kim, Min-Soo; Song, Il-Yeol
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 29/07/2008 Português
Relevância na Pesquisa
370.54918%
MEMS storage devices are new non-volatile secondary storages that have outstanding advantages over magnetic disks. MEMS storage devices, however, are much different from magnetic disks in the structure and access characteristics. They have thousands of heads called probe tips and provide the following two major access facilities: (1) flexibility: freely selecting a set of probe tips for accessing data, (2) parallelism: simultaneously reading and writing data with the set of probe tips selected. Due to these characteristics, it is nontrivial to find data placements that fully utilize the capability of MEMS storage devices. In this paper, we propose a simple logical model called the Region-Sector (RS) model that abstracts major characteristics affecting data retrieval performance, such as flexibility and parallelism, from the physical MEMS storage model. We also suggest heuristic data placement strategies based on the RS model and derive new data placements for relational data and two-dimensional spatial data by using those strategies. Experimental results show that the proposed data placements improve the data retrieval performance by up to 4.0 times for relational data and by up to 4.8 times for two-dimensional spatial data of approximately 320 Mbytes compared with those of existing data placements. Further...

The technique of in-place associative sorting

Cetin, A. Emre
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 10/07/2013 Português
Relevância na Pesquisa
370.54918%
In the first place, a novel, yet straightforward in-place integer value-sorting algorithm is presented. It sorts in linear time using constant amount of additional memory for storing counters and indices beside the input array. The technique is inspired from the principal idea behind one of the ordinal theories of "serial order in behavior" and explained by the analogy with the three main stages in the formation and retrieval of memory in cognitive neuroscience: (i) practicing, (ii) storage and (iii) retrieval. It is further improved in terms of time complexity as well as specialized for distinct integers, though still improper for rank-sorting. Afterwards, another novel, yet straightforward technique is introduced which makes this efficient value-sorting technique proper for rank-sorting. Hence, given an array of n elements each have an integer key, the technique sorts the elements according to their integer keys in linear time using only constant amount of additional memory. The devised technique is very practical and efficient outperforming bucket sort, distribution counting sort and address calculation sort family of algorithms making it attractive in almost every case even when space is not a critical resource.; Comment: 34 Pages. arXiv admin note: substantial text overlap with arXiv:1209.0572...

A Logic and Adaptive Approach for Efficient Diagnosis Systems using CBR

Bitar, Ibrahim El; Belouadha, Fatima-Zahra; Roudies, Ounsa
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 17/11/2012 Português
Relevância na Pesquisa
370.54918%
Case Based Reasoning (CBR) is an intelligent way of thinking based on experience and capitalization of already solved cases (source cases) to find a solution to a new problem (target case). Retrieval phase consists on identifying source cases that are similar to the target case. This phase may lead to erroneous results if the existing knowledge imperfections are not taken into account. This work presents a novel solution based on Fuzzy logic techniques and adaptation measures which aggregate weighted similarities to improve the retrieval results. To confirm the efficiency of our solution, we have applied it to the industrial diagnosis domain. The obtained results are more efficient results than those obtained by applying typical measures.; Comment: 5 pages,3 figures, 1 table

Real time unsupervised learning of visual stimuli in neuromorphic VLSI systems

Giulioni, Massimiliano; Corradi, Federico; Dante, Vittorio; del Giudice, Paolo
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 17/06/2015 Português
Relevância na Pesquisa
370.54918%
Neuromorphic chips embody computational principles operating in the nervous system, into microelectronic devices. In this domain it is important to identify computational primitives that theory and experiments suggest as generic and reusable cognitive elements. One such element is provided by attractor dynamics in recurrent networks. Point attractors are equilibrium states of the dynamics (up to fluctuations), determined by the synaptic structure of the network; a `basin' of attraction comprises all initial states leading to a given attractor upon relaxation, hence making attractor dynamics suitable to implement robust associative memory. The initial network state is dictated by the stimulus, and relaxation to the attractor state implements the retrieval of the corresponding memorized prototypical pattern. In a previous work we demonstrated that a neuromorphic recurrent network of spiking neurons and suitably chosen, fixed synapses supports attractor dynamics. Here we focus on learning: activating on-chip synaptic plasticity and using a theory-driven strategy for choosing network parameters, we show that autonomous learning, following repeated presentation of simple visual stimuli, shapes a synaptic connectivity supporting stimulus-selective attractors. Associative memory develops on chip as the result of the coupled stimulus-driven neural activity and ensuing synaptic dynamics...

Difference-Huffman Coding of Multidimensional Databases

Szépkúti, István
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
370.54918%
A new compression method called difference-Huffman coding (DHC) is introduced in this paper. It is verified empirically that DHC results in a smaller multidimensional physical representation than those for other previously published techniques (single count header compression, logical position compression, base-offset compression and difference sequence compression). The article examines how caching influences the expected retrieval time of the multidimensional and table representations of relations. A model is proposed for this, which is then verified with empirical data. Conclusions are drawn, based on the model and the experiment, about when one physical representation outperforms another in terms of retrieval time. Over the tested range of available memory, the performance for the multidimensional representation was always much quicker than for the table representation.; Comment: 23 pages, 3 figures, 6 tables. Revised version of this paper appeared in Periodica Polytechnica Electrical Engineering. Please refer to http://arxiv.org/abs/1103.4168; Computing Research Repository, 2011

In-place associative integer sorting

Cetin, A. Emre
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
370.54918%
A novel integer value-sorting technique is proposed replacing bucket sort, distribution counting sort and address calculation sort family of algorithms. It requires only constant amount of additional memory. The technique is inspired from one of the ordinal theories of "serial order in behavior" and explained by the analogy with the three main stages in the formation and retrieval of memory in cognitive neuroscience namely (i) practicing, (ii) storing and (iii) retrieval. Although not suitable for integer rank-sorting where the problem is to put an array of elements into ascending or descending order by their numeric keys, each of which is an integer, the technique seems to be efficient and applicable to rank-sorting, as well as other problems such as hashing, searching, element distinction, succinct data structures, gaining space, etc.; Comment: 25 pages. arXiv admin note: substantial text overlap with arXiv:1209.3668, arXiv:1210.1771, arXiv:1209.1942, arXiv:1209.4714

Codes Can Reduce Queueing Delay in Data Centers

Huang, Longbo; Pawar, Sameer; Zhang, Hao; Ramchandran, Kannan
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 07/02/2012 Português
Relevância na Pesquisa
370.54918%
In this paper, we quantify how much codes can reduce the data retrieval latency in storage systems. By combining a simple linear code with a novel request scheduling algorithm, which we call Blocking-one Scheduling (BoS), we show analytically that it is possible to reduce data retrieval delay by up to 17% over currently popular replication-based strategies. Although in this work we focus on a simplified setting where the storage system stores a single content, the methodology developed can be applied to more general settings with multiple contents. The results also offer insightful guidance to the design of storage systems in data centers and content distribution networks.

Improved in-place associative integer sorting

Cetin, A. Emre
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 17/09/2012 Português
Relevância na Pesquisa
370.54918%
A novel integer sorting technique was proposed replacing bucket sort, distribution counting sort and address calculation sort family of algorithms which requires only constant amount of additional memory. The technique was inspired from one of the ordinal theories of "serial order in behavior" and explained by the analogy with the three main stages in the formation and retrieval of memory in cognitive neuroscience namely (i) practicing, (ii) storing and (iii) retrieval. In this study, the technique is improved both theoretically and practically and an algorithm is obtained which is faster than the former making it more competitive. With the improved version, n integers S[0...n-1] each in the range [0, n-1] are sorted exactly in O(n) time while the complexity of the former technique was the recursion T(n) = T(n/2) + O(n) yielding T(n) = O(n).; Comment: 16 pages. arXiv admin note: substantial text overlap with arXiv:1209.0572, arXiv:1209.1942

Sorting distinct integer keys using in-place associative sort

Cetin, A. Emre
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
370.54918%
In-place associative integer sorting technique was proposed for integer lists which requires only constant amount of additional memory replacing bucket sort, distribution counting sort and address calculation sort family of algorithms. The technique was explained by the analogy with the three main stages in the formation and retrieval of memory in cognitive neuroscience which are (i) practicing, (ii) storing and (iii) retrieval. In this study, the technique is specialized with two variants one for read-only integer keys and the other for modifiable integers. Hence, a novel algorithm is obtained that does not require additional memory other than a constant amount and sorts faster than all no matter how large is the list provided that m = O (n logn) where m is the range and n is the number of keys (or integers).; Comment: 20 pages. arXiv admin note: substantial text overlap with arXiv:1209.0572

sDTW: Computing DTW Distances using Locally Relevant Constraints based on Salient Feature Alignments

Candan, K. Selçuk; Rossini, Rosaria; Sapino, Maria Luisa; Wang, Xiaolan
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 01/08/2012 Português
Relevância na Pesquisa
370.54918%
Many applications generate and consume temporal data and retrieval of time series is a key processing step in many application domains. Dynamic time warping (DTW) distance between time series of size N and M is computed relying on a dynamic programming approach which creates and fills an NxM grid to search for an optimal warp path. Since this can be costly, various heuristics have been proposed to cut away the potentially unproductive portions of the DTW grid. In this paper, we argue that time series often carry structural features that can be used for identifying locally relevant constraints to eliminate redundant work. Relying on this observation, we propose salient feature based sDTW algorithms which first identify robust salient features in the given time series and then find a consistent alignment of these to establish the boundaries for the warp path search. More specifically, we propose alternative fixed core&adaptive width, adaptive core&fixed width, and adaptive core&adaptive width strategies which enforce different constraints reflecting the high level structural characteristics of the series in the data set. Experiment results show that the proposed sDTW algorithms help achieve much higher accuracy in DTWcomputation and time series retrieval than fixed core & fixed width algorithms that do not leverage local features of the given time series.; Comment: VLDB2012