检索结果-内蒙古大学图书馆

International Conference on pattern Recognition

作者： Jose A. Rodriguez Florent Perronnin Gemma Sanchez Josep Llados Xerox Research Centre Europe Textual and Visual Pattern Analysis (TVPA) France Computer Vision Center (CVC) Universitat Authnòma de Barcelona Spain

ISBN: (纸本)9781424421749

We propose a novel approach for writer adaptation in a word spotting task. The method exploits the fact that a semi-continuous hidden Markov model separates the word model parameters into (i) a shared codebook of shapes and (ii) a set of word-specific parameters. Our main contribution is to derive writer-specific word models by statistically adapting an initial universal codebook to each document. This process is unsupervised and does not even require the appearance of the keyword(s) in the searched document. Experimental results show an increase in performance when this adaptation technique is applied. To the best knowledge of the authors, this is the first work dealing with adaptation for word spotting.

关键词： Hidden Markov models Character recognition Handwriting recognition Shape Testing pattern analysis Europe computer vision pattern classification Degradation

来源：评论

学校读者我要写书评

暂无评论

Robust Superdirective End-Fire Arrays

Robust Superdirective End-Fire Arrays

引用

Oceans 2013 - Norway

作者： A. Trucco F. Traverso M. Crocco Dept. of Electrical Electronic Telecommunications Engineering and Naval Architecture (DITEN) University of Genoa Pattern Analysis & Computer Vision Istituto Italiano di Tecnologia (IIT)

ISBN: (纸本)9781479900022

Oversteering is a technique to achieving robust superdirective performance by end-fire arrays whose transducers are spaced less than half wavelength. To reduce the beamwidth, the main-lobe is pushed past end-fire by the introduction of additional delays. The reduction of the main-lobe sensitivity produces, in turn, an increase of the side-lobe level and a fall of the white noise gain. This paper proposes a method to compute the real-valued weight coefficients that yield the maximum directivity for a given oversteering amount and assure a white noise gain above a given threshold. If this optimization is carried out in parallel with the exhaustive search for the best oversteering amount, the optimum oversteering performance can be reached. Finally, it is shown that for a linear array composed of 8 transducers, the oversteering technique yields a directivity which is very close to that provided by the optimum complex-valued weight coefficients, requiring a simpler processing system and assuring the same robustness (i.e., the two solutions show the same white noise gain).

关键词： End-fire arrays Superdirective beamforming Oversteering Maximum directivity White noise gain

来源：评论

学校读者我要写书评

暂无评论

Using Image Morphing for Memory-Efficient Impostor Rendering on GPU

Using Image Morphing for Memory-Efficient Impostor Rendering...

引用

International Conference on Cyberworlds

作者： Kamer Ali Yuksel Aytul Ercil Alp Yucebilgin Selim Balcisoy Computer Vision and Pattern Analysis Laboratory Faculty of Engineering and Natural Sciences Sabanci University Istanbul Turkey Faculty of Engineering and Natural Sciences Computer Graphics Laboratory Sabanci University Istanbul Turkey

Real-time rendering of large animated crowds consisting thousands of virtual humans is important for several applications including simulations, games and interactive walkthroughs, but cannot be performed using complex polygonal models at interactive frame rates. For that reason, several methods using large numbers of pre-computed image-based representations, which are called as impostors, have been proposed. These methods take the advantage of existing programmable graphics hardware to compensate the computational expense while maintaining the visual fidelity. Making the number of different virtual humans, which can be rendered in real-time, not restricted anymore by the required computational power but by the texture memory consumed for the variety and discretization of their animations. In this work, we proposed an alternative method that reduces the memory consumption by generating compelling intermediate textures using image-morphing techniques. In order to demonstrate the preserved perceptual quality of animations, where half of the key-frames were rendered using the proposed methodology, we have implemented the system using the graphical processing unit and obtained promising results at interactive frame rates.

关键词： Rendering (computer graphics) Animation Graphics processing unit Memory management Cameras Face Humans

来源：评论

学校读者我要写书评

暂无评论

Automatic White Matter Fiber Clustering Using Dominant Sets

Automatic White Matter Fiber Clustering Using Dominant Sets

引用

International Workshop on pattern Recognition in NeuroImaging (PRNI)

作者： L. Dodero S. Vascon L. Giancardo A. Gozzi D. Sona V. Murino Pattern Analysis and Computer Vision Istituto Italiano di Tecnologia Genoa Italy Center for Neuroscience and Cognitive Systems@UniTn Istituto Italiano di Tecnologia Rovereto Italy

We present an unsupervised approach based on the Dominant Sets framework to automatically segment the white matter fibers into bundles. This framework, rooted in the Game Theory, allows for the automatic determination of the number of clusters from the data itself, without any prior assumption. The clustered bundles are a key information for the generation of unbiased structural connectivity atlases. We have thoroughly validated our algorithm both quantitatively and qualitatively. Indeed, we used biologically plausible synthetic datasets to numerically validate the performance in terms of Precision, Recall and other measures employed in the literature. We also evaluated the algorithm on a real Diffusion Tensor Imaging tractography of a whole mouse brain obtaining promising results. In fact, some of the most prominent brain structures determined by the algorithm correspond to white matter expected anatomy.

关键词： Clustering algorithms Diffusion tensor imaging Mice Image segmentation Indexes

来源：评论

学校读者我要写书评

暂无评论

Data-driven Study of Mouse Sleep-stages using Restricted Boltzmann Machines

Data-driven Study of Mouse Sleep-stages using Restricted Bol...

引用

International Joint Conference on Neural Networks

作者： Vasiliki-Maria Katsageorgiou Matteo Zanotto Valter Tucci Vittorio Murino Diego Sona Pattern Analysis and Computer Vision (PAVIS) Istituto Italiano di Tecnologia Genova Italy Neuroscience and Brain Technologies (NBT) Istituto Italiano di Tecnologia Genova Italy

ISBN: (纸本)9781509061839

Rodents play an important role in sleep studies since they are the most easily available low-cost animal species sharing most genes and gene functions with humans. The scoring of sleep stages in these studies is usually based on a manual analysis of long-lasting recordings of the brain electrical activity and the activity of skeletal muscles. Hence, there is a great need for tools automating the investigation over large experiments. In this paper we present a way of analyzing this huge amount of electrophysiological data using unsupervised learning models. We show how employing latent variable models, like Restricted Boltzmann Machines, we can define different sleep-wakefulness sub-stages reflected by regularities in the data, without any prior knowledge. Our analysis shows that we can effectively discover meaningful feature representations which characterize sleep stages at a finer level than those commonly used by the experts. These feature representations can be also used to further characterize different mouse genotypes, without incurring biases of experts like in a classical analysis setup where predefined rules limit the discovery of novel insights.

关键词： Brain modeling Sleep Mice Strain Data models Standards Muscles

来源：评论

学校读者我要写书评

暂无评论

LEDNet: Deep Network for Single Image Haze Removal 2018

LEDNet: Deep Network for Single Image Haze Removal

引用

Proceedings of the 11th Indian Conference on computer vision, Graphics and Image Processing

作者： Akshay Dudhane Subrahmanyam Murala Abhinav Dhall Computer Vision and Pattern Recognition Lab Indian Institute of Technology Ropar India Learning Affect and Semantic Image Analysis Group Indian Institute of Technology Ropar India

ISBN: (纸本)9781450366151

Haze during the bad weather, degrades the visibility of the scene drastically. Degradation of scene visibility varies with respect to the transmission coefficient/map (Tc) of the scene. Estimation of accurate Tc is key step to reconstruct the haze free scene. Previously, local as well as global priors were proposed to estimate the Tc. We, on the other hand, propose integration of local and global approaches to learn both point level and object level Tc. The proposed local encoder decoder network (LEDNet) estimates the scene transmission map in two stages. During first stage, network estimates the point level Tc using parallel convolutional filters and spatial invariance filtering. The second stage comprises of a two level encoder-decoder architecture which anticipates the object level Tc. We also propose, local air-light estimation (LAE) algorithm, which is able to obtain the air-light component of the outdoor scene. Combination of LEDNet and LAE improves the accuracy of haze model to recover the scene radiance. Structural similarity index, mean square error and peak signal to noise ratio are used to evaluate the performance of the proposed approach for single image haze removal. Experiments on benchmark datasets show that LEDNet outperforms the existing state-of-the-art methods for single image haze removal.

关键词： Haze removal transmission map CNN

来源：评论

学校读者我要写书评

暂无评论

Lifting Monocular Events to 3D Human Poses

arXiv

引用

arXiv 2021年

作者： Scarpellini, Gianluca Morerio, Pietro Del Bue, Alessio Pattern Analysis and Computer Vision-Istituto Italiano di Tecnologia Italy University of Genova Genoa Italy Visual Geometry and Modelling Istituto Italiano di Tecnologia Italy

This paper presents a novel 3D human pose estimation approach using a single stream of asynchronous events as input. Most of the state-of-the-art approaches solve this task with RGB cameras, however struggling when subjects are moving fast. On the other hand, event-based 3D pose estimation benefits from the advantages of event-cameras, especially their efficiency and robustness to appearance changes. Yet, finding human poses in asynchronous events is in general more challenging than standard RGB pose estimation, since little or no events are triggered in static scenes. Here we propose the first learning-based method for 3D human pose from a single stream of events. Our method consists of two steps. First, we process the event-camera stream to predict three orthogonal heatmaps per joint;each heatmap is the projection of of the joint onto one orthogonal plane. Next, we fuse the sets of heatmaps to estimate 3D localisation of the body joints. As a further contribution, we make available a new, challenging dataset for eventbased human pose estimation by simulating events from the RGB Human3.6m dataset. Experiments demonstrate that our method achieves solid accuracy, narrowing the performance gap between standard RGB and event-based vision. The code is freely available at https://***/lifting-events-to-3d-hpe. © 2021, CC BY.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

An analysis of dropout for matrix factorization

arXiv

引用

arXiv 2017年

作者： Cavazza, Jacopo Lane, Connor Haeffele, Benjamin D. Murino, Vittorio Vidal, René Pattern Analysis and Computer Vision Istituto Italiano di Tecnologia Genova16163 Italy Johns Hopkins University Center for Imaging Science BaltimoreMD21218 United States

Dropout is a simple yet effective algorithm for regularizing neural networks by randomly dropping out units through Bernoulli multiplicative noise, and for some restricted problem classes, such as linear or logistic regression, several theoretical studies have demonstrated the equivalence between dropout and a fully deterministic optimization problem with data-dependent Tikhonov regularization. This work presents a theoretical analysis of dropout for matrix factorization, where Bernoulli random variables are used to drop a factor, thereby attempting to control the size of the factorization. While recent work has demonstrated the empirical effectiveness of dropout for matrix factorization, a theoretical understanding of the regularization properties of dropout in this context remains elusive. This work demonstrates the equivalence between dropout and a fully deterministic model for matrix factorization in which the factors are regularized by the sum of the product of the norms of the columns. While the resulting regularizer is closely related to a variational form of the nuclear norm, suggesting that dropout may limit the size of the factorization, we show that it is possible to trivially lower the objective value by doubling the size of the factorization. We show that this problem is caused by the use of a fixed dropout rate, which motivates the use of a rate that increases with the size of the factorization. Synthetic experiments validate our theoretical findings. Copyright © 2017, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

MULTIPLE HYPOTHESES DATA ASSOCIATION PROPAGATION FOR ROBUST MONOCULAR-BASED SLAM ALGORITHMS

MULTIPLE HYPOTHESES DATA ASSOCIATION PROPAGATION FOR ROBUST ...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Mauricio Soto-Alvarez Petri Honkamaa Pattern Analysis & Computer Vision Istituto Italiano di Tecnologia (IIT) via Morego 30 16163 Genoa Italy VTT Technical Research Centre of Finland Espoo Finland

ISBN: (纸本)9781479928941

Data Association is probably the most important step of every monocular Simultaneous Localization and Mapping (SLAM) algorithm because it provides the basic information to the estimation module, independently on the estimation algorithm of choice. Although important, it is also a difficult task because the analytic solution is NP-Hard. The usual approximation is obtaining only one data association hypothesis per frame which affects the robustness of the result [1][2][3][4][5]. In this paper, a data association approach is presented, where multiple hypotheses are propagated between frames using a probabilistic framework. Experimental results, using real and synthetic data, show that the proposed algorithm produces promising results with respect to other state of the art methods.

关键词： data association state of the art supersonic low altitude missile FRAMES synthetic data simultaneous localization and mapping algorithms

来源：评论

学校读者我要写书评

暂无评论

Dropout as a low-rank regularizer for matrix factorization

arXiv

引用

arXiv 2017年

作者： Cavazza, Jacopo Morerio, Pietro Haeffele, Benjamin Lane, Connor Murino, Vittorio Vidal, René Pattern Analysis and Computer Vision Istituto Italiano di Tecnologia Genova16163 Italy Johns Hopkins University Center for Imaging Science BaltimoreMD21218 United States

Regularization for matrix factorization (MF) and approximation problems has been carried out in many different ways. Due to its popularity in deep learning, dropout has been applied also for this class of problems. Despite its solid empirical performance, the theoretical properties of dropout as a regularizer remain quite elusive for this class of problems. In this paper, we present a theoretical analysis of dropout for MF, where Bernoulli random variables are used to drop columns of the factors. We demonstrate the equivalence between dropout and a fully deterministic model for MF in which the factors are regularized by the sum of the product of squared Euclidean norms of the columns. Additionally, we inspect the case of a variable sized factorization and we prove that dropout achieves the global minimum of a convex approximation problem with (squared) nuclear norm regularization. As a result, we conclude that dropout can be used as a low-rank regularizer with data dependent singular-value thresholding. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：