检索结果-内蒙古大学图书馆

6th international Conference on Learning representations, ICLR 2018

作者： Achlioptas, Panos Diamanti, Olga Mitliagkas, Ioannis Guibas, Leonidas Department of Computer Science Stanford University United States Department of Computer Science and Operations Research University of Montréal Canada

three-dimensional geometric data offer an excellent domain for studying representation learning and generative modeling. In this paper, we look at geometric data represented as point clouds. We introduce a deep autoencoder (AE) network with state-of-the-art reconstruction quality and generalization ability. the learned representations outperform existing methods on 3D recognition tasks and enable basic shape editing via simple algebraic manipulations, such as semantic part editing, shape analogies and shape interpolation. We perform a thorough study of different generative models including: GANs operating on the raw point clouds, significantly improved GANs trained in the fixed latent space of our AEs and, Gaussian mixture models (GMM). For our quantitative evaluation we propose measures of sample fidelity and diversity based on matchings between sets of point clouds. Interestingly, our careful evaluation of generalization, fidelity and diversity reveals that GMMs trained in the latent space of our AEs produce the best results. © 6th international Conference on Learning representations, ICLR 2018 - workshop Track Proceedings. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Using a Generic Model for Codebook-based Gait recognition Algorithms 6

Using a Generic Model for Codebook-based Gait Recognition Al...

引用

6th international workshop on Biometrics and Forensics (IWBF)

作者： Khan, Muhammad Hassan Farid, Muhammad Shahid Grzegorzek, Marcin Univ Siegen Res Grp Pattern Recognit Siegen Germany Univ Punjab Punjab Univ Coll Informat Technol Lahore Pakistan Univ Econ Fac Informat & Commun Katowice Poland

ISBN: (纸本)9781538613665

Gait has emerged as a distinguishable human biological trait. It refers to the walking style of an individual and is considered an important biometric feature for person identification. Codebook based gait recognition algorithms have demonstrated excellent performance by achieving high recognition rates. However, such methods construct a codebook for each database or scenario. In this paper, we investigate the idea of using a generic codebook for gait recognition. the proposed codebook is built by using spatiotemporal characteristics of gait sequences from a large diverse synthetic gait database. We also propose a gait recognition algorithm based on this generic codebook. the advantages of the proposed algorithm over the existing methods include its independency from generating a codebook for each database, rather the proposed generic codebook can be used to encode any gait scenario. Moreover, the proposed algorithm is model free and does not require human body segmentation or modeling. the performance of the proposed generic codebook-based gait recognition algorithm is evaluated on two large gait databases TUM GAID and CMU MoBo, and recognition rate reveals the effectiveness of the proposed algorithm.

关键词： Gait recognition generic codebook spatiotemporal features Fisher vector encoding

来源：评论

学校读者我要写书评

暂无评论

Fast node embeddings: Learning ego-centric representations 6

Fast node embeddings: Learning ego-centric representations

引用

6th international Conference on Learning representations, ICLR 2018

作者： Pimentel, Tiago Veloso, Adriano Ziviani, Nivio CS Dept. UFMG Belo Horizonte Brazil Kunumi Belo Horizonte Brazil

Representation learning is one of the foundations of Deep Learning and allowed important improvements on several Machine Learning tasks, such as Neural Machine Translation, Question Answering and Speech recognition. Recent works have proposed new methods for learning representations for nodes and edges in graphs. Several of these methods are based on the SkipGram algorithm, and they usually process a large number of multi-hop neighbors in order to produce the context from which node representations are learned. In this paper, we propose an effective and also efficient method for generating node embeddings in graphs that employs a restricted number of permutations over the immediate neighborhood of a node as context to generate its representation, thus ego-centric representations. We present a thorough evaluation showing that our method outperforms state-of-the-art methods in six different datasets related to the problems of link prediction and node classification, being one to three orders of magnitude faster than baselines when generating node embeddings for very large graphs. © 6th international Conference on Learning representations, ICLR 2018 - workshop Track Proceedings. 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

Exploring Local Deep representations for Facial Gender Classification in Videos 6th

Exploring Local Deep Representations for Facial Gender Class...

引用

6th international workshop on Artificial Intelligence and pattern recognition (IWAIPR)

作者： Becerra-Riera, Fabiola Morales-Gonzalez, Annette Mendez-Vazquez, Heydi Adv Technol Applicat Ctr 7ma A 21406 Havana Cuba

ISBN: (纸本)9783030011321;9783030011314

Gender recognition in videos is a challenging task that has received limited attention in recent years. To tackle this problem, we propose to explore the use of intermediate features of a Convolutional Neural Network (CNN) with a component-based face representation methodology. With this approach we intend to exploit the gender information provided by different face parts. the features extracted from video key frames are combined with two different strategies to preserve the temporal information, and Random Forest classifiers are employed to obtain a final gender prediction for a video sequence. Our results on the McGill and COX datasets show that our proposal outperforms the end-to-end CNN approach and, in the McGill dataset, 100% of accuracy was obtained.

关键词： Soft-biometrics Gender classification Video face analysis Deep learning representation

来源：评论

学校读者我要写书评

暂无评论

10th IAPR-TC-15 international workshop on graph-based representations in pattern recognition, GbRPR 2015

10th IAPR-TC-15 International Workshop on Graph-Based Repres...

引用

10th IAPR-TC-15 international workshop on graph-based representations in pattern recognition, GbRPR 2015

ISBN: (纸本)9783319182230

the proceedings contain 36 papers. the special focus in this conference is on graph-based Representation, graph Matching, graph Clustering and graph-based Applications. the topics include: Approximation of graph edit distance in quadratic time;data graph formulation as the minimum-weight maximum-entropy problem;an entropic edge assortativity measure;a subpath kernel for learning hierarchical image representations;coupled-feature hypergraph representation for feature selection;reeb graphs through local binary patterns;incremental embedding within a dissimilarity-based framework;a first step towards exact graph edit distance using bipartite graph matching;consensus of two graph correspondences through a generalisation of the bipartite graph matching;revisiting Volgenant-Jonker for approximating graph edit distance;a hypergraph matching framework for refining multi-source feature correspondences;a tool for solving substitution-tolerant subgraph isomorphism;a graph database repository and performance evaluation metrics for graph edit distance;learning graph model for different dimensions image matching;report on the first contest on graph matching algorithms for pattern search in biological databases;large-scale graph indexing using binary embeddings of node contexts;on the influence of node centralities on graph edit distance for graph classification;a quantum Jensen-Shannon graph kernel using discrete-time quantum walks;density based cluster extension and dominant sets clustering;salient object segmentation from stereoscopic images;causal video segmentation using superseeds and graph matching;fast minimum spanning tree based clustering algorithms on local neighborhood graph and graph based lymphatic vessel wall localisation and tracking.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CEUR workshop Proceedings

CEUR Workshop Proceedings

引用

6th international workshop "What can FCA do for Artificial Intelligence"?, FCA4AI 2018

the proceedings contain 11 papers. the topics discussed include: inductive reasoning with conceptual space representations;an answer set programming environment for high-level specification and visualization of FCA;three approaches for mining definitions from relational data in the web of data;relational proportions between objects and attributes;the theory and practice of coupling formal concept analysis to relational databases;generalized metrics with applications to ratings and formal concept analysis;binary lattices;biclustering based on FCA and partition pattern structures for recommendation systems;and combining concept annotation and pattern structures for guiding ontology mapping.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Shape Simplification through graph Sparsification 11th

Shape Simplification Through Graph Sparsification

引用

11th IAPR-TC15 international workshop on graph-based representations in pattern recognition (GbRPR)

作者： Escolano, Francisco Curado, Manuel Biasotti, Silvia Hancock, Edwin R. Univ Alicante Dept Comp Sci & AI Alicante 03690 Spain CNR IMATI Via Marini 6 Torre de Francia I-16149 Genoa Italy Univ York Dept Comp Sci York YO10 5DD N Yorkshire England

ISBN: (纸本)9783319589619;9783319589602

In this paper, we draw on Spielman and Srivastava's method for graph sparsification in order to simplify shape representations. the underlying principle of graph sparsification is to retain only the edges which are key to the preservation of desired properties. In this regard, sparsification by edge resistance allows us to preserve (to some extent) links between protrusions and the remainder of the shape (e.g. parts of a shape) while removing in-part edges. Applying this idea to alpha shapes (abstract representations which have a huge number of edges) opens up a way of introducing a hierarchy of the edge strength, thus being relevant for shape analysis and interpretation.

关键词： graph sparsification Shape simplification Alpha shapes

来源：评论

学校读者我要写书评

暂无评论

Optimum-Path Forest based on k-connectivity: theory and applications

引用

pattern recognition LETTERS 2017年第Feb.1期87卷 117-126页

作者： Papa, Joao Paulo Nachif Fernandes, Silas Evandro Falcao, Alexandre Xavier Sao Paulo State Univ Dept Comp Av Eng Luiz Edmundo Carrijo Coube BR-17033360 Bauru SP Brazil Univ Fed Sao Carlos Dept Comp Rod Washington LuisKm 235 BR-13565905 Sao Carlos SP Brazil Univ Estadual Campinas Inst Comp Av Albert Einstein 1251 BR-13083852 Campinas SP Brazil

graph-based pattern recognition techniques have been in the spotlight for many years, since there is a constant need for faster and more effective approaches. Among them, the Optimum-Path Forest (OPF) framework has gained considerable attention in the last years, mainly due to the promising results obtained by OPF-based classifiers, which range from unsupervised, semi-supervised and supervised learning. In this paper, we consider a deeper theoretical explanation concerning the supervised OPF classifier with k-neighborhood (OPFk), as well as we proposed two different training and classification algorithms that allow OPFk to work faster. the experimental validation against standard OPF and Support Vector Machines also validates the robustness of OPFk in real and synthetic datasets. (C) 2016 Elsevier B.V. All rights reserved.

关键词： pattern classification Optimum-Path Forest Supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Survey on Applications of Bipartite graph Edit Distance 11th

A Survey on Applications of Bipartite Graph Edit Distance

引用

11th IAPR-TC15 international workshop on graph-based representations in pattern recognition (GbRPR)

作者： Stauffer, Michael Tschachtli, thomas Fischer, Andreas Riesen, Kaspar Univ Appl Sci & Arts Northwestern Switzerland Inst Informat Syst Riggenbachstr 16 CH-4600 Olten Switzerland Univ Fribourg Dept Informat CH-1700 Fribourg Switzerland Univ Appl Sci & Arts Western Switzerland Inst Complex Syst CH-1705 Fribourg Switzerland Univ Pretoria Dept Informat Pretoria South Africa

ISBN: (纸本)9783319589619;9783319589602

About ten years ago, a novel graph edit distance framework based on bipartite graph matching has been introduced. this particular framework allows the approximation of graph edit distance in cubic time. this, in turn, makes the concept of graph edit distance also applicable to larger graphs. In the last decade the corresponding paper has been cited more than 360 times. Besides various extensions from the methodological point of view, we also observe a great variety of applications that make use of the bipartite graph matching framework. the present paper aims at giving a first survey on these applications stemming from six different categories (which range from document analysis, over biometrics to malware detection).

关键词： Applications of bipartite graph matching graph-based pattern representations

来源：评论

学校读者我要写书评

暂无评论

graph edit distance as a quadratic assignment problem

引用

pattern recognition LETTERS 2017年 87卷 38-46页

作者： Bougleux, Sebastien Brun, Luc Carletti, Vincenzo Foggia, Pasquale Gauzere, Benoit Vento, Mario Normandie Univ UNICAEN ENSICAEN CNRSGREYC UMR 6072 6 Bd Marechal Juin F-14050 Caen France Univ Salerno Dept Informat Elect Engn & Appl Math MIVIA Via Giovanni Paolo 2 I-84084 Fisciano SA Italy Normandie Univ INSA Rouen LITIS EA 4108 Ave Univ F-76801 St Etienne Du Rouvray France

the graph Edit Distance (GED) is a flexible measure of dissimilarity between graphs which arises in error-correcting graph matching. It is defined from an optimal sequence of edit operations (edit path) transforming one graph into another. Unfortunately, the exact computation of this measure is NP-hard. In the last decade, several approaches were proposed to approximate the GED in polynomial time, mainly by solving linear programming problems. Among them, the bipartite GED received much attention. It is deduced from a linear sum assignment of the nodes of the two graphs, which can be efficiently computed by Hungarian-type algorithms. However, edit operations on nodes and edges are not handled simultaneously, which limits the accuracy of the approximation. To overcome this limitation, we propose to extend the linear assignment model to a quadratic one. this is achieved through the definition of a family of edit paths induced by assignments between nodes. We formally show that the GED, restricted to the paths in this family, is equivalent to a quadratic assignment problem. Since this problem is NP-hard, we propose to compute an approximate solution by adapting two algorithms: Integer Projected Fixed Point method and Graduated Non Convexity and Concavity Procedure. Experiments show that the proposed approach is generally able to reach a more accurate approximation of the exact GED than the bipartite GED, with a computational cost that is still affordable for graphs of non trivial sizes. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Structural pattern recognition graph edit distance Edit paths Quadratic assignment problem Combinatorial optimization Relaxation methods

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：