IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 10 • Oct. 2014

Filter Results

Displaying Results 1 - 19 of 19
  • Table of Contents

    Publication Year: 2014, Page(s): C1
    Request permission for commercial reuse | |PDF file iconPDF (315 KB)
    Freely Available from IEEE
  • IEEE Transactions on Pattern Analysis and Machine Intelligence Editorial Board

    Publication Year: 2014, Page(s): C2
    Request permission for commercial reuse | |PDF file iconPDF (318 KB)
    Freely Available from IEEE
  • A Framework for Analysis of Computational Imaging Systems: Role of Signal Prior, Sensor Noise and Multiplexing

    Publication Year: 2014, Page(s):1909 - 1921
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1466 KB) | HTML iconHTML

    Over the last decade, a number of computational imaging (CI) systems have been proposed for tasks such as motion deblurring, defocus deblurring and multispectral imaging. These techniques increase the amount of light reaching the sensor via multiplexing and then undo the deleterious effects of multiplexing by appropriate reconstruction algorithms. Given the widespread appeal and the considerable e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A MultiScale Particle Filter Framework for Contour Detection

    Publication Year: 2014, Page(s):1922 - 1935
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2067 KB)

    We investigate the contour detection task in complex natural images. We propose a novel contour detection algorithm which jointly tracks at two scales small pieces of edges called edgelets. This multiscale edgelet structure naturally embeds semi-local information and is the basic element of the proposed recursive Bayesian modeling. Prior and transition distributions are learned offline using a sha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Batch-Orthogonal Locality-Sensitive Hashing for Angular Similarity

    Publication Year: 2014, Page(s):1963 - 1974
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (805 KB) | HTML iconHTML Multimedia Media

    Sign-random-projection locality-sensitive hashing (SRP-LSH) is a widely used hashing method, which provides an unbiased estimate of pairwise angular similarity, yet may suffer from its large estimation variance. We propose in this work batch-orthogonal locality-sensitive hashing (BOLSH), as a significant improvement of SRP-LSH. Instead of independent random projections, BOLSH makes use of batch-or... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Active Learning by Querying Informative and Representative Examples

    Publication Year: 2014, Page(s):1936 - 1949
    Cited by:  Papers (38)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2109 KB)

    Active learning reduces the labeling cost by iteratively selecting the most valuable data to query their labels. It has attracted a lot of interests given the abundance of unlabeled data and the high cost of labeling. Most active learning approaches select either informative or representative unlabeled instances to query their labels, which could significantly limit their performance. Although sev... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Autonomous Document Cleaning—A Generative Approach to Reconstruct Strongly Corrupted Scanned Texts

    Publication Year: 2014, Page(s):1950 - 1962
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1349 KB) | HTML iconHTML Multimedia Media

    We study the task of cleaning scanned text documents that are strongly corrupted by dirt such as manual line strokes, spilled ink, etc. We aim at autonomously removing such corruptions from a single letter-size page based only on the information the page contains. Our approach first learns character representations from document patches without supervision. For learning, we use a probabilistic gen... View full abstract»

    Open Access
  • Block-Sparse RPCA for Salient Motion Detection

    Publication Year: 2014, Page(s):1975 - 1987
    Cited by:  Papers (26)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2303 KB) | HTML iconHTML

    Recent evaluation [2], [13] of representative background subtraction techniques demonstrated that there are still considerable challenges facing these methods. Challenges in realistic environment include illumination change causing complex intensity variation, background motions (trees, waves, etc.) whose magnitude can be greater than those of the foreground, poor image quality under low light, ca... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Classemes and Other Classifier-Based Features for Efficient Object Categorization

    Publication Year: 2014, Page(s):1988 - 2001
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (984 KB) |  Multimedia Media

    This paper describes compact image descriptors enabling accurate object categorization with linear classification models, which offer the advantage of being efficient to both train and test. The shared property of our descriptors is the use of classifiers to produce the features of each image. Intuitively, these classifiers evaluate the presence of a set of basis classes inside the image. We first... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive Linear Regression for Appearance-Based Gaze Estimation

    Publication Year: 2014, Page(s):2033 - 2046
    Cited by:  Papers (37)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2055 KB)

    We investigate the appearance-based gaze estimation problem, with respect to its essential difficulty in reducing the number of required training samples, and other practical issues such as slight head motion, image resolution variation, and eye blinking. We cast the problem as mapping high-dimensional eye image features to low-dimensional gaze positions, and propose an adaptive linear regression ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast Compressive Tracking

    Publication Year: 2014, Page(s):2002 - 2015
    Cited by:  Papers (194)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2833 KB) | HTML iconHTML

    It is a challenging task to develop effective and efficient appearance models for robust object tracking due to factors such as pose variation, illumination change, occlusion, and motion blur. Existing online tracking algorithms often update models with samples from observations in recent frames. Despite much success has been demonstrated, numerous issues remain to be addressed. First, while these... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • High Dimensional Semiparametric Scale-Invariant Principal Component Analysis

    Publication Year: 2014, Page(s):2016 - 2032
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (5532 KB)

    We propose a new high dimensional semiparametric principal component analysis (PCA) method, named Copula Component Analysis (COCA). The semiparametric model assumes that, after unspecified marginally monotone transformations, the distributions are multivariate Gaussian. COCA improves upon PCA and sparse PCA in three aspects: (i) It is robust to modeling assumptions; (ii) It is robust to outliers a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sparse Feature Extraction for Pose-Tolerant Face Recognition

    Publication Year: 2014, Page(s):2061 - 2073
    Cited by:  Papers (16)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2269 KB)

    Automatic face recognition performance has been steadily improving over years of research, however it remains significantly affected by a number of factors such as illumination, pose, expression, resolution and other factors that can impact matching scores. The focus of this paper is the pose problem which remains largely overlooked in most real-world applications. Specifically, we focus on one-to... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Statistical Inverse Ray Tracing for Image-Based 3D Modeling

    Publication Year: 2014, Page(s):2074 - 2088
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2070 KB) | HTML iconHTML Multimedia Media

    This paper proposes a new formulation and solution to image-based 3D modeling (aka “multi-view stereo”) based on generative statistical modeling and inference. The proposed new approach, named statistical inverse ray tracing, models and estimates the occlusion relationship accurately through optimizing a physically sound image generation model based on volumetric ray tracing. Togethe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Kernelized Bayesian Matrix Factorization

    Publication Year: 2014, Page(s):2047 - 2060
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1105 KB)

    We extend kernelized matrix factorization with a full-Bayesian treatment and with an ability to work with multiple side information sources expressed as different kernels. Kernels have been introduced to integrate side information about the rows and columns, which is necessary for making out-of-matrix predictions. We discuss specifically binary output matrices but extensions to realvalued matrices... View full abstract»

    Open Access
  • Structured Labels in Random Forests for Semantic Labelling and Object Detection

    Publication Year: 2014, Page(s):2104 - 2116
    Cited by:  Papers (17)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1432 KB) | HTML iconHTML Multimedia Media

    Ensembles of randomized decision trees, known as Random Forests, have become a valuable machine learning tool for addressing many computer vision problems. Despite their popularity, few works have tried to exploit contextual and structural information in random forests in order to improve their performance. In this paper, we propose a simple and effective way to integrate contextual information in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • StructBoost: Boosting Methods for Predicting Structured Output Variables

    Publication Year: 2014, Page(s):2089 - 2103
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1828 KB) | HTML iconHTML Multimedia Media

    Boosting is a method for learning a single accurate predictor by linearly combining a set of less accurate weak learners. Recently, structured learning has found many applications in computer vision. Inspired by structured support vector machines (SSVM), here we propose a new boosting algorithm for structured output prediction, which we refer to as StructBoost. StructBoost supports nonlinear struc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • IEEE Transactions on Pattern Analysis and Machine Intelligence Information for Authors

    Publication Year: 2014, Page(s): C3
    Request permission for commercial reuse | |PDF file iconPDF (318 KB)
    Freely Available from IEEE
  • IEEE Computer Society

    Publication Year: 2014, Page(s): C4
    Request permission for commercial reuse | |PDF file iconPDF (315 KB)
    Freely Available from IEEE

Aims & Scope

The IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) is published monthly. Its editorial board strives to present most important research results in areas within TPAMI's scope.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
Sven Dickinson
University of Toronto
e-mail: sven@cs.toronto.edu