By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 6 • Date June 2012

Filter Results

Displaying Results 1 - 22 of 22
  • [Front cover]

    Publication Year: 2012, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (168 KB)
    Freely Available from IEEE
  • [Inside front cover]

    Publication Year: 2012, Page(s): c2
    Request permission for commercial reuse | PDF file iconPDF (200 KB)
    Freely Available from IEEE
  • A Least-Squares Framework for Component Analysis

    Publication Year: 2012, Page(s):1041 - 1055
    Cited by:  Papers (35)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (532 KB) | HTML iconHTML

    Over the last century, Component Analysis (CA) methods such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Canonical Correlation Analysis (CCA), Locality Preserving Projections (LPP), and Spectral Clustering (SC) have been extensively used as a feature extraction step for modeling, classification, visualization, and clustering. CA techniques are appealing because many c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting Carried Objects from Sequences of Walking Pedestrians

    Publication Year: 2012, Page(s):1056 - 1067
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2457 KB) | HTML iconHTML

    This paper proposes a method for detecting objects carried by pedestrians, such as backpacks and suitcases, from video sequences. In common with earlier work [14], [16] on the same problem, the method produces a representation of motion and shape (known as a temporal template) that has some immunity to noise in foreground segmentations and phase of the walking cycle. Our key novelty is for carried... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast Bundle Algorithm for Multiple-Instance Learning

    Publication Year: 2012, Page(s):1068 - 1079
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1588 KB) | HTML iconHTML

    We present a bundle algorithm for multiple-instance classification and ranking. These frameworks yield improved models on many problems possessing special structure. Multiple-instance loss functions are typically nonsmooth and nonconvex, and current algorithms convert these to smooth nonconvex optimization problems that are solved iteratively. Inspired by the latest linear-time subgradient-based m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intrinsic Dimensionality Predicts the Saliency of Natural Dynamic Scenes

    Publication Year: 2012, Page(s):1080 - 1091
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1805 KB) | HTML iconHTML

    Since visual attention-based computer vision applications have gained popularity, ever more complex, biologically inspired models seem to be needed to predict salient locations (or interest points) in naturalistic scenes. In this paper, we explore how far one can go in predicting eye movements by using only basic signal processing, such as image representations derived from efficient coding princi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Kernelized Locality-Sensitive Hashing

    Publication Year: 2012, Page(s):1092 - 1104
    Cited by:  Papers (60)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1833 KB) | HTML iconHTML

    Fast retrieval methods are critical for many large-scale and data-driven vision applications. Recent work has explored ways to embed high-dimensional features or complex distance functions into a low-dimensional Hamming space where items can be efficiently searched. However, existing methods do not apply for high-dimensional kernelized data when the underlying feature embedding for the kernel is u... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Latent Log-Linear Models for Handwritten Digit Classification

    Publication Year: 2012, Page(s):1105 - 1117
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2233 KB) | HTML iconHTML

    We present latent log-linear models, an extension of log-linear models incorporating latent variables, and we propose two applications thereof: log-linear mixture models and image deformation-aware log-linear models. The resulting models are fully discriminative, can be trained efficiently, and the model complexity can be controlled. Log-linear mixture models offer additional flexibility within th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Monocular 3D Reconstruction of Locally Textured Surfaces

    Publication Year: 2012, Page(s):1118 - 1130
    Cited by:  Papers (4)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2984 KB) | HTML iconHTML Multimedia Media

    Most recent approaches to monocular nonrigid 3D shape recovery rely on exploiting point correspondences and work best when the whole surface is well textured. The alternative is to rely on either contours or shading information, which has only been demonstrated in very restrictive settings. Here, we propose a novel approach to monocular deformable shape recovery that can operate under complex ligh... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Prototype-Based Domain Description for One-Class Classification

    Publication Year: 2012, Page(s):1131 - 1144
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2055 KB) | HTML iconHTML

    This work introduces the Prototype-based Domain Description rule (PDD) one-class classifier. PDD is a nearest neighbor-based classifier since it accepts objects on the basis of their nearest neighbor distances in a reference set of objects, also called prototypes. For a suitable choice of the prototype set, the PDD classifier is equivalent to another nearest neighbor-based one-class classifier, na... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reading between the Lines: Object Localization Using Implicit Cues from Image Tags

    Publication Year: 2012, Page(s):1145 - 1158
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5646 KB) | HTML iconHTML Multimedia Media

    Current uses of tagged images typically exploit only the most explicit information: the link between the nouns named and the objects present somewhere in the image. We propose to leverage “unspoken” cues that rest within an ordered list of image tags so as to improve object localization. We define three novel implicit features from an image's tags-the relative prominence of each obje... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rhythmic Brushstrokes Distinguish van Gogh from His Contemporaries: Findings via Automated Brushstroke Extraction

    Publication Year: 2012, Page(s):1159 - 1176
    Cited by:  Papers (17)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4394 KB) | HTML iconHTML

    Art historians have long observed the highly characteristic brushstroke styles of Vincent van Gogh and have relied on discerning these styles for authenticating and dating his works. In our work, we compared van Gogh with his contemporaries by statistically analyzing a massive set of automatically extracted brushstrokes. A novel extraction method is developed by exploiting an integration of edge d... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simultaneously Fitting and Segmenting Multiple-Structure Data with Outliers

    Publication Year: 2012, Page(s):1177 - 1192
    Cited by:  Papers (24)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4038 KB) | HTML iconHTML

    We propose a robust fitting framework, called Adaptive Kernel-Scale Weighted Hypotheses (AKSWH), to segment multiple-structure data even in the presence of a large number of outliers. Our framework contains a novel scale estimator called Iterative Kth Ordered Scale Estimator (IKOSE). IKOSE can accurately estimate the scale of inliers for heavily corrupted multiple-structure data and is of interest... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spacetime Texture Representation and Recognition Based on a Spatiotemporal Orientation Analysis

    Publication Year: 2012, Page(s):1193 - 1205
    Cited by:  Papers (20)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2819 KB) | HTML iconHTML

    This paper is concerned with the representation and recognition of the observed dynamics (i.e., excluding purely spatial appearance cues) of spacetime texture based on a spatiotemporal orientation analysis. The term “spacetime texture” is taken to refer to patterns in visual spacetime, (x,y,t), that primarily are characterized by the aggregate dynamic properties of elements or local ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spatiotemporal Stereo and Scene Flow via Stequel Matching

    Publication Year: 2012, Page(s):1206 - 1219
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3438 KB) | HTML iconHTML

    This paper is concerned with the recovery of temporally coherent estimates of 3D structure and motion of a dynamic scene from a sequence of binocular stereo images. A novel approach is presented based on matching of spatiotemporal quadric elements (stequels) between views, as this primitive encapsulates both spatial and temporal image structure for 3D estimation. Match constraints are developed fo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Blur-Robust Descriptor with Applications to Face Recognition

    Publication Year: 2012, Page(s):1220 - 1226
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1335 KB) | HTML iconHTML Multimedia Media

    Understanding the effect of blur is an important problem in unconstrained visual analysis. We address this problem in the context of image-based recognition by a fusion of image-formation models and differential geometric tools. First, we discuss the space spanned by blurred versions of an image and then, under certain assumptions, provide a differential geometric analysis of that space. More spec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Ensemble Manifold Regularization

    Publication Year: 2012, Page(s):1227 - 1233
    Cited by:  Papers (95)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1119 KB) | HTML iconHTML Multimedia Media

    We propose an automatic approximation of the intrinsic manifold for general semi-supervised learning (SSL) problems. Unfortunately, it is not trivial to define an optimization function to obtain optimal hyperparameters. Usually, cross validation is applied, but it does not necessarily scale up. Other problems derive from the suboptimality incurred by discrete grid search and the overfitting. There... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Medial Spheres for Shape Approximation

    Publication Year: 2012, Page(s):1234 - 1240
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1648 KB) | HTML iconHTML

    We study the problem of approximating a 3D solid with a union of overlapping spheres. In comparison with a state-of-the-art approach, our method offers more than an order of magnitude speedup and achieves a tighter approximation in terms of volume difference with the original solid while using fewer spheres. The spheres generated by our method are internal and tangent to the solid's boundary, whic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • VCells: Simple and Efficient Superpixels Using Edge-Weighted Centroidal Voronoi Tessellations

    Publication Year: 2012, Page(s):1241 - 1247
    Cited by:  Papers (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1936 KB) | HTML iconHTML

    VCells, the proposed Edge-Weighted Centroidal Voronoi Tessellations (EWCVTs)-based algorithm, is used to generate superpixels, i.e., an oversegmentation of an image. For a wide range of images, the new algorithm is capable of generating roughly uniform subregions and nicely preserving local image boundaries. The undersegmentation error is effectively limited in a controllable manner. Moreover, VCe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • IEEE Computer Society OnlinePlus Tutorial Video

    Publication Year: 2012, Page(s): 1248
    Request permission for commercial reuse | PDF file iconPDF (773 KB)
    Freely Available from IEEE
  • [Inside back cover]

    Publication Year: 2012, Page(s): c3
    Request permission for commercial reuse | PDF file iconPDF (201 KB)
    Freely Available from IEEE
  • [Back cover]

    Publication Year: 2012, Page(s): c4
    Request permission for commercial reuse | PDF file iconPDF (168 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
David A. Forsyth
University of Illinois
e-mail: daf@illinois.edu