By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 4 • Date April 2014

Filter Results

Displaying Results 1 - 21 of 21
  • Table of Contents

    Publication Year: 2014, Page(s): C1
    Request permission for commercial reuse | PDF file iconPDF (158 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 (83 KB)
    Freely Available from IEEE
  • A Geometric Particle Filter for Template-Based Visual Tracking

    Publication Year: 2014, Page(s):625 - 643
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2602 KB) | HTML iconHTML Multimedia Media

    Existing approaches to template-based visual tracking, in which the objective is to continuously estimate the spatial transformation parameters of an object template over video frames, have primarily been based on deterministic optimization, which as is well-known can result in convergence to local optima. To overcome this limitation of the deterministic optimization approach, in this paper we pre... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Histogram Transform for ProbabilityDensity Function Estimation

    Publication Year: 2014, Page(s):644 - 656
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1680 KB) | HTML iconHTML

    The estimation of multivariate probability density functions has traditionally been carried out by mixtures of parametric densities or by kernel density estimators. Here we present a new nonparametric approach to this problem which is based on the integration of several multivariate histograms, computed over affine transformations of the training data. Our proposal belongs to the class of averaged... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Markov Random Field Groupwise Registration Framework for Face Recognition

    Publication Year: 2014, Page(s):657 - 669
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2279 KB) | HTML iconHTML

    In this paper, we propose a new framework for tackling face recognition problem. The face recognition problem is formulated as groupwise deformable image registration and feature matching problem. The main contributions of the proposed method lie in the following aspects: (1) Each pixel in a facial image is represented by an anatomical signature obtained from its corresponding most salient scale l... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Background Subtraction with DirichletProcess Mixture Models

    Publication Year: 2014, Page(s):670 - 683
    Cited by:  Papers (27)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1918 KB) | HTML iconHTML

    Video analysis often begins with background subtraction. This problem is often approached in two steps-a background model followed by a regularisation scheme. A model of the background allows it to be distinguished on a per-pixel basis from the foreground, whilst the regularisation combines information from adjacent pixels. We present a new method based on Dirichlet process Gaussian mixture models... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Camera Localization UsingTrajectories and Maps

    Publication Year: 2014, Page(s):684 - 697
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2091 KB) | HTML iconHTML Multimedia Media

    We propose a new Bayesian framework for automatically determining the position (location and orientation) of an uncalibrated camera using the observations of moving objects and a schematic map of the passable areas of the environment. Our approach takes advantage of static and dynamic information on the scene structures through prior probability distributions for object dynamics. The proposed appr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast and Robust Recursive Algorithmsfor Separable Nonnegative Matrix Factorization

    Publication Year: 2014, Page(s):698 - 714
    Cited by:  Papers (29)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1391 KB) | HTML iconHTML

    In this paper, we study the nonnegative matrix factorization problem under the separability assumption (that is, there exists a cone spanned by a small subset of the columns of the input nonnegative data matrix containing all columns), which is equivalent to the hyperspectral unmixing problem under the linear mixing model and the pure-pixel assumption. We present a family of fast recursive algorit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Jointly Learning Visually Correlated Dictionaries for Large-Scale Visual Recognition Applications

    Publication Year: 2014, Page(s):715 - 730
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3840 KB) | HTML iconHTML

    Learning discriminative dictionaries for image content representation plays a critical role in visual recognition. In this paper, we present a joint dictionary learning (JDL) algorithm which exploits the inter-category visual correlations to learn more discriminative dictionaries. Given a group of visually correlated categories, JDL simultaneously learns one common dictionary and multiple category... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Non-Rigid Object Detection with LocalInterleaved Sequential Alignment (LISA)

    Publication Year: 2014, Page(s):731 - 743
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1945 KB) | HTML iconHTML

    This paper shows that the successively evaluated features used in a sliding window detection process to decide about object presence/absence also contain knowledge about object deformation. We exploit these detection features to estimate the object deformation. Estimated deformation is then immediately applied to not yet evaluated features to align them with the observed image data. In our approac... View full abstract»

    Open Access
  • Optimized Product Quantization

    Publication Year: 2014, Page(s):744 - 755
    Cited by:  Papers (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1733 KB) | HTML iconHTML

    Product quantization (PQ) is an effective vector quantization method. A product quantizer can generate an exponentially large codebook at very low memory/time cost. The essence of PQ is to decompose the high-dimensional vector space into the Cartesian product of subspaces and then quantize these subspaces separately. The optimal space decomposition is important for the PQ performance, but still re... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Preserving Structure in Model-Free Tracking

    Publication Year: 2014, Page(s):756 - 769
    Cited by:  Papers (17)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1847 KB) | HTML iconHTML Multimedia Media

    Model-free trackers can track arbitrary objects based on a single (bounding-box) annotation of the object. Whilst the performance of model-free trackers has recently improved significantly, simultaneously tracking multiple objects with similar appearance remains very hard. In this paper, we propose a new multi-object model-free tracker (using a tracking-by-detection framework) that resolves this p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust Recovery of Corrupted Low-RankMatrix by Implicit Regularizers

    Publication Year: 2014, Page(s):770 - 783
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1640 KB) | HTML iconHTML Multimedia Media

    Low-rank matrix recovery algorithms aim to recover a corrupted low-rank matrix with sparse errors. However, corrupted errors may not be sparse in real-world problems and the relationship between ℓ1 regularizer on noise and robust M-estimators is still unknown. This paper proposes a general robust framework for low-rank matrix recovery via implicit regularizers of robust M-estimat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Applicability of Spatiotemporal Oriented Energy Features to Region Tracking

    Publication Year: 2014, Page(s):784 - 796
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1671 KB) | HTML iconHTML

    This paper proposes the novel application of an uncommonly rich feature representation to the domain of visual tracking. The proposed representation for tracking models both the spatial structure and dynamics of a target in a unified fashion, while simultaneously offering robustness to illumination variations. Specifically, the proposed feature is derived from spatiotemporal energy measurements th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Virtual and Real World Adaptation for Pedestrian Detection

    Publication Year: 2014, Page(s):797 - 809
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2200 KB) | HTML iconHTML

    Pedestrian detection is of paramount interest for many applications. Most promising detectors rely on discriminatively learnt classifiers, i.e., trained with annotated samples. However, the annotation step is a human intensive and subjective task worth to be minimized. By using virtual worlds we can automatically obtain precise and rich annotations. Thus, we face the question: can a pedestrian app... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Web Image Re-Ranking UsingQuery-Specific Semantic Signatures

    Publication Year: 2014, Page(s):810 - 823
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1410 KB) | HTML iconHTML Multimedia Media

    Image re-ranking, as an effective way to improve the results of web-based image search, has been adopted by current commercial search engines such as Bing and Google. Given a query keyword, a pool of images are first retrieved based on textual information. By asking the user to select a query image from the pool, the remaining images are re-ranked based on their visual similarities with the query ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multimodal Similarity-Preserving Hashing

    Publication Year: 2014, Page(s):824 - 830
    Cited by:  Papers (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1840 KB) | HTML iconHTML

    We introduce an efficient computational framework for hashing data belonging to multiple modalities into a single representation space where they become mutually comparable. The proposed approach is based on a novel coupled siamese neural network architecture and allows unified treatment of intra- and inter-modality similarity learning. Unlike existing cross-modality similarity learning approaches... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Open Access

    Publication Year: 2014, Page(s): 831
    Request permission for commercial reuse | PDF file iconPDF (1157 KB)
    Freely Available from IEEE
  • myIEEE

    Publication Year: 2014, Page(s): 832
    Request permission for commercial reuse | PDF file iconPDF (771 KB)
    Freely Available from IEEE
  • 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 (83 KB)
    Freely Available from IEEE
  • IEEE Computer Society [Advertisement]

    Publication Year: 2014, Page(s): C4
    Request permission for commercial reuse | PDF file iconPDF (159 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