By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 6 • Date June 2014

Filter Results

Displaying Results 1 - 22 of 22
  • Table of Contents

    Publication Year: 2014, Page(s): C1
    Request permission for commercial reuse | PDF file iconPDF (354 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 (315 KB)
    Freely Available from IEEE
  • A Unified Approach for Registration and Depth in Depth from Defocus

    Publication Year: 2014, Page(s):1041 - 1055
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2268 KB) | HTML iconHTML Multimedia Media

    Depth from Defocus (DFD) suggests a simple optical set-up to recover the shape of a scene through imaging with shallow depth of field. Although numerous methods have been proposed for DFD, less attention has been paid to the particular problem of alignment between the captured images. The inherent shift-variant defocus often prevents standard registration techniques from achieving the accuracy nee... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Associative Hierarchical Random Fields

    Publication Year: 2014, Page(s):1056 - 1077
    Cited by:  Papers (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4215 KB) | HTML iconHTML

    This paper makes two contributions: the first is the proposal of a new model-The associative hierarchical random field (AHRF), and a novel algorithm for its optimization; the second is the application of this model to the problem of semantic segmentation. Most methods for semantic segmentation are formulated as a labeling problem for variables that might correspond to either pixels or segments suc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bi-Polynomial Modeling of Low-Frequency Reflectances

    Publication Year: 2014, Page(s):1078 - 1091
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2296 KB) | HTML iconHTML

    We present a bi-polynomial reflectance model that can precisely represent the low-frequency component of reflectance. Most existing reflectance models aim at accurately representing the complete reflectance domain for photo-realistic rendering purposes. In contrast, our bi-polynomial model is developed for the purpose of accurately solving inverse problems by effectively discarding the high-freque... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • “Clustering by Composition”—Unsupervised Discovery of Image Categories

    Publication Year: 2014, Page(s):1092 - 1106
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1719 KB) | HTML iconHTML

    We define a “good image cluster” as one in which images can be easily composed (like a puzzle) using pieces from each other, while are difficult to compose from images outside the cluster. The larger and more statistically significant the pieces are, the stronger the affinity between the images. This gives rise to unsupervised discovery of very challenging image categories. We furthe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast Exact Search in Hamming Space With Multi-Index Hashing

    Publication Year: 2014, Page(s):1107 - 1119
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1842 KB) | HTML iconHTML

    There is growing interest in representing image data and feature descriptors using compact binary codes for fast near neighbor search. Although binary codes are motivated by their use as direct indices (addresses) into a hash table, codes longer than 32 bits are not being used as such, as it was thought to be ineffective. We introduce a rigorous way to build multiple hash tables on binary code sub... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Iris Image Classification Based on Hierarchical Visual Codebook

    Publication Year: 2014, Page(s):1120 - 1133
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1708 KB) | HTML iconHTML Multimedia Media

    Iris recognition as a reliable method for personal identification has been well-studied with the objective to assign the class label of each iris image to a unique subject. In contrast, iris image classification aims to classify an iris image to an application specific category, e.g., iris liveness detection (classification of genuine and fake iris images), race classification (e.g., classificatio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning With Augmented Features for Supervised and Semi-Supervised Heterogeneous Domain Adaptation

    Publication Year: 2014, Page(s):1134 - 1148
    Cited by:  Papers (23)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1306 KB) | HTML iconHTML Multimedia Media

    In this paper, we study the heterogeneous domain adaptation (HDA) problem, in which the data from the source domain and the target domain are represented by heterogeneous features with different dimensions. By introducing two different projection matrices, we first transform the data from two domains into a common subspace such that the similarity between samples across different domains can be me... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mixtures of Shifted AsymmetricLaplace Distributions

    Publication Year: 2014, Page(s):1149 - 1157
    Cited by:  Papers (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (749 KB) | HTML iconHTML

    A mixture of shifted asymmetric Laplace distributions is introduced and used for clustering and classification. A variant of the EM algorithm is developed for parameter estimation by exploiting the relationship with the generalized inverse Gaussian distribution. This approach is mathematically elegant and relatively computationally straightforward. Our novel mixture modelling approach is demonstra... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Online Learning and Sequential Anomaly Detection in Trajectories

    Publication Year: 2014, Page(s):1158 - 1173
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1214 KB) | HTML iconHTML

    Detection of anomalous trajectories is an important problem in the surveillance domain. Various algorithms based on learning of normal trajectory patterns have been proposed for this problem. Yet, these algorithms typically suffer from one or more limitations: They are not designed for sequential analysis of incomplete trajectories or online learning based on an incrementally updated training set.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On-Line Video Event Detection by Constraint Flow

    Publication Year: 2014, Page(s):1174 - 1186
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2402 KB) | HTML iconHTML Multimedia Media

    We present a novel approach in describing and detecting the composite video events based on scenarios, which constrain the configurations of target events by temporal-logical structures of primitive events. We propose a new scenario description method to represent composite events more fluently and efficiently, and discuss an on-line event detection algorithm based on a combinatorial optimization.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation of Moving Objects by Long Term Video Analysis

    Publication Year: 2014, Page(s):1187 - 1200
    Cited by:  Papers (36)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2572 KB) | HTML iconHTML

    Motion is a strong cue for unsupervised object-level grouping. In this paper, we demonstrate that motion will be exploited most effectively, if it is regarded over larger time windows. Opposed to classical two-frame optical flow, point trajectories that span hundreds of frames are less susceptible to short-term variations that hinder separating different objects. As a positive side effect, the res... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semi-Supervised Kernel Mean Shift Clustering

    Publication Year: 2014, Page(s):1201 - 1215
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3012 KB) | HTML iconHTML Multimedia Media

    Mean shift clustering is a powerful nonparametric technique that does not require prior knowledge of the number of clusters and does not constrain the shape of the clusters. However, being completely unsupervised, its performance suffers when the original distance metric fails to capture the underlying cluster structure. Despite recent advances in semi-supervised clustering methods, there has been... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Soft Biometrics; Human Identification Using Comparative Descriptions

    Publication Year: 2014, Page(s):1216 - 1228
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1415 KB) | HTML iconHTML

    Soft biometrics are a new form of biometric identification which use physical or behavioral traits that can be naturally described by humans. Unlike other biometric approaches, this allows identification based solely on verbal descriptions, bridging the semantic gap between biometrics and human description. To permit soft biometric identification the description must be accurate, yet conventional ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spatially-Constrained Similarity Measurefor Large-Scale Object Retrieval

    Publication Year: 2014, Page(s):1229 - 1241
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1756 KB) | HTML iconHTML

    One fundamental problem in object retrieval with the bag-of-words model is its lack of spatial information. Although various approaches are proposed to incorporate spatial constraints into the model, most of them are either too strict or too loose so that they are only effective in limited cases. In this paper, a new spatially-constrained similarity measure (SCSM) is proposed to handle object rota... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Understanding Collective Activitiesof People from Videos

    Publication Year: 2014, Page(s):1242 - 1257
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1878 KB) | HTML iconHTML

    This paper presents a principled framework for analyzing collective activities at different levels of semantic granularity from videos. Our framework is capable of jointly tracking multiple individuals, recognizing activities performed by individuals in isolation (i.e., atomic activities such as walking or standing), recognizing the interactions between pairs of individuals (i.e., interaction acti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • GNCCP—Graduated NonConvexityand Concavity Procedure

    Publication Year: 2014, Page(s):1258 - 1267
    Cited by:  Papers (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1447 KB) | HTML iconHTML Multimedia Media

    In this paper we propose the graduated nonconvexity and concavity procedure (GNCCP) as a general optimization framework to approximately solve the combinatorial optimization problems defined on the set of partial permutation matrices. GNCCP comprises two sub-procedures, graduated nonconvexity which realizes a convex relaxation and graduated concavity which realizes a concave relaxation. It is prov... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Sum-over-Forests Density Index: Identifying Dense Regions in a Graph

    Publication Year: 2014, Page(s):1268 - 1274
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (652 KB) | HTML iconHTML Multimedia Media

    This work introduces a novel nonparametric density index defined on graphs, the Sum-over-Forests (SoF) density index. It is based on a clear and intuitive idea: high-density regions in a graph are characterized by the fact that they contain a large amount of low-cost trees with high outdegrees while low-density regions contain few ones. Therefore, a Boltzmann probability distribution on the counta... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Transform-Invariant PCA: A Unified Approach to Fully Automatic FaceAlignment, Representation, and Recognition

    Publication Year: 2014, Page(s):1275 - 1284
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1477 KB) | HTML iconHTML Multimedia Media

    We develop a transform-invariant PCA (TIPCA) technique which aims to accurately characterize the intrinsic structures of the human face that are invariant to the in-plane transformations of the training images. Specially, TIPCA alternately aligns the image ensemble and creates the optimal eigenspace, with the objective to minimize the mean square error between the aligned images and their reconstr... 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 (315 KB)
    Freely Available from IEEE
  • IEEE Computer Society

    Publication Year: 2014, Page(s): C4
    Request permission for commercial reuse | PDF file iconPDF (354 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