Scheduled System Maintenance
On Tuesday, September 26, IEEE Xplore will undergo scheduled maintenance from 1:00-4:00 PM ET.
During this time, there may be intermittent impact on performance. We apologize for any inconvenience.

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 1 • Jan. 2015

Filter Results

Displaying Results 1 - 23 of 23
  • Table of contents

    Publication Year: 2015, Page(s): C1
    Request permission for commercial reuse | PDF file iconPDF (325 KB)
    Freely Available from IEEE
  • IEEE Transactions on Pattern Analysis and Machine Intelligence Editorial Board

    Publication Year: 2015, Page(s): C2
    Request permission for commercial reuse | PDF file iconPDF (319 KB)
    Freely Available from IEEE
  • State of the Journal

    Publication Year: 2015, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (34 KB) | HTML iconHTML
    Freely Available from IEEE
  • A Hybrid Loss for Multiclass and Structured Prediction

    Publication Year: 2015, Page(s):2 - 12
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (900 KB) | HTML iconHTML

    We propose a novel hybrid loss for multiclass and structured prediction problems that is a convex combination of a log loss for Conditional Random Fields (CRFs) and a multiclass hinge loss for Support Vector Machines (SVMs). We provide a sufficient condition for when the hybrid loss is Fisher consistent for classification. This condition depends on a measure of dominance between labels-specificall... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Contextualizing Object Detection and Classification

    Publication Year: 2015, Page(s):13 - 27
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1752 KB) | HTML iconHTML

    We investigate how to iteratively and mutually boost object classification and detection performance by taking the outputs from one task as the context of the other one. While context models have been quite popular, previous works mainly concentrate on co-occurrence relationship within classes and few of them focus on contextualization from a top-down perspective, i.e. high-level task context. In ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Convex Discriminative Multitask Clustering

    Publication Year: 2015, Page(s):28 - 40
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1687 KB) | HTML iconHTML Multimedia Media

    Multitask clustering tries to improve the clustering performance of multiple tasks simultaneously by taking their relationship into account. Most existing multitask clustering algorithms fall into the type of generative clustering, and none are formulated as convex optimization problems. In this paper, we propose two convex Discriminative Multitask Clustering (DMTC) objectives to address the probl... View full abstract»

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

    Publication Year: 2015, Page(s):41 - 53
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (597 KB) | HTML iconHTML

    For most problems in science and engineering we can obtain data sets that describe the observed system from various perspectives and record the behavior of its individual components. Heterogeneous data sets can be collectively mined by data fusion. Fusion can focus on a specific target relation and exploit directly associated data together with contextual data and data about system's constraints. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature Space Independent Semi-Supervised Domain Adaptation via Kernel Matching

    Publication Year: 2015, Page(s):54 - 66
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (831 KB) | HTML iconHTML Multimedia Media

    Domain adaptation methods aim to learn a good prediction model in a label-scarce target domain by leveraging labeled patterns from a related source domain where there is a large amount of labeled data. However, in many practical domain adaptation learning scenarios, the feature distribution in the source domain is different from that in the target domain. In the extreme, the two distributions coul... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • From Shading to Local Shape

    Publication Year: 2015, Page(s):67 - 79
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1569 KB) | HTML iconHTML Multimedia Media

    We develop a framework for extracting a concise representation of the shape information available from diffuse shading in a small image patch. This produces a mid-level scene descriptor, comprised of local shape distributions that are inferred separately at every image patch across multiple scales. The framework is based on a quadratic representation of local shape that, in the absence of noise, h... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Gentle Nearest Neighbors Boosting over Proper Scoring Rules

    Publication Year: 2015, Page(s):80 - 93
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2386 KB) | HTML iconHTML

    Tailoring nearest neighbors algorithms to boosting is an important problem. Recent papers study an approach, UNN, which provably minimizes particular convex surrogates under weak assumptions. However, numerical issues make it necessary to experimentally tweak parts of the UNN algorithm, at the possible expense of the algorithm's convergence and performance. In this paper, we propose a lightweight ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning Separable Filters

    Publication Year: 2015, Page(s):94 - 106
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1324 KB) | HTML iconHTML Multimedia Media

    Learning filters to produce sparse image representations in terms of over-complete dictionaries has emerged as a powerful way to create image features for many different purposes. Unfortunately, these filters are usually both numerous and non-separable, making their use computationally expensive. In this paper, we show that such filters can be computed as linear combinations of a smaller number of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Lift: Multi-Label Learning with Label-Specific Features

    Publication Year: 2015, Page(s):107 - 120
    Cited by:  Papers (24)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (497 KB) | HTML iconHTML Multimedia Media

    Multi-label learning deals with the problem where each example is represented by a single instance (feature vector) while associated with a set of class labels. Existing approaches learn from multi-label data by manipulating with identical feature set, i.e. the very instance representation of each example is employed in the discrimination processes of all class labels. However, this popular strate... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Matrix Completion for Weakly-Supervised Multi-Label Image Classification

    Publication Year: 2015, Page(s):121 - 135
    Cited by:  Papers (19)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1377 KB) | HTML iconHTML

    In the last few years, image classification has become an incredibly active research topic, with widespread applications. Most methods for visual recognition are fully supervised, as they make use of bounding boxes or pixelwise segmentations to locate objects of interest. However, this type of manual labeling is time consuming, error prone and it has been shown that manual segmentations are not ne... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rank-Based Similarity Search: Reducing the Dimensional Dependence

    Publication Year: 2015, Page(s):136 - 150
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1568 KB) | HTML iconHTML

    This paper introduces a data structure for k-NN search, the Rank Cover Tree (RCT), whose pruning tests rely solely on the comparison of similarity values; other properties of the underlying space, such as the triangle inequality, are not employed. Objects are selected according to their ranks with respect to the query object, allowing much tighter control on the overall execution costs. A formal t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shape Matching Using Multiscale Integral Invariants

    Publication Year: 2015, Page(s):151 - 160
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1495 KB) | HTML iconHTML

    We present a shape descriptor based on integral kernels. Shape is represented in an implicit form and it is characterized by a series of isotropic kernels that provide desirable invariance properties. The shape features are characterized at multiple scales which form a signature that is a compact description of shape over a range of scales. The shape signature is designed to be invariant with resp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tangent Bundle Elastica and Computer Vision

    Publication Year: 2015, Page(s):161 - 174
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1428 KB) | HTML iconHTML

    Visual curve completion, an early visual process that completes the occluded parts between observed boundary fragments (a.k.a. inducers), is a major problem in perceptual organization and a critical step toward higher level visual tasks in both biological and machine vision. Most computational contributions to solving this problem suggest desired perceptual properties that the completed contour sh... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards Making Unlabeled Data Never Hurt

    Publication Year: 2015, Page(s):175 - 188
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2617 KB) | HTML iconHTML

    It is usually expected that learning performance can be improved by exploiting unlabeled data, particularly when the number of labeled data is limited. However, it has been reported that, in some cases existing semi-supervised learning approaches perform even worse than supervised ones which only use labeled data. For this reason, it is desirable to develop safe semi-supervised learning approaches... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Data-Driven Objectness

    Publication Year: 2015, Page(s):189 - 195
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1149 KB) | HTML iconHTML

    We propose a data-driven approach to estimate the likelihood that an image segment corresponds to a scene object (its “objectness”) by comparing it to a large collection of example object regions. We demonstrate that when the application domain is known, for example, in our case activity of daily living (ADL), we can capture the regularity of the domain specific objects using million... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Low Bias Local Intrinsic Dimension Estimation from Expected Simplex Skewness

    Publication Year: 2015, Page(s):196 - 202
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (465 KB) | HTML iconHTML Multimedia Media

    In exploratory high-dimensional data analysis, local intrinsic dimension estimation can sometimes be used in order to discriminate between data sets sampled from different low-dimensional structures. Global intrinsic dimension estimators can in many cases be adapted to local estimation, but this leads to problems with high negative bias or high variance. We introduce a method that exploits the cur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 2014 Reviewers List*

    Publication Year: 2015, Page(s):203 - 208
    Request permission for commercial reuse | PDF file iconPDF (38 KB)
    Freely Available from IEEE
  • 2014 Index IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 36

    Publication Year: 2015, Page(s):209 - 231
    Request permission for commercial reuse | PDF file iconPDF (443 KB)
    Freely Available from IEEE
  • IEEE Transactions on Pattern Analysis and Machine Intelligence Information for Authors

    Publication Year: 2015, Page(s): C3
    Request permission for commercial reuse | PDF file iconPDF (319 KB)
    Freely Available from IEEE
  • IEEE Computer Society [advertisement]

    Publication Year: 2015, Page(s): C4
    Request permission for commercial reuse | PDF file iconPDF (325 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