IEEE Transactions on Pattern Analysis and Machine Intelligence

Volume 37 Issue 5 • May 2015

Filter Results

Displaying Results 1 - 20 of 20
  • Table of Contents

    Publication Year: 2015, Page(s): C1
    Request permission for commercial reuse | PDF file iconPDF (286 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 (318 KB)
    Freely Available from IEEE
  • 3D Reasoning from Blocks to Stability

    Publication Year: 2015, Page(s):905 - 918
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1414 KB) | HTML iconHTML

    Objects occupy physical space and obey physical laws. To truly understand a scene, we must reason about the space that objects in it occupy, and how each objects is supported stably by each other. In other words, we seek to understand which objects would, if moved, cause other objects to fall. This 3D volumetric reasoning is important for many scene understanding tasks, ranging from segmentation o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A New Look at Reweighted Message Passing

    Publication Year: 2015, Page(s):919 - 930
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (572 KB) | HTML iconHTML

    We propose a new family of message passing techniques for MAP estimation in graphical models which we call Sequential Reweighted Message Passing (SRMP). Special cases include well-known techniques such as Min-Sum Diffusion (MSD) and a faster Sequential Tree-Reweighted Message Passing (TRW-S). Importantly, our derivation is simpler than the original derivation of TRW-S, and does not involve a decom... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Boundary Preserving Dense Local Regions

    Publication Year: 2015, Page(s):931 - 943
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1862 KB) | HTML iconHTML

    We propose a dense local region detector to extract features suitable for image matching and object recognition tasks. Whereas traditional local interest operators rely on repeatable structures that often cross object boundaries (e.g., corners, scale-space blobs), our sampling strategy is driven by segmentation, and thus preserves object boundaries and shape. At the same time, whereas existing reg... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Context-Sensitive Dynamic Ordinal Regression for Intensity Estimation of Facial Action Units

    Publication Year: 2015, Page(s):944 - 958
    Cited by:  Papers (26)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1037 KB) | HTML iconHTML

    Modeling intensity of facial action units from spontaneously displayed facial expressions is challenging mainly because of high variability in subject-specific facial expressiveness, head-movements, illumination changes, etc. These factors make the target problem highly context-sensitive. However, existing methods usually ignore this context-sensitivity of the target problem. We propose a novel Co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Discriminatively Trained And-Or Graph Models for Object Shape Detection

    Publication Year: 2015, Page(s):959 - 972
    Cited by:  Papers (42)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1569 KB) | HTML iconHTML

    In this paper, we investigate a novel reconfigurable part-based model, namely And-Or graph model, to recognize object shapes in images. Our proposed model consists of four layers: leaf-nodes at the bottom are local classifiers for detecting contour fragments; or-nodes above the leaf-nodes function as the switches to activate their child leaf-nodes, making the model reconfigurable during inference;... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Discriminative Relational Topic Models

    Publication Year: 2015, Page(s):973 - 986
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1706 KB) | HTML iconHTML

    Relational topic models (RTMs) provide a probabilistic generative process to describe both the link structure and document contents for document networks, and they have shown promise on predicting network structures and discovering latent topic representations. However, existing RTMs have limitations in both the restricted model expressiveness and incapability of dealing with imbalanced network da... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimation of an Observation Satellite’s Attitude Using Multimodal Pushbroom Cameras

    Publication Year: 2015, Page(s):987 - 1000
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1234 KB) | HTML iconHTML

    Pushbroom cameras are widely used for earth observation applications. This sensor acquires 1D images over time and uses the straight motion of the satellite to sweep out a region of space and build a 2D image. The stability of the satellite is critical during the pushbroom acquisition process. Therefore its attitude is assumed to be constant overtime. However, the recent manufacture of smaller and... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generalized Sparselet Models for Real-Time Multiclass Object Recognition

    Publication Year: 2015, Page(s):1001 - 1012
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1034 KB) | HTML iconHTML

    The problem of real-time multiclass object recognition is of great practical importance in object recognition. In this paper, we describe a framework that simultaneously utilizes shared representation, reconstruction sparsity, and parallelism to enable real-time multiclass object detection with deformable part models at 5Hz on a laptop computer with almost no decrease in task performance. Our fram... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning Near-Optimal Cost-Sensitive Decision Policy for Object Detection

    Publication Year: 2015, Page(s):1013 - 1027
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (999 KB) | HTML iconHTML

    Many popular object detectors, such as AdaBoost, SVM and deformable part-based models (DPM), compute additive scoring functions at a large number of windows in an image pyramid, thus computational efficiency is an important consideration in real time applications besides accuracy. In this paper, a decision policy refers to a sequence of two-sided thresholds to execute early reject and early accept... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Retrieving Similar Styles to Parse Clothing

    Publication Year: 2015, Page(s):1028 - 1040
    Cited by:  Papers (21)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1753 KB) | HTML iconHTML

    Clothing recognition is a societally and commercially important yet extremely challenging problem due to large variations in clothing appearance, layering, style, and body shape and pose. In this paper, we tackle the clothing parsing problem using a retrieval-based approach. For a query image, we find similar styles from a large database of tagged fashion images and use these examples to recognize... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semi-Supervised Affinity Propagation with Soft Instance-Level Constraints

    Publication Year: 2015, Page(s):1041 - 1052
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (836 KB) | HTML iconHTML

    Soft-constraint semi-supervised affinity propagation (SCSSAP) adds supervision to the affinity propagation (AP) clustering algorithm without strictly enforcing instance-level constraints. Constraint violations lead to an adjustment of the AP similarity matrix at every iteration of the proposed algorithm and to addition of a penalty to the objective function. This formulation is particularly advant... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shape Tracking with Occlusions via Coarse-to-Fine Region-Based Sobolev Descent

    Publication Year: 2015, Page(s):1053 - 1066
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1546 KB) | HTML iconHTML Multimedia Media

    We present a method to track the shape of an object from video. The method uses a joint shape and appearance model of the object, which is propagated to match shape and radiance in subsequent frames, determining object shape. Self-occlusions and dis-occlusions of the object from camera and object motion pose difficulties to joint shape and appearance models in tracking. They are unable to adapt to... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sparse and Dense Hybrid Representation via Dictionary Decomposition for Face Recognition

    Publication Year: 2015, Page(s):1067 - 1079
    Cited by:  Papers (46)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1355 KB) | HTML iconHTML

    Sparse representation provides an effective tool for classification under the conditions that every class has sufficient representative training samples and the training data are uncorrupted. These conditions may not hold true in many practical applications. Face identification is an example where we have a large number of identities but sufficient representative and uncorrupted training images ca... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Statistical Optimality in Multipartite Ranking and Ordinal Regression

    Publication Year: 2015, Page(s):1080 - 1094
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (822 KB) | HTML iconHTML

    Statistical optimality in multipartite ranking is investigated as an extension of bipartite ranking. We consider the optimality of ranking algorithms through minimization of the theoretical risk which combines pairwise ranking errors of ordinal categories with differential ranking costs. The extension shows that for a certain class of convex loss functions including exponential loss, the optimal r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Viewpoint Invariant Human Re-Identification in Camera Networks Using Pose Priors and Subject-Discriminative Features

    Publication Year: 2015, Page(s):1095 - 1108
    Cited by:  Papers (33)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1550 KB) | HTML iconHTML

    Human re-identification across cameras with non-overlapping fields of view is one of the most important and difficult problems in video surveillance and analysis. However, current algorithms are likely to fail in real-world scenarios for several reasons. For example, surveillance cameras are typically mounted high above the ground plane, causing serious perspective changes. Also, most algorithms a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Why Does Rebalancing Class-Unbalanced Data Improve AUC for Linear Discriminant Analysis?

    Publication Year: 2015, Page(s):1109 - 1112
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (218 KB) | HTML iconHTML

    Many established classifiers fail to identify the minority class when it is much smaller than the majority class. To tackle this problem, researchers often first rebalance the class sizes in the training dataset, through oversampling the minority class or undersampling the majority class, and then use the rebalanced data to train the classifiers. This leads to interesting empirical patterns. In pa... View full abstract»

    Open Access
  • 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 (318 KB)
    Freely Available from IEEE
  • IEEE Computer Society

    Publication Year: 2015, Page(s): C4
    Request permission for commercial reuse | PDF file iconPDF (309 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