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 2 • Feb. 2016

Filter Results

Displaying Results 1 - 20 of 20
  • Table of contents

    Publication Year: 2016, Page(s): C1
    Request permission for commercial reuse | PDF file iconPDF (327 KB)
    Freely Available from IEEE
  • IEEE Transactions on Pattern Analysis and Machine Intelligence Editorial Board

    Publication Year: 2016, Page(s): C2
    Request permission for commercial reuse | PDF file iconPDF (327 KB)
    Freely Available from IEEE
  • State of the Journal

    Publication Year: 2016, Page(s):209 - 210
    Request permission for commercial reuse | PDF file iconPDF (39 KB) | HTML iconHTML
    Freely Available from IEEE
  • A Fast and Accurate Unconstrained Face Detector

    Publication Year: 2016, Page(s):211 - 223
    Cited by:  Papers (21)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2007 KB) | HTML iconHTML Multimedia Media

    We propose a method to address challenges in unconstrained face detection, such as arbitrary pose variations and occlusions. First, a new image feature called Normalized Pixel Difference (NPD) is proposed. NPD feature is computed as the difference to sum ratio between two pixel values, inspired by the Weber Fraction in experimental psychology. The new feature is scale invariant, bounded, and is ab... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Generalized Probabilistic Framework for Compact Codebook Creation

    Publication Year: 2016, Page(s):224 - 237
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (845 KB) | HTML iconHTML Multimedia Media

    Compact and discriminative visual codebooks are preferred in many visual recognition tasks. In the literature, a number of works have taken the approach of hierarchically merging visual words of an initial large-sized codebook, but implemented this approach with different merging criteria. In this work, we propose a single probabilistic framework to unify these merging criteria, by identifying two... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Stochastic Approach to Diffeomorphic Point Set Registration with Landmark Constraints

    Publication Year: 2016, Page(s):238 - 251
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2809 KB) | HTML iconHTML

    This work presents a deformable point set registration algorithm that seeks an optimal set of radial basis functions to describe the registration. A novel, global optimization approach is introduced composed of simulated annealing with a particle filter based generator function to perform the registration. It is shown how constraints can be incorporated into this framework. A constraint on the def... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast Direct Methods for Gaussian Processes

    Publication Year: 2016, Page(s):252 - 265
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1306 KB) | HTML iconHTML

    A number of problems in probability and statistics can be addressed using the multivariate normal (Gaussian) distribution. In the one-dimensional case, computing the probability for a given mean and variance simply requires the evaluation of the corresponding Gaussian density. In the n-dimensional setting, however, it requires the inversion of an n x n covariance matrix, C, as well as the evaluati... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Flexible Clustered Multi-Task Learning by Learning Representative Tasks

    Publication Year: 2016, Page(s):266 - 278
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (613 KB) | HTML iconHTML

    Multi-task learning (MTL) methods have shown promising performance by learning multiple relevant tasks simultaneously, which exploits to share useful information across relevant tasks. Among various MTL methods, clustered multi-task learning (CMTL) assumes that all tasks can be clustered into groups and attempts to learn the underlying cluster structure from the training data. In this paper, we pr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generalized Canonical Time Warping

    Publication Year: 2016, Page(s):279 - 294
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3025 KB) | HTML iconHTML

    Temporal alignment of human motion has been of recent interest due to its applications in animation, tele-rehabilitation and activity recognition. This paper presents generalized canonical time warping (GCTW), an extension of dynamic time warping (DTW) and canonical correlation analysis (CCA) for temporally aligning multi-modal sequences from multiple subjects performing similar activities. GCTW e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image Super-Resolution Using Deep Convolutional Networks

    Publication Year: 2016, Page(s):295 - 307
    Cited by:  Papers (82)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2121 KB) | HTML iconHTML Multimedia Media

    We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also be vie... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Isotonic Modeling with Non-Differentiable Loss Functions with Application to Lasso Regularization

    Publication Year: 2016, Page(s):308 - 321
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (746 KB) | HTML iconHTML

    In this paper we present an algorithmic approach for fitting isotonic models under convex, yet non-differentiable, loss functions. It is a generalization of the greedy non-regret approach proposed by Luss and Rosset (2014) for differentiable loss functions, taking into account the sub-gradiental extensions required. We prove that our suggested algorithm solves the isotonic modeling problem while m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mixture of Switching Linear Dynamics to Discover Behavior Patterns in Object Tracks

    Publication Year: 2016, Page(s):322 - 334
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3084 KB) | HTML iconHTML

    We present a novel non-parametric Bayesian model to jointly discover the dynamics of low-level actions and high-level behaviors of tracked objects. In our approach, actions capture both linear, low-level object dynamics, and an additional spatial distribution on where the dynamic occurs. Furthermore, behavior classes capture high-level temporal motion dependencies in Markov chains of actions, thus... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • NUS-PRO: A New Visual Tracking Challenge

    Publication Year: 2016, Page(s):335 - 349
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4216 KB) | HTML iconHTML

    Numerous approaches on object tracking have been proposed during the past decade with demonstrated success. However, most tracking algorithms are evaluated on limited video sequences and annotations. For thorough performance evaluation, we propose a large-scale database which contains 365 challenging image sequences of pedestrians and rigid objects. The database covers 12 kinds of objects, and mos... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust Model Fitting Using Higher Than Minimal Subset Sampling

    Publication Year: 2016, Page(s):350 - 362
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1966 KB) | HTML iconHTML

    Identifying the underlying model in a set of data contaminated by noise and outliers is a fundamental task in computer vision. The cost function associated with such tasks is often highly complex, hence in most cases only an approximate solution is obtained by evaluating the cost function on discrete locations in the parameter (hypothesis) space. To be successful at least one hypothesis has to be ... View full abstract»

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

    Publication Year: 2016, Page(s):363 - 375
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1731 KB) | HTML iconHTML

    Discriminative methods (e.g., kernel regression, SVM) have been extensively used to solve problems such as object recognition, image alignment and pose estimation from images. These methods typically map image features (X) to continuous (e.g., pose) or discrete (e.g., object category) values. A major drawback of existing discriminative methods is that samples are directly projected onto a subspace... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shape and Reflectance Estimation in the Wild

    Publication Year: 2016, Page(s):376 - 389
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1940 KB) | HTML iconHTML

    Our world is full of objects with complex reflectances situated in rich illumination environments. Though stunning, the diversity of appearance that arises from this complexity is also daunting. For this reason, past work on geometry recovery has tried to frame the problem into simplistic models of reflectance (such as Lambertian, mirrored, or dichromatic) or illumination (one or more distant poin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture Illumination Separation for Single-Shot Structured Light Reconstruction

    Publication Year: 2016, Page(s):390 - 404
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3696 KB) | HTML iconHTML

    Active illumination based methods have a trade-off between acquisition time and resolution of the estimated 3D shapes. Multi-shot approaches can generate dense reconstructions but require stationary scenes. Single-shot methods are applicable to dynamic objects but can only estimate sparse reconstructions and are sensitive to surface texture. We present a single-shot approach to produce dense shape... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Weakly Supervised Large Scale Object Localization with Multiple Instance Learning and Bag Splitting

    Publication Year: 2016, Page(s):405 - 416
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1216 KB) | HTML iconHTML

    Localizing objects of interest in images when provided with only image-level labels is a challenging visual recognition task. Previous efforts have required carefully designed features and have difficulty in handling images with cluttered backgrounds. Up-scaling to large datasets also poses a challenge to applying these methods to real applications. In this paper, we propose an efficient and effec... 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: 2016, Page(s): C3
    Request permission for commercial reuse | PDF file iconPDF (327 KB)
    Freely Available from IEEE
  • IEEE Computer Society

    Publication Year: 2016, Page(s): C4
    Request permission for commercial reuse | PDF file iconPDF (327 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