By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 8 • Date Aug. 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 (357 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 (319 KB)
    Freely Available from IEEE
  • A Two-Stage Framework for 3D FaceReconstruction from RGBD Images

    Publication Year: 2014, Page(s):1493 - 1504
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1764 KB) | HTML iconHTML

    This paper proposes a new approach for 3D face reconstruction with RGBD images from an inexpensive commodity sensor. The challenges we face are: 1) substantial random noise and corruption are present in low-resolution depth maps; and 2) there is high degree of variability in pose and face expression. We develop a novel two-stage algorithm that effectively maps low-quality depth maps to realistic f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive Color Constancy Using Faces

    Publication Year: 2014, Page(s):1505 - 1518
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2576 KB) | HTML iconHTML

    In this work we design an adaptive color constancy algorithm that, exploiting the skin regions found in faces, is able to estimate and correct the scene illumination. The algorithm automatically switches from global to spatially varying color correction on the basis of the illuminant estimations on the different faces detected in the image. An extensive comparison with both global and local color ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Classification and Boosting with Multiple Collaborative Representations

    Publication Year: 2014, Page(s):1519 - 1531
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1879 KB) | HTML iconHTML

    Recent advances have shown a great potential to explore collaborative representations of test samples in a dictionary composed of training samples from all classes in multi-class recognition including sparse representations. In this paper, we present two multi-class classification algorithms that make use of multiple collaborative representations in their formulations, and demonstrate performance ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast Feature Pyramids for Object Detection

    Publication Year: 2014, Page(s):1532 - 1545
    Cited by:  Papers (114)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1388 KB) | HTML iconHTML

    Multi-resolution image features may be approximated via extrapolation from nearby scales, rather than being computed explicitly. This fundamental insight allows us to design object detection algorithms that are as accurate, and considerably faster, than the state-of-the-art. The computational bottleneck of many modern detectors is the computation of features at every scale of a finely-sampled imag... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image Geo-Localization Based on MultipleNearest Neighbor Feature Matching UsingGeneralized Graphs

    Publication Year: 2014, Page(s):1546 - 1558
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1790 KB) | HTML iconHTML

    In this paper, we present a new framework for geo-locating an image utilizing a novel multiple nearest neighbor feature matching method using Generalized Minimum Clique Graphs (GMCP). First, we extract local features (e.g., SIFT) from the query image and retrieve a number of nearest neighbors for each query feature from the reference data set. Next, we apply our GMCP-based feature matching to sele... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Large-Margin Multi-ViewInformation Bottleneck

    Publication Year: 2014, Page(s):1559 - 1572
    Cited by:  Papers (39)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1226 KB) | HTML iconHTML

    In this paper, we extend the theory of the information bottleneck (IB) to learning from examples represented by multi-view features. We formulate the problem as one of encoding a communication system with multiple senders, each of which represents one view of the data. Based on the precise components filtered out from multiple information sources through a “bottleneck”, a margin maxi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning Local Feature Descriptors Using Convex Optimisation

    Publication Year: 2014, Page(s):1573 - 1585
    Cited by:  Papers (25)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1749 KB) | HTML iconHTML

    The objective of this work is to learn descriptors suitable for the sparse feature detectors used in viewpoint invariant matching. We make a number of novel contributions towards this goal. First, it is shown that learning the pooling regions for the descriptor can be formulated as a convex optimisation problem selecting the regions using sparsity. Second, it is shown that descriptor dimensionalit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Measuring Crowd Collectiveness

    Publication Year: 2014, Page(s):1586 - 1599
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2339 KB) | HTML iconHTML

    Collective motions of crowds are common in nature and have attracted a great deal of attention in a variety of multidisciplinary fields. Collectiveness, which indicates the degree of individuals acting as a union, is a fundamental and universal measurement for various crowd systems. By quantifying the topological structures of collective manifolds of crowd, this paper proposes a descriptor of coll... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiclass Data Segmentation Using Diffuse Interface Methods on Graphs

    Publication Year: 2014, Page(s):1600 - 1613
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1114 KB) | HTML iconHTML

    We present two graph-based algorithms for multiclass segmentation of high-dimensional data on graphs. The algorithms use a diffuse interface model based on the Ginzburg-Landau functional, related to total variation and graph cuts. A multiclass extension is introduced using the Gibbs simplex, with the functional's double-well potential modified to handle the multiclass case. The first algorithm min... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-Commodity Network Flow for Tracking Multiple People

    Publication Year: 2014, Page(s):1614 - 1627
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1945 KB) | HTML iconHTML Multimedia Media

    In this paper, we show that tracking multiple people whose paths may intersect can be formulated as a multi-commodity network flow problem. Our proposed framework is designed to exploit image appearance cues to prevent identity switches. Our method is effective even when such cues are only available at distant time intervals. This is unlike many current approaches that depend on appearance being e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-Observation Blind Deconvolution with an Adaptive Sparse Prior

    Publication Year: 2014, Page(s):1628 - 1643
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1998 KB) | HTML iconHTML

    This paper describes a robust algorithm for estimating a single latent sharp image given multiple blurry and/or noisy observations. The underlying multi-image blind deconvolution problem is solved by linking all of the observations together via a Bayesian-inspired penalty function, which couples the unknown latent image along with a separate blur kernel and noise variance associated with each obse... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Prediction of Human Activity by Discovering Temporal Sequence Patterns

    Publication Year: 2014, Page(s):1644 - 1657
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2175 KB) | HTML iconHTML

    Early prediction of ongoing human activity has become more valuable in a large variety of time-critical applications. To build an effective representation for prediction, human activities can be characterized by a complex temporal composition of constituent simple actions and interacting objects. Different from early detection on short-duration simple actions, we propose a novel framework for long... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Random Cluster Model for Robust Geometric Fitting

    Publication Year: 2014, Page(s):1658 - 1671
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3293 KB) | HTML iconHTML Multimedia Media

    Random hypothesis generation is central to robust geometric model fitting in computer vision. The predominant technique is to randomly sample minimal subsets of the data, and hypothesize the geometric models from the selected subsets. While taking minimal subsets increases the chance of successively “hitting” inliers in a sample, hypotheses fitted on minimal subsets may be severely b... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic and Accurate Shadow Detection Using Near-Infrared Information

    Publication Year: 2014, Page(s):1672 - 1678
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1578 KB) | HTML iconHTML

    We present a method to automatically detect shadows in a fast and accurate manner by taking advantage of the inherent sensitivity of digital camera sensors to the near-infrared (NIR) part of the spectrum. Dark objects, which confound many shadow detection algorithms, often have much higher reflectance in the NIR. We can thus build an accurate shadow candidate map based on image pixels that are dar... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Perceptual Annotation: Measuring Human Vision to Improve Computer Vision

    Publication Year: 2014, Page(s):1679 - 1686
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (987 KB) | HTML iconHTML

    For many problems in computer vision, human learners are considerably better than machines. Humans possess highly accurate internal recognition and learning mechanisms that are not yet understood, and they frequently have access to more extensive training data through a lifetime of unbiased experience with the visual world. We propose to use visual psychophysics to directly leverage the abilities ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation of 3D Meshes Usingp-Spectral Clustering

    Publication Year: 2014, Page(s):1687 - 1693
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (746 KB) | HTML iconHTML

    In this paper, we propose a new approach to get the optimal segmentation of a 3D mesh as a human can perceive using the minima rule and spectral clustering. This method is fully unsupervised and provides a hierarchical segmentation via recursive cuts. We introduce a new concept of the adjacency matrix based on cognitive studies. We also introduce the use of one-spectral clustering which leads to t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stacked Sequential Scale-SpaceTaylor Context

    Publication Year: 2014, Page(s):1694 - 1700
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1114 KB) | HTML iconHTML

    We analyze sequential image labeling methods that sample the posterior label field in order to gather contextual information. We propose an effective method that extracts local Taylor coefficients from the posterior at different scales. Results show that our proposal outperforms state-of-the-art methods on MSRC-21, CAMVID, eTRIMS8 and KAIST2 data sets. 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 (319 KB)
    Freely Available from IEEE
  • IEEE Computer Society

    Publication Year: 2014, Page(s): C4
    Request permission for commercial reuse | PDF file iconPDF (357 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