By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 3 • Date March 2012

Filter Results

Displaying Results 1 - 22 of 22
  • [Front cover]

    Publication Year: 2012, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (178 KB)
    Freely Available from IEEE
  • [Cover 2]

    Publication Year: 2012, Page(s): c2
    Request permission for commercial reuse | PDF file iconPDF (201 KB)
    Freely Available from IEEE
  • Prototype Selection for Nearest Neighbor Classification: Taxonomy and Empirical Study

    Publication Year: 2012, Page(s):417 - 435
    Cited by:  Papers (128)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4726 KB) | HTML iconHTML

    The nearest neighbor classifier is one of the most used and well-known techniques for performing recognition tasks. It has also demonstrated itself to be one of the most useful algorithms in data mining in spite of its simplicity. However, the nearest neighbor classifier suffers from several drawbacks such as high storage requirements, low efficiency in classification response, and low noise toler... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Slow Feature Analysis for Human Action Recognition

    Publication Year: 2012, Page(s):436 - 450
    Cited by:  Papers (104)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5494 KB) | HTML iconHTML

    Slow Feature Analysis (SFA) extracts slowly varying features from a quickly varying input signal [1]. It has been successfully applied to modeling the visual receptive fields of the cortical neurons. Sufficient experimental results in neuroscience suggest that the temporal slowness principle is a general learning principle in visual perception. In this paper, we introduce the SFA framework to the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Altered Fingerprints: Analysis and Detection

    Publication Year: 2012, Page(s):451 - 464
    Cited by:  Papers (33)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5616 KB) | HTML iconHTML

    The widespread deployment of Automated Fingerprint Identification Systems (AFIS) in law enforcement and border control applications has heightened the need for ensuring that these systems are not compromised. While several issues related to fingerprint system security have been investigated, including the use of fake fingerprints for masquerading identity, the problem of fingerprint alteration or ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Domain Transfer Multiple Kernel Learning

    Publication Year: 2012, Page(s):465 - 479
    Cited by:  Papers (92)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1431 KB) | HTML iconHTML

    Cross-domain learning methods have shown promising results by leveraging labeled patterns from the auxiliary domain to learn a robust classifier for the target domain which has only a limited number of labeled samples. To cope with the considerable change between feature distributions of different domains, we propose a new cross-domain kernel learning framework into which many existing kernel meth... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient Additive Kernels via Explicit Feature Maps

    Publication Year: 2012, Page(s):480 - 492
    Cited by:  Papers (181)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1410 KB) | HTML iconHTML

    Large scale nonlinear support vector machines (SVMs) can be approximated by linear ones using a suitable feature map. The linear SVMs are in general much faster to learn and evaluate (test) than the original nonlinear SVMs. This work introduces explicit feature maps for the additive class of kernels, such as the intersection, Hellinger's, and χ2 kernels, commonly used in computer... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast Joint Estimation of Silhouettes and Dense 3D Geometry from Multiple Images

    Publication Year: 2012, Page(s):493 - 505
    Cited by:  Papers (25)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1346 KB) | HTML iconHTML

    We propose a probabilistic formulation of joint silhouette extraction and 3D reconstruction given a series of calibrated 2D images. Instead of segmenting each image separately in order to construct a 3D surface consistent with the estimated silhouettes, we compute the most probable 3D shape that gives rise to the observed color information. The probabilistic framework, based on Bayesian inference,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • IrisCode Decompression Based on the Dependence between Its Bit Pairs

    Publication Year: 2012, Page(s):506 - 520
    Cited by:  Papers (5)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1903 KB) | HTML iconHTML Multimedia Media

    IrisCode is an iris recognition algorithm developed in 1993 and continuously improved by Daugman. Understanding IrisCode's properties is extremely important because over 60 million people have been mathematically enrolled by the algorithm. In this paper, IrisCode is proved to be a compression algorithm, which is to say its templates are compressed iris images. In our experiments, the compression r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Maximum Margin Bayesian Network Classifiers

    Publication Year: 2012, Page(s):521 - 532
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1191 KB) | HTML iconHTML Multimedia Media

    We present a maximum margin parameter learning algorithm for Bayesian network classifiers using a conjugate gradient (CG) method for optimization. In contrast to previous approaches, we maintain the normalization constraints on the parameters of the Bayesian network during optimization, i.e., the probabilistic interpretation of the model is not lost. This enables us to handle missing features in d... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognizing Human Actions by Learning and Matching Shape-Motion Prototype Trees

    Publication Year: 2012, Page(s):533 - 547
    Cited by:  Papers (41)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2645 KB) | HTML iconHTML

    A shape-motion prototype-based approach is introduced for action recognition. The approach represents an action as a sequence of prototypes for efficient and flexible action matching in long video sequences. During training, an action prototype tree is learned in a joint shape and motion space via hierarchical K-means clustering and each training sequence is represented as a labeled prototype sequ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust Active Stereo Vision Using Kullback-Leibler Divergence

    Publication Year: 2012, Page(s):548 - 563
    Cited by:  Papers (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2152 KB) | HTML iconHTML

    Active stereo vision is a method of 3D surface scanning involving the projecting and capturing of a series of light patterns where depth is derived from correspondences between the observed and projected patterns. In contrast, passive stereo vision reveals depth through correspondences between textured images from two or more cameras. By employing a projector, active stereo vision systems find cor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sampling for Shape from Focus in Optical Microscopy

    Publication Year: 2012, Page(s):564 - 573
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1821 KB) | HTML iconHTML

    Shape from focus (SFF), which relies on image focus as a cue within sequenced images, represents a passive technique in recovering object shapes in scenes. Although numerous methods have been recently proposed, less attention has been paid to particular factors affecting them. In regard to SFF, one such critical factor impacting system application is the total number of images. A large data set re... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture Classification from Random Features

    Publication Year: 2012, Page(s):574 - 586
    Cited by:  Papers (69)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2905 KB) | HTML iconHTML

    Inspired by theories of sparse representation and compressed sensing, this paper presents a simple, novel, yet very powerful approach for texture classification based on random projection, suitable for large texture database applications. At the feature extraction stage, a small set of random features is extracted from local image patches. The random features are embedded into a bag--of-words mode... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tracking Mobile Users in Wireless Networks via Semi-Supervised Colocalization

    Publication Year: 2012, Page(s):587 - 600
    Cited by:  Papers (32)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1872 KB) | HTML iconHTML

    Recent years have witnessed the growing popularity of sensor and sensor-network technologies, supporting important practical applications. One of the fundamental issues is how to accurately locate a user with few labeled data in a wireless sensor network, where a major difficulty arises from the need to label large quantities of user location data, which in turn requires knowledge about the locati... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Weakly Supervised Learning of Interactions between Humans and Objects

    Publication Year: 2012, Page(s):601 - 614
    Cited by:  Papers (51)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3265 KB) | HTML iconHTML

    We introduce a weakly supervised approach for learning human actions modeled as interactions between humans and objects. Our approach is human-centric: We first localize a human in the image and then determine the object relevant for the action and its spatial relation with the human. The model is learned automatically from a set of still images annotated only with the action label. Our approach r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Action Similarity Labeling Challenge

    Publication Year: 2012, Page(s):615 - 621
    Cited by:  Papers (33)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1314 KB) | HTML iconHTML Multimedia Media

    Recognizing actions in videos is rapidly becoming a topic of much research. To facilitate the development of methods for action recognition, several video collections, along with benchmark protocols, have previously been proposed. In this paper, we present a novel video database, the “Action Similarity LAbeliNg” (ASLAN) database, along with benchmark protocols. The ASLAN set includes... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • TPAMI Seeks Applications for EIC for 2013-2014 Term

    Publication Year: 2012, Page(s): 622
    Request permission for commercial reuse | PDF file iconPDF (90 KB)
    Freely Available from IEEE
  • IEEE Computer Society OnlinePlus Video Tutorial

    Publication Year: 2012, Page(s): 623
    Request permission for commercial reuse | PDF file iconPDF (769 KB)
    Freely Available from IEEE
  • What's new in Transactions [advertisement]

    Publication Year: 2012, Page(s): 624
    Request permission for commercial reuse | PDF file iconPDF (764 KB)
    Freely Available from IEEE
  • [Cover3]

    Publication Year: 2012, Page(s): c3
    Request permission for commercial reuse | PDF file iconPDF (201 KB)
    Freely Available from IEEE
  • [Cover 4]

    Publication Year: 2012, Page(s): c4
    Request permission for commercial reuse | PDF file iconPDF (178 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