IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 9 • Sept. 2017

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.

Filter Results

Displaying Results 1 - 19 of 19
  • Table of Contents

    Publication Year: 2017, Page(s): C1
    Request permission for commercial reuse | PDF file iconPDF (275 KB)
    Freely Available from IEEE
  • Cover

    Publication Year: 2017, Page(s): C2
    Request permission for commercial reuse | PDF file iconPDF (297 KB)
    Freely Available from IEEE
  • Clustering with Hypergraphs: The Case for Large Hyperedges

    Publication Year: 2017, Page(s):1697 - 1711
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2202 KB) | HTML iconHTML

    The extension of conventional clustering to hypergraph clustering, which involves higher order similarities instead of pairwise similarities, is increasingly gaining attention in computer vision. This is due to the fact that many clustering problems require an affinity measure that must involve a subset of data of size more than two. In the context of hypergraph clustering, the calculation of such... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • DASC: Robust Dense Descriptor for Multi-Modal and Multi-Spectral Correspondence Estimation

    Publication Year: 2017, Page(s):1712 - 1729
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3520 KB) | HTML iconHTML Multimedia Media

    Establishing dense correspondences between multiple images is a fundamental task in many applications. However, finding a reliable correspondence between multi-modal or multi-spectral images still remains unsolved due to their challenging photometric and geometric variations. In this paper, we propose a novel dense descriptor, called dense adaptive self-correlation (DASC), to estimate dense multi-... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dense Semantic 3D Reconstruction

    Publication Year: 2017, Page(s):1730 - 1743
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1435 KB) | HTML iconHTML

    Both image segmentation and dense 3D modeling from images represent an intrinsically ill-posed problem. Strong regularizers are therefore required to constrain the solutions from being `too noisy'. These priors generally yield overly smooth reconstructions and/or segmentations in certain regions while they fail to constrain the solution sufficiently in other areas. In this paper, we argue that ima... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient & Effective Prioritized Matching for Large-Scale Image-Based Localization

    Publication Year: 2017, Page(s):1744 - 1756
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (874 KB) | HTML iconHTML

    Accurately determining the position and orientation from which an image was taken, i.e., computing the camera pose, is a fundamental step in many Computer Vision applications. The pose can be recovered from 2D-3D matches between 2D image positions and points in a 3D model of the scene. Recent advances in Structure-from-Motion allow us to reconstruct large scenes and thus create the need for image-... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extracting 3D Parametric Curves from 2D Images of Helical Objects

    Publication Year: 2017, Page(s):1757 - 1769
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1879 KB) | HTML iconHTML

    Helical objects occur in medicine, biology, cosmetics, nanotechnology, and engineering. Extracting a 3D parametric curve from a 2D image of a helical object has many practical applications, in particular being able to extract metrics such as tortuosity, frequency, and pitch. We present a method that is able to straighten the image object and derive a robust 3D helical curve from peaks in the objec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hierarchical Context Modeling for Video Event Recognition

    Publication Year: 2017, Page(s):1770 - 1782
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1060 KB) | HTML iconHTML Multimedia Media

    Current video event recognition research remains largely target-centered. For real-world surveillance videos, target-centered event recognition faces great challenges due to large intra-class target variation, limited image resolution, and poor detection and tracking results. To mitigate these challenges, we introduced a context-augmented video event recognition approach. Specifically, we explicit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improving Large-Scale Image Retrieval Through Robust Aggregation of Local Descriptors

    Publication Year: 2017, Page(s):1783 - 1796
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2130 KB) | HTML iconHTML

    Visual search and image retrieval underpin numerous applications, however the task is still challenging predominantly due to the variability of object appearance and ever increasing size of the databases, often exceeding billions of images. Prior art methods rely on aggregation of local scale-invariant descriptors, such as SIFT, via mechanisms including Bag of Visual Words (BoW), Vector of Locally... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Interferences in Match Kernels

    Publication Year: 2017, Page(s):1797 - 1810
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1265 KB) | HTML iconHTML

    We consider the design of an image representation that embeds and aggregates a set of local descriptors into a single vector. Popular representations of this kind include the bag-of-visual-words, the Fisher vector and the VLAD. When two such image representations are compared with the dot-product, the image-to-image similarity can be interpreted as a match kernel. In match kernels, one has to deal... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learn on Source, Refine on Target: A Model Transfer Learning Framework with Random Forests

    Publication Year: 2017, Page(s):1811 - 1824
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (748 KB) | HTML iconHTML

    We propose novel model transfer-learning methods that refine a decision forest model M learned within a “source” domain using a training set sampled from a “target” domain, assumed to be a variation of the source. We present two random forest transfer algorithms. The first algorithm searches greedily for locally optimal modifications of each tree structure by trying to ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Linear Subspace Ranking Hashing for Cross-Modal Retrieval

    Publication Year: 2017, Page(s):1825 - 1838
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2041 KB) | HTML iconHTML

    Hashing has attracted a great deal of research in recent years due to its effectiveness for the retrieval and indexing of large-scale high-dimensional multimedia data. In this paper, we propose a novel ranking-based hashing framework that maps data from different modalities into a common Hamming space where the cross-modal similarity can be measured using Hamming distance. Unlike existing cross-mo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-Instance Classification by Max-Margin Training of Cardinality-Based Markov Networks

    Publication Year: 2017, Page(s):1839 - 1852
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1254 KB) | HTML iconHTML

    We propose a probabilistic graphical framework for multi-instance learning (MIL) based on Markov networks. This framework can deal with different levels of labeling ambiguity (i.e., the portion of positive instances in a bag) in weakly supervised data by parameterizing cardinality potential functions. Consequently, it can be used to encode different cardinality-based multi-instance assumptions, ra... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimal Transport for Domain Adaptation

    Publication Year: 2017, Page(s):1853 - 1865
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (642 KB) | HTML iconHTML Multimedia Media

    Domain adaptation is one of the most challenging tasks of modern data analytics. If the adaptation is done correctly, models built on a specific data representation become more robust when confronted to data depicting the same classes, but described by another observation system. Among the many strategies proposed, finding domain-invariant representations has shown excellent properties, in particu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • PatchMatch Filter: Edge-Aware Filtering Meets Randomized Search for Visual Correspondence

    Publication Year: 2017, Page(s):1866 - 1879
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1456 KB) | HTML iconHTML

    Though many tasks in computer vision can be formulated elegantly as pixel-labeling problems, a typical challenge discouraging such a discrete formulation is often due to computational efficiency. Recent studies on fast cost volume filtering based on efficient edge-aware filters provide a fast alternative to solve discrete labeling problems, with the complexity independent of the support window siz... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Photometric Stereo in a Scattering Medium

    Publication Year: 2017, Page(s):1880 - 1891
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2305 KB) | HTML iconHTML

    Photometric stereo is widely used for 3D reconstruction. However, its use in scattering media such as water, biological tissue and fog has been limited until now, because of forward scattered light from both the source and object, as well as light scattered back from the medium (backscatter). Here we make three contributions to address the key modes of light propagation, under the common single sc... View full abstract»

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

    Publication Year: 2017, Page(s):1892 - 1904
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1881 KB) | HTML iconHTML

    Most existing bottom-up algorithms measure the foreground saliency of a pixel or region based on its contrast within a local context or the entire image, whereas a few methods focus on segmenting out background regions and thereby salient objects. Instead of only considering the contrast between salient objects and their surrounding regions, we consider both foreground and background cues in this ... View full abstract»

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

    Publication Year: 2017, Page(s): C3
    Request permission for commercial reuse | PDF file iconPDF (297 KB)
    Freely Available from IEEE
  • Cover

    Publication Year: 2017, Page(s): C4
    Request permission for commercial reuse | PDF file iconPDF (275 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