IEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELIGENCE / Volume 33 Issue 1

http://ieeexplore.ieee.org/xpl/tocresult.jsp?isnumber=5639101

IEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELIGENCE 

2011 

Volume 33 Issue 1

Cover1

Page(s): c1 - c1
Digital Object Identifier : 10.1109/TPAMI.2011.3
Full Text: PDF (239KB)

Cover2

Page(s): c2 - c2
Digital Object Identifier : 10.1109/TPAMI.2011.4
Full Text: PDF (221KB)

State of the Journal

Zabih, Ramin  Matas, Jiri  Ghahramani, Zoubin 
Page(s): 1 - 2
Digital Object Identifier : 10.1109/TPAMI.2011.7

AbstractPlus | Full Text: PDF (56KB)

Decomposition of Complex Line Drawings with Hidden Lines for 3D Planar-Faced Manifold Object Reconstruction

Liu, Jianzhuang  Chen, Yu  Tang, Xiaoou 
Page(s): 3 - 15
Digital Object Identifier : 10.1109/TPAMI.2010.49

AbstractPlus | Full Text: PDF (3272KB)

Three-dimensional object reconstruction from a single 2D line drawing is an important problem in computer vision. Many methods have been presented to solve this problem, but they usually fail when the geometric structure of a 3D object becomes complex. In this paper, a novel approach based on a divide-and-conquer strategy is proposed to handle the 3D reconstruction of a planar-faced complex manifold object from its 2D line drawing with hidden lines visible. The approach consists of four steps: 1... Read More »

Turbo Segmentation of Textured Images

Lehmann, Frederic 
Page(s): 16 - 29
Digital Object Identifier : 10.1109/TPAMI.2010.58

AbstractPlus | Full Text: PDF (4218KB)

We consider the problem of semi-supervised segmentation of textured images. Existing model-based approaches model the intensity field of textured images as a Gauss-Markov random field to take into account the local spatial dependencies between the pixels. Classical Bayesian segmentation consists of also modeling the label field as a Markov random field to ensure that neighboring pixels correspond to the same texture class with high probability. Well-known relaxation techniques are available whic... Read More »

Bilayer Segmentation of Webcam Videos Using Tree-Based Classifiers

Yin, Pei  Criminisi, Antonio  Winn, John  Essa, Irfan A. 
Page(s): 30 - 42
Digital Object Identifier : 10.1109/TPAMI.2010.65

AbstractPlus | Full Text: PDF (3254KB)

This paper presents an automatic segmentation algorithm for video frames captured by a (monocular) webcam that closely approximates depth segmentation from a stereo camera. The frames are segmented into foreground and background layers that comprise a subject (participant) and other objects and individuals. The algorithm produces correct segmentations even in the presence of large background motion with a nearly stationary foreground. This research makes three key contributions: First, we introd... Read More »

Discriminative Learning of Local Image Descriptors

Brown, Matthew  Hua, Gang  Winder, Simon 
Page(s): 43 - 57
Digital Object Identifier : 10.1109/TPAMI.2010.54

AbstractPlus | Full Text: PDF (5468KB)

In this paper, we explore methods for learning local image descriptors from training data. We describe a set of building blocks for constructing descriptors which can be combined together and jointly optimized so as to minimize the error of a nearest-neighbor classifier. We consider both linear and nonlinear transforms with dimensionality reduction, and make use of discriminant learning techniques such as Linear Discriminant Analysis (LDA) and Powell minimization to solve for the parameters. Usi... Read More »

Flexible Depth of Field Photography

Kuthirummal, Sujit  Nagahara, Hajime  Zhou, Changyin  Nayar, Shree K. 
Page(s): 58 - 71
Digital Object Identifier : 10.1109/TPAMI.2010.66

AbstractPlus | Full Text: PDF (4735KB)

The range of scene depths that appear focused in an image is known as the depth of field (DOF). Conventional cameras are limited by a fundamental trade-off between depth of field and signal-to-noise ratio (SNR). For a dark scene, the aperture of the lens must be opened up to maintain SNR, which causes the DOF to reduce. Also, today's cameras have DOFs that correspond to a single slab that is perpendicular to the optical axis. In this paper, we present an imaging system that enables one to contro... Read More »

Global Ridge Orientation Modeling for Partial Fingerprint Identification

Wang, Yi  Hu, Jiankun 
Page(s): 72 - 87
Digital Object Identifier : 10.1109/TPAMI.2010.73

AbstractPlus | Full Text: PDF (5735KB)

Identifying incomplete or partial fingerprints from a large fingerprint database remains a difficult challenge today. Existing studies on partial fingerprints focus on one-to-one matching using local ridge details. In this paper, we investigate the problem of retrieving candidate lists for matching partial fingerprints by exploiting global topological features. Specifically, we propose an analytical approach for reconstructing the global topology representation from a partial fingerprint. First,... Read More »

Latent Fingerprint Matching

Jain, Anil K.  Feng, Jianjiang 
Page(s): 88 - 100
Digital Object Identifier : 10.1109/TPAMI.2010.59

AbstractPlus | Full Text: PDF (4119KB)

Multiperson Visual Focus of Attention from Head Pose and Meeting Contextual Cues

Ba, Sileye O.  Odobez, Jean-Marc 
Page(s): 101 - 116
Digital Object Identifier : 10.1109/TPAMI.2010.69

AbstractPlus | Full Text: PDF (3170KB)

This paper introduces a novel contextual model for the recognition of people's visual focus of attention (VFOA) in meetings from audio-visual perceptual cues. More specifically, instead of independently recognizing the VFOA of each meeting participant from his own head pose, we propose to jointly recognize the participants' visual attention in order to introduce context-dependent interaction models that relate to group activity and the social dynamics of communication. Meeting contextual informa... Read More »

Product Quantization for Nearest Neighbor Search

Jegou, Herve  Douze, Matthijs  Schmid, Cordelia 
Page(s): 117 - 128
Digital Object Identifier : 10.1109/TPAMI.2010.57

AbstractPlus | Full Text: PDF (1904KB)

This paper introduces a product quantization-based approach for approximate nearest neighbor search. The idea is to decompose the space into a Cartesian product of low-dimensional subspaces and to quantize each subspace separately. A vector is represented by a short code composed of its subspace quantization indices. The euclidean distance between two vectors can be efficiently estimated from their codes. An asymmetric version increases precision, as it computes the approximate distance between ... Read More »

Semi-Supervised Learning via Regularized Boosting Working on Multiple Semi-Supervised Assumptions

Chen, Ke  Wang, Shihai 
Page(s): 129 - 143
Digital Object Identifier : 10.1109/TPAMI.2010.92

AbstractPlus | Full Text: PDF (3226KB)

Semi-supervised learning concerns the problem of learning in the presence of labeled and unlabeled data. Several boosting algorithms have been extended to semi-supervised learning with various strategies. To our knowledge, however, none of them takes all three semi-supervised assumptions, i.e., smoothness, cluster, and manifold assumptions, together into account during boosting learning. In this paper, we propose a novel cost functional consisting of the margin cost on labeled data and the regul... Read More »

Tracking with Occlusions via Graph Cuts

Papadakis, Nicolas  Bugeau, Aurelie 
Page(s): 144 - 157
Digital Object Identifier : 10.1109/TPAMI.2010.56

AbstractPlus | Full Text: PDF (3510KB)

This work presents a new method for tracking and segmenting along time-interacting objects within an image sequence. One major contribution of the paper is the formalization of the notion of visible and occluded parts. For each object, we aim at tracking these two parts. Assuming that the velocity of each object is driven by a dynamical law, predictions can be used to guide the successive estimations. Separating these predicted areas into good and bad parts with respect to the final segmentation... Read More »

Video Registration Using Dynamic Textures

Ravichandran, Avinash  Vidal, Rene 
Page(s): 158 - 171
Digital Object Identifier : 10.1109/TPAMI.2010.61

AbstractPlus | Full Text: PDF (3253KB)

We consider the problem of spatially and temporally registering multiple video sequences of dynamical scenes which contain, but are not limited to, nonrigid objects such as fireworks, flags fluttering in the wind, etc., taken from different vantage points. This problem is extremely challenging due to the presence of complex variations in the appearance of such dynamic scenes. In this paper, we propose a simple algorithm for matching such complex scenes. Our algorithm does not require the cameras... Read More »

View-Independent Action Recognition from Temporal Self-Similarities

Junejo, Imran N.  Dexter, Emilie  Laptev, Ivan  Perez, Patrick 
Page(s): 172 - 185
Digital Object Identifier : 10.1109/TPAMI.2010.68

AbstractPlus | Full Text: PDF (3810KB)

This paper addresses recognition of human actions under view changes. We explore self-similarities of action sequences over time and observe the striking stability of such measures across views. Building upon this key observation, we develop an action descriptor that captures the structure of temporal similarities and dissimilarities within an action sequence. Despite this temporal self-similarity descriptor not being strictly view-invariant, we provide intuition and experimental validation demo... Read More »

A Fast Bilinear Structure from Motion Algorithm Using a Video Sequence and Inertial Sensors

Ramachandran, Mahesh  Veeraraghavan, Ashok  Chellappa, Rama 
Page(s): 186 - 193
Digital Object Identifier : 10.1109/TPAMI.2010.163

AbstractPlus | Full Text: PDF (1601KB)

In this paper, we study the benefits of the availability of a specific form of additional information—the vertical direction (gravity) and the height of the camera, both of which can be conveniently measured using inertial sensors and a monocular video sequence for 3D urban modeling. We show that in the presence of this information, the SfM equations can be rewritten in a bilinear form. This allows us to derive a fast, robust, and scalable SfM algorithm for large scale applications. The ... Read More »

Canonical Correlation Analysis for Multilabel Classification: A Least-Squares Formulation, Extensions, and Analysis

Sun, Liang  Ji, Shuiwang  Ye, Jieping 
Page(s): 194 - 200
Digital Object Identifier : 10.1109/TPAMI.2010.160

AbstractPlus | Full Text: PDF (509KB)

Canonical Correlation Analysis (CCA) is a well-known technique for finding the correlations between two sets of multidimensional variables. It projects both sets of variables onto a lower-dimensional space in which they are maximally correlated. CCA is commonly applied for supervised dimensionality reduction in which the two sets of variables are derived from the data and the class labels, respectively. It is well-known that CCA can be formulated as a least-squares problem in the binary class ca... Read More »

Connectedness of Random Walk Segmentation

Cheng, Ming-Ming  Zhang, Guo-Xin 
Page(s): 200 - 202
Digital Object Identifier : 10.1109/TPAMI.2010.138

AbstractPlus | Full Text: PDF (244KB)

Connectedness of random walk segmentation is examined, and novel properties are discovered, by considering electrical circuits equivalent to random walks. A theoretical analysis shows that earlier conclusions concerning connectedness of random walk segmentation results are incorrect, and counterexamples are demonstrated. Read More »

2010 Reviewers List

Page(s): 203 - 208
Digital Object Identifier : 10.1109/TPAMI.2011.2

AbstractPlus | Full Text: PDF (77KB)

 

2010 Annual Index

Page(s): Not in Print - Not in Print
Digital Object Identifier : 10.1109/TPAMI.2011.1

AbstractPlus | Full Text: PDF (733KB)

Cover3

Page(s): c3 - c3
Digital Object Identifier : 10.1109/TPAMI.2011.5
Full Text: PDF (221KB)

Cover4

Page(s): c4 - c4
Digital Object Identifier : 10.1109/TPAMI.2011.6
Full Text: PDF (269KB)