Wed, 20 Aug 2008 21:18:26 BST CiteULike: meirc's library [143 articles] http://www.citeulike.org/user/meirc CiteULike.org en-gb Copyright © 2004-2008 citeulike.org http://www.citeulike.org/user/meirc/article/1745231 <i>(2007), pp. 19-26.</i> Using 3D computer graphics for perception: the role of local and global information in face processing Adrian Schwaninger Sandra Schumacher Heinrich Bülthoff Christian Wallraven doi:10.1145/1272582.1272586 (2007), pp. 19-26. 2007-10-09T10:28:12-00:00 2007 19 26 ACM Press head-pose http://www.citeulike.org/user/meirc/article/1410131 <i>(2004)</i><br /><br />The non-rigid motion of a driver's head (i.e. the motion of their mouth, eye-brows, cheeks, etc) can tell us a lot about their mental state; e.g. whether they are drowsy, alert, aggressive, comfortable, tense, distracted, etc. In this paper, we describe our recent research on non-rigid face tracking. In particular, we present both 2D and 3D algorithms for tracking the non-rigid motion of the driver's head using an Active Appearance Model. Both algorithms operate at over 200 frames per... Real-time non-rigid driver head tracking for driver mental state estimation S Baker I Matthews J Xiao R Gross T Kanade T Ishikawa (2004) 2007-06-25T05:53:22-00:00 2004 emotions http://www.citeulike.org/user/meirc/article/1410128 <i></i><br /><br />This thesis describes a research project aimed at detecting emotions based on facial expression analysis. The context of this project is the I.N.E.S. system which is an intelligent tutoring system. It provides a simulation environment for nursing students to practice administering medicine by subcutaneous injection. Componential Appraisal Theory is used to describe facial expressions in terms of Stimulus Evaluation Checks and their outcomes. Also the situations in which these facial expressions ... Facial Expression Analysis for Human Computer Interaction - Recognizing Emotions in an Intelligent . . . M Ghijsen 2007-06-25T05:50:54-00:00 emotions http://www.citeulike.org/user/meirc/article/201537 <i>(2001)</i><br /><br />This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called the "Integral Image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features ... Rapid object detection using a boosted cascade of simple features P Viola M Jones (2001) 2005-05-16T15:51:34-00:00 2001 face-identity http://www.citeulike.org/user/meirc/article/1318077 <i>(2003)</i><br /><br />This paper presents a new method for face recognition which learns a face similarity measure from example image pairs. A set of computationally efficient "rectangle" features are described which act on pairs of input images. The features compare regions within the input images at different locations, scales, and orientations. The AdaBoost algorithm is used to train the face similarity function by selecting features. Given a large face database, the set of face pairs is too large for... Face recognition using boosted local features M Jones P Viola (2003) 2007-05-21T17:39:51-00:00 2003 face-identity http://www.citeulike.org/user/meirc/article/1015545 <i>(2000)</i><br /><br />Mixtures of Gaussians, factor analyzers (probabilistic PCA) and hidden Markov models are staples of static and dynamic data modeling and image and video modeling in particular. We show how topographic transformations in the input, such as translation and shearing in images, can be accounted for in these models by including a discrete transformation variable. The resulting models perform clustering, dimensionality reduction and time-series analysis in a way that is invariant to... Learning graphical models of images, videos and their spatial transformations B Frey N Jojic (2000) 2006-12-26T21:42:54-00:00 2000 hmm temporal http://www.citeulike.org/user/meirc/article/1015536 <i>pp. 50-59.</i><br /><br />A new, exemplar-based, probabilistic paradigm for visual tracking is presented. Probabilistic mechanisms are attractive because they handle fusion of information, especially temporal fusion, in a principled manner. Exemplars are selected representatives of raw training data, used here to represent probabilistic mixture distributions of object configurations. Their use avoids tedious hand-construction of object models and problems with changes of topology. Using exemplars in place of a... Probabilistic Tracking in a Metric Space Kentaro Toyama Andrew Blake pp. 50-59. 2006-12-26T21:02:41-00:00 50 59 case-based hmm trajectory http://www.citeulike.org/user/meirc/article/989399 <i>(2003)</i><br /><br />There is general consensus that context can be a rich source of information about an object's identity, location and scale. In fact, the structure of many real-world scenes is governed by strong configurational rules akin to those that apply to a single object. Here we introduce a simple framework for modeling the relationship between context and object properties based on the correlation between the statistics of low-level features across the entire scene and the objects that it contains. The... Contextual priming for object detection A Torralba (2003) 2006-12-12T08:13:27-00:00 2003 context strcuture http://www.citeulike.org/user/meirc/article/989398 <i></i><br /><br />SpatialBoost extends AdaBoost to incorporate spatial reasoning. SpatialBoost: Adding Spatial Reasoning to AdaBoost Shai Avidan 2006-12-12T08:12:10-00:00 context strcuture http://www.citeulike.org/user/meirc/article/989397 <i>(2006)</i><br /><br />Image understanding requires not only individually estimating elements of the visual world but also capturing the interplay among them. In this paper, we provide a framework for placing local object detection in the context of the overall 3D scene by modeling the interdependence of objects, surface orientations, and camera viewpoint. Putting Objects in Perspective Derek Hoiem Alexei Efros Martial Hebert (2006) 2006-12-12T08:11:42-00:00 2006 context strcuture http://www.citeulike.org/user/meirc/article/989395 <i>(2003)</i><br /><br />In visual surveillance face detection can be an important cue for initializing tracking algorithms. Recent work in psychophics hints at the importance of the local context of a face for robust detection, such as head contours and torso. This paper describes a detector that actively utilizes the idea of local context. The promise is to gain robustness that goes beyond the capabilities of traditional face detection making it particularly interesting for surveillance. The performance of the... Fast and robust face finding via local context H Kruppa M Santana B Schiele (2003) 2006-12-12T08:09:52-00:00 2003 context hand-pose http://www.citeulike.org/user/meirc/article/989394 <i>(2003)</i><br /><br />Standard approaches to object detection focus on local patches of the image, and try to classify them as background or not. We propose to use the scene context (image as a whole) as an extra source of (global) information, to help resolve local ambiguities. We present a conditional random field for jointly solving the tasks of object detection and scene classification. Using the forest to see the tree: a graphical model relating features, objects and the scenes K Murphy A Torralba W Freeman (2003) 2006-12-12T08:09:15-00:00 2003 context strcuture http://www.citeulike.org/user/meirc/article/967239 <i></i><br /><br />Many computer vision algorithms limit their performance by ignoring the underlying 3D geometric structure in the image. We show that we can estimate the coarse geometric properties of a scene by learning appearance-based models of geometric classes, even in cluttered natural scenes. Geometric classes describe the 3D orientation of an image region with respect to the camera. We provide a multiplehypothesis framework for robustly estimating scene structure from a single image and obtaining... Geometric Context from a Single Image Derek Alexei 2006-11-29T18:32:20-00:00 context strcuture http://www.citeulike.org/user/meirc/article/972175 <i>Neural Netw., Vol. 19, No. 3. (April 2006), pp. 299-310.</i> A probabilistic model of gaze imitation and shared attention Matthew Hoffman David Grimes Aaron Shon Rajesh Rao doi:10.1016/j.neunet.2006.02.008 Neural Netw., Vol. 19, No. 3. (April 2006), pp. 299-310. 2006-12-03T08:25:26-00:00 2006 Neural Netw. 0893-6080 19 3 299 310 Elsevier Science Ltd. attention gaze imitation shared-attention http://www.citeulike.org/user/meirc/article/972033 <i></i> attention: augmented, collective, visual, shared, mutual, joint, 2006-12-02T23:24:19-00:00 attention augmented-attention collective-attention joint-attention mutual-attention public-attention shared-attention visual-attention http://www.citeulike.org/user/meirc/article/967504 <i>(2006), pp. 573-578.</i> Accurate Head Pose Tracking in Low Resolution Video Jilin Tu Thomas Huang Hai Tao doi:10.1109/FGR.2006.19 (2006), pp. 573-578. 2006-11-29T23:02:59-00:00 2006 573 578 IEEE Computer Society head-pose low-res multiple-people http://www.citeulike.org/user/meirc/article/965215 <i>Lecture Notes in Computer Science : Computer Vision in Human-Computer Interaction (2005), pp. 100-109.</i> Attention Monitoring Based on Temporal Signal-Behavior Structures Akira Utsumi Shinjiro Kawato Shinji Abe doi:10.1007/11573425_10 Lecture Notes in Computer Science : Computer Vision in Human-Computer Interaction (2005), pp. 100-109. 2006-11-28T12:06:28-00:00 2005 Lecture Notes in Computer Science : Computer Vision in Human-Computer Interaction 100 109 attention content-control therapy http://www.citeulike.org/user/meirc/article/965206 <i>Lecture Notes in Computer Science : Computer Vision â ECCV 2006 (2006), pp. 402-415.</i> Estimating Gaze Direction from Low-Resolution Faces in Video Neil Robertson Ian Reid doi:10.1007/11744047_31 Lecture Notes in Computer Science : Computer Vision â ECCV 2006 (2006), pp. 402-415. 2006-11-28T11:45:05-00:00 2006 Lecture Notes in Computer Science : Computer Vision â ECCV 2006 402 415 body-pose head-pose low-res http://www.citeulike.org/user/meirc/article/965082 <i>(2006), pp. 3-8.</i> Graph Embedded Analysis for Head Pose Estimation Yun Fu Thomas Huang doi:10.1109/FGR.2006.60 (2006), pp. 3-8. 2006-11-28T09:52:11-00:00 2006 3 8 IEEE Computer Society dimension-reduction head-pose http://www.citeulike.org/user/meirc/article/942167 <i>pp. 295-300.</i><br /><br />In 3D object detection and recognition, an object of interest is subject to changes in view as well as in illumination and shape. For image classification purpose, it is desirable to derive a representation in which intrinsic characteristics of the object are captured in a low dimensional space while effects due to artifacts are reduced. In this paper, we propose a method for view-based unsupervised learning of object appearances. First, view-subspaces are learned from a view-unlabeled data set ... View-Based Clustering of Object Appearances Based on Independent Subspace Analysis Stan Li X Lv H Zhang doi:http://static.citeulike.org/img/en.png pp. 295-300. 2006-11-13T22:08:44-00:00 295 300 head-pose unsupervised http://www.citeulike.org/user/meirc/article/965059 <i>(2003), pp. 288-299.</i><br /><br />Estimation of 3D hand pose is useful in many gesture recognition applications, ranging from human-computer interaction to automated recognition of sign languages. In this paper, 3D hand pose estimation is treated as a database indexing problem. Given an input image of a hand, the most similar images in a large database of hand images are retrieved. The hand pose parameters of the retrieved images are used as estimates for the hand pose in the input image. Lipschitz embeddings of edge images... Database indexing methods for 3D hand pose estimation V Athitsos S Sclaroff (2003), pp. 288-299. 2006-11-28T09:06:05-00:00 2003 288 299 Springer-Verlag, Heidelberg hand-pose k-nn http://www.citeulike.org/user/meirc/article/965057 <i>(1996), pp. 239-27.</i><br /><br />. In pattern recognition, statistical modeling, or regression, the amount of data is a critical factor affecting the performance. If the amount of data and computational resources are unlimited, even trivial algorithms will converge to the optimal solution. However, in the practical case, given limited data and other resources, satisfactory performance requires sophisticated methods to regularize the problem by introducing a priori knowledge. Invariance of the output with respect to... Transformation Invariance in Pattern Recognition-Tangent Distance and Tangent Propagation Patrice Simard Yann Lecun John Denker Bernard Victorri (1996), pp. 239-27. 2006-11-28T08:58:42-00:00 1996 239 27 similarity tangent-distance http://www.citeulike.org/user/meirc/article/965056 <i>IEEE Trans. Pattern Anal. Mach. Intell., Vol. 24, No. 2. (February 2002), pp. 214-223.</i> Multiview Constraints on Homographies Lihi Zelnik-Manor Michal Irani doi:10.1109/34.982901 IEEE Trans. Pattern Anal. Mach. Intell., Vol. 24, No. 2. (February 2002), pp. 214-223. 2006-11-28T08:56:53-00:00 2002 IEEE Trans. Pattern Anal. Mach. Intell. 0162-8828 24 2 214 223 IEEE Computer Society mosaic multiview http://www.citeulike.org/user/meirc/article/965029 <i>Journal of Visualization and Computer Animation (2003)</i> Motion Panoramas A Bartoli N Dalal R Horaud Journal of Visualization and Computer Animation (2003) 2006-11-28T07:40:23-00:00 2003 Journal of Visualization and Computer Animation mosaic http://www.citeulike.org/user/meirc/article/965028 <i>IEEE Trans. on Image Processing, Vol. 6, No. 9. (1997)</i> Video orbits of the projective group: A simple approach to featureless estimation of parameters Steve Mann Rosalind Picard IEEE Trans. on Image Processing, Vol. 6, No. 9. (1997) 2006-11-28T07:40:22-00:00 1997 IEEE Trans. on Image Processing 6 9 mosaic http://www.citeulike.org/user/meirc/article/965027 <i>International Journal of Computer Vision, Vol. 60, No. 2. (2004), pp. 91-110.</i> Distinctive image features from scale-invariant keypoints David Lowe International Journal of Computer Vision, Vol. 60, No. 2. (2004), pp. 91-110. 2006-11-28T07:40:22-00:00 2004 International Journal of Computer Vision 60 2 91 110 mosaic http://www.citeulike.org/user/meirc/article/965026 <i>A.I. Memo, No. 1594. (Nov. 1996)</i> Direct Methods for Estimation of Structure and Motion from Three Views A Shashua GP Stein A.I. Memo, No. 1594. (Nov. 1996) 2006-11-28T07:40:22-00:00 1996 A.I. Memo 1594 direct mosaic http://www.citeulike.org/user/meirc/article/965025 <i></i> Algebraic Projective Geometry JG Semple GT Kneebone 2006-11-28T07:40:22-00:00 Oxford Classic Texts in the physical sciences, Clarendon Press, Oxford (ISBN 0 19 8503636). mosaic http://www.citeulike.org/user/meirc/article/965024 <i>Workshop on 25 Years of RANSAC (June 2006)</i> Beyond RANSAC: User Independent Robust Regression R Subbarao Meer Workshop on 25 Years of RANSAC (June 2006) 2006-11-28T07:40:22-00:00 2006 Workshop on 25 Years of RANSAC mosaic http://www.citeulike.org/user/meirc/article/965023 <i>Tech report 213, AI Center, SRI International (1980)</i> Random sample consensus: a paradigm for model tting with applications to image analysis and automated cartography MA Fishler RC Bolles Tech report 213, AI Center, SRI International (1980) 2006-11-28T07:40:22-00:00 1980 Tech report 213, AI Center, SRI International bibtex-import http://www.citeulike.org/user/meirc/article/965022 <i>International Journal of Computer Vision, Vol. 9, No. 2. (1992), pp. 137-154.</i> Shape and Motion from Image Streams under Orthography: a Factorization Method C Tomasi T Kanade International Journal of Computer Vision, Vol. 9, No. 2. (1992), pp. 137-154. 2006-11-28T07:40:21-00:00 1992 International Journal of Computer Vision 9 2 137 154 mosaic http://www.citeulike.org/user/meirc/article/965021 <i>CVPR (1996), pp. 845-851.</i> Factorization Methods for Projective Structure and Motion B Triggs CVPR (1996), pp. 845-851. 2006-11-28T07:40:21-00:00 1996 CVPR 845 851 mosaic http://www.citeulike.org/user/meirc/article/965020 <i>European Conference on Computer Vision, Vol. B (1996), pp. 709-720.</i> A factorization based algorithm for multi-image projective structure and motion P Sturm B Triggs European Conference on Computer Vision, Vol. B (1996), pp. 709-720. 2006-11-28T07:40:21-00:00 1996 European Conference on Computer Vision B 709 720 mosaic http://www.citeulike.org/user/meirc/article/965019 <i>IEEE Conference on Computer Vision and Pattern Recognition (1997), pp. 400-406.</i> Model-based Brightness constraints: On Direct Estimation of Structure and Motion GP Stein A Shashua IEEE Conference on Computer Vision and Pattern Recognition (1997), pp. 400-406. 2006-11-28T07:40:21-00:00 1997 IEEE Conference on Computer Vision and Pattern Recognition 400 406 direct mosaic http://www.citeulike.org/user/meirc/article/965018 <i>IEEE Conference on Computer Vision and Pattern Recognition (1994), pp. 483-489.</i> Relative affine Structure: Theory and Application to 3D Reconstruction From Perspective Views A Shashua N Navab IEEE Conference on Computer Vision and Pattern Recognition (1994), pp. 483-489. 2006-11-28T07:40:21-00:00 1994 IEEE Conference on Computer Vision and Pattern Recognition 483 489 mosaic http://www.citeulike.org/user/meirc/article/965017 <i>IEEE Conference on Computer Vision and Pattern Recognition (June 1994), pp. 929-934.</i> 3D Geometry From Planar Parallax HS Sawhney IEEE Conference on Computer Vision and Pattern Recognition (June 1994), pp. 929-934. 2006-11-28T07:40:21-00:00 1994 IEEE Conference on Computer Vision and Pattern Recognition 929 934 mosaic parallax http://www.citeulike.org/user/meirc/article/965016 <i>Proceedings of The Royal Society of London B, Vol. 223 (1984), pp. 165-175.</i> Visual Ambiguity of a Moving Plane Longuet Proceedings of The Royal Society of London B, Vol. 223 (1984), pp. 165-175. 2006-11-28T07:40:21-00:00 1984 Proceedings of The Royal Society of London B 223 165 175 mosaic http://www.citeulike.org/user/meirc/article/965015 <i>Nature, Vol. 293 (Sep. 1981), pp. 133-135.</i> A computer algorithm for reconstructing a scene from two projections Longuet Nature, Vol. 293 (Sep. 1981), pp. 133-135. 2006-11-28T07:40:21-00:00 1981 Nature 293 133 135 mosaic http://www.citeulike.org/user/meirc/article/965014 <i>International Conference on Pattern Recognition (Oct. 1994), pp. 685-688.</i> Direct Recovery of shape From Multiple Views: a Parallax Based Approach R Kumar P Anandan K Hanna International Conference on Pattern Recognition (Oct. 1994), pp. 685-688. 2006-11-28T07:40:21-00:00 1994 International Conference on Pattern Recognition 685 688 direct mosaic parallax http://www.citeulike.org/user/meirc/article/965013 <i>IEEE Trans. on Pattern Analysis and Machine Intelligence (1998)</i> Untitled M Irani IEEE Trans. on Pattern Analysis and Machine Intelligence (1998) 2006-11-28T07:40:20-00:00 1998 IEEE Trans. on Pattern Analysis and Machine Intelligence bibtex-import http://www.citeulike.org/user/meirc/article/965012 <i>European Conference on Computer Vision, Vol. II (1998), pp. 829-845.</i> From Reference Frames to Reference Planes: Multi-View Parallax Geometry and Applications M Irani P Anandan D Weinshall European Conference on Computer Vision, Vol. II (1998), pp. 829-845. 2006-11-28T07:40:20-00:00 1998 European Conference on Computer Vision II 829 845 mosaic parallax http://www.citeulike.org/user/meirc/article/965011 <i>IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 19, No. 3. (March 1997), pp. 268-272.</i> Recovery of Ego-Motion Using Region Alignment M Irani B Rousso P Peleg IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 19, No. 3. (March 1997), pp. 268-272. 2006-11-28T07:40:20-00:00 1997 IEEE Trans. on Pattern Analysis and Machine Intelligence 19 3 268 272 direct mosaic http://www.citeulike.org/user/meirc/article/965010 <i>European Conference on Computer Vision, Vol. A (April 1996), pp. 17-30.</i> Parallax Geometry of Pairs of Points for 3D Scene Analysis M Irani P Anandan European Conference on Computer Vision, Vol. A (April 1996), pp. 17-30. 2006-11-28T07:40:20-00:00 1996 European Conference on Computer Vision A 17 30 mosaic parallax http://www.citeulike.org/user/meirc/article/965009 <i>International Journal of Computer Vision, Vol. 12, No. 1. (Jan. 1994), pp. 5-16.</i> Computing Occluding and Transparent Motions M Irani B Rousso S Peleg International Journal of Computer Vision, Vol. 12, No. 1. (Jan. 1994), pp. 5-16. 2006-11-28T07:40:20-00:00 1994 International Journal of Computer Vision 12 1 5 16 direct mosaic http://www.citeulike.org/user/meirc/article/965008 <i>International Journal of Computer Vision, Vol. 2 (1988), pp. 51-76.</i> Direct Methods for Recovering Motion BKP Horn Weldon International Journal of Computer Vision, Vol. 2 (1988), pp. 51-76. 2006-11-28T07:40:20-00:00 1988 International Journal of Computer Vision 2 51 76 direct mosaic http://www.citeulike.org/user/meirc/article/965007 <i>IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 19, No. 6. (June 1997), pp. 580-593.</i> In Defense of the Eight-Point Algorithm RI Hartley IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 19, No. 6. (June 1997), pp. 580-593. 2006-11-28T07:40:19-00:00 1997 IEEE Trans. on Pattern Analysis and Machine Intelligence 19 6 580 593 mosaic http://www.citeulike.org/user/meirc/article/965006 <i>International Conference on Computer Vision (1993), pp. 357-365.</i> Combining Stereo and Motion for Direct Estimation of Scene Structure KJ Hanna NE Okamoto International Conference on Computer Vision (1993), pp. 357-365. 2006-11-28T07:40:19-00:00 1993 International Conference on Computer Vision 357 365 direct mosaic http://www.citeulike.org/user/meirc/article/965005 <i>Workshop on Visual Motion (Oct. 1991), pp. 156-162.</i> Direct Multi-Resolution Estimation of Ego-Motion and Structure From Motion KJ Hanna Workshop on Visual Motion (Oct. 1991), pp. 156-162. 2006-11-28T07:40:19-00:00 1991 Workshop on Visual Motion 156 162 mosaic http://www.citeulike.org/user/meirc/article/965004 <i>MIT Press (1996)</i> Three-Dimensional Computer Vision -- A Geometric Viewpoint Faugeras Olivier MIT Press (1996) 2006-11-28T07:40:18-00:00 1996 MIT Press mosaic http://www.citeulike.org/user/meirc/article/965003 <i>European Conference on Computer Vision (May 1992), pp. 563-578.</i> What can be seen in three dimensions with an uncalibrated stereo rig? OD Faugeras European Conference on Computer Vision (May 1992), pp. 563-578. 2006-11-28T07:40:18-00:00 1992 European Conference on Computer Vision 563 578 mosaic