Search For:

Displaying 1-25 out of 25 total
3D Traffic Scene Understanding From Movable Platforms
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Andreas Geiger,Martin Lauer,Christian Wojek,Christoph Stiller,Raquel Urtasun
Issue Date:May 2014
pp. 1-1
In this paper, we present a novel probabilistic generative model for multi-object traffic scene understanding from movable platforms which reasons jointly about the 3D scene layout as well as the location and orientation of objects in the scene. In particu...
   
Holistic Scene Understanding for 3D Object Detection with RGBD Cameras
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Dahua Lin,Sanja Fidler,Raquel Urtasun
Issue Date:December 2013
pp. 1417-1424
In this paper, we tackle the problem of indoor scene understanding using RGBD data. Towards this goal, we propose a holistic approach that exploits 2D segmentation, 3D geometry, as well as contextual relations between scenes and objects. Specifically, we e...
 
Estimating the 3D Layout of Indoor Scenes and Its Clutter from Depth Sensors
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Jian Zhang,Chen Kan,Alexander G. Schwing,Raquel Urtasun
Issue Date:December 2013
pp. 1273-1280
In this paper we propose an approach to jointly estimate the layout of rooms as well as the clutter present in the scene using RGB-D data. Towards this goal, we propose an effective model that is able to exploit both depth and appearance features, which ar...
 
Box in the Box: Joint 3D Layout and Object Reasoning from Single Images
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Alexander G. Schwing,Sanja Fidler,Marc Pollefeys,Raquel Urtasun
Issue Date:December 2013
pp. 353-360
In this paper we propose an approach to jointly infer the room layout as well as the objects present in the scene. Towards this goal, we propose a branch and bound algorithm which is guaranteed to retrieve the global optimum of the joint problem. The main ...
 
Understanding High-Level Semantics by Modeling Traffic Patterns
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Hongyi Zhang,Andreas Geiger,Raquel Urtasun
Issue Date:December 2013
pp. 3056-3063
In this paper, we are interested in understanding the semantics of outdoor scenes in the context of autonomous driving. Towards this goal, we propose a generative model of 3D urban scenes which is able to reason not only about the geometry and objects pres...
 
Physically-based motion models for 3D tracking: A convex formulation
Found in: Computer Vision, IEEE International Conference on
By Mathieu Salzmann,Raquel Urtasun
Issue Date:November 2011
pp. 2064-2071
In this paper, we propose a physically-based dynamical model for tracking. Our model relies on Newton's second law of motion, which governs any real-world dynamical system. As a consequence, it can be generally applied to very different tracking problems. ...
 
Combining discriminative and generative methods for 3D deformable surface and articulated pose reconstruction
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Mathieu Salzmann, Raquel Urtasun
Issue Date:June 2010
pp. 647-654
Historically non-rigid shape recovery and articulated pose estimation have evolved as separate fields. Recent methods for non-rigid shape recovery have focused on improving the algorithmic formulation, but have only considered the case of reconstruction fr...
 
Sufficient dimension reduction for visual sequence classification
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Alex Shyr, Raquel Urtasun, Michael I. Jordan
Issue Date:June 2010
pp. 3610-3617
When classifying high-dimensional sequence data, traditional methods (e.g., HMMs, CRFs) may require large amounts of training data to avoid overfitting. In such cases dimensionality reduction can be employed to find a low-dimensional representation on whic...
 
Unsupervised feature selection via distributed coding for multi-view object recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By C. Mario Christoudias, Raquel Urtasun, Trevor Darrell
Issue Date:June 2008
pp. 1-8
Object recognition accuracy can be improved when information from multiple views is integrated, but information in each view can often be highly redundant. We consider the problem of distributed object recognition or indexing from multiple cameras, where t...
 
Local deformation models for monocular 3D shape recovery
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Mathieu Salzmann, Raquel Urtasun, Pascal Fua
Issue Date:June 2008
pp. 1-8
Without a deformation model, monocular 3D shape recovery of deformable surfaces is severly under-constrained. Even when the image information is rich enough, prior knowledge of the feasible deformations is required to overcome the ambiguities. This is furt...
 
Sparse probabilistic regression for activity-independent human pose inference
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Raquel Urtasun, Trevor Darrell
Issue Date:June 2008
pp. 1-8
Discriminative approaches to human pose inference in volve mapping visual observations to articulated body configurations. Current probabilistic approaches to learn this mapping have been limited in their ability to handle domains with a large number of ac...
 
Active Learning with Gaussian Processes for Object Categorization
Found in: Computer Vision, IEEE International Conference on
By Ashish Kapoor, Kristen Grauman, Raquel Urtasun, Trevor Darrell
Issue Date:October 2007
pp. 1-8
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gaussian Processes (GPs) are powerful regression techniques with explicit uncertai...
 
3D People Tracking with Gaussian Process Dynamical Models
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Raquel Urtasun, David J. Fleet, Pascal Fua
Issue Date:June 2006
pp. 238-245
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of human motion data, with a density function that gives higher probability to pos...
 
Priors for People Tracking from Small Training Sets
Found in: Computer Vision, IEEE International Conference on
By Raquel Urtasun, David J. Fleet, Aaron Hertzmann, Pascal Fua
Issue Date:October 2005
pp. 403-410
We advocate the use of Scaled Gaussian Process Latent Variable Models (SGPLVM) to learn prior models of 3D human pose for 3D people tracking. The SGPLVM simultaneously optimizes a low-dimensional embedding of the high-dimensional pose data and a density fu...
 
Monocular 3-D Tracking of the Golf Swing
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Raquel Urtasun, David J. Fleet, Pascal Fua
Issue Date:June 2005
pp. 932-938
<p>We propose an approach to incorporating dynamic models into the human body tracking process that yields full 3-D reconstructions from monocular sequences. We formulate the tracking problem in terms of minimizing a differentiable criterion whose di...
 
Monocular 3D Tracking of the Golf Swing
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Raquel Urtasun, David J. Fleet, Pascal Fua
Issue Date:June 2005
pp. 1199
No summary available.
   
3D Tracking for Gait Characterization and Recognition
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Raquel Urtasun, Pascal Fua
Issue Date:May 2004
pp. 17
We propose an approach to gait analysis that relies on fitting 3-D temporal motion models to synchronized video sequences. These models allow us not only to track but also to recover motion parameters that can be used to recognize people and characterize t...
 
An Automatic Method For Determining Quaternion Field Boundaries for Ball-and-Socket Joint Limits
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Lorna Herda, Raquel Urtasun, Pascal Fua, Andrew Hanson
Issue Date:May 2002
pp. 0095
To improve the robustness of human motion synthesis and capture algorithms, our goal is to provide an effective framework for imposing joint limits and reducing ambiguities. To this end, we determine these joint limits from measures performed on human subj...
 
Transductive Gaussian processes for image denoising
Found in: 2014 IEEE International Conference on Computational Photography (ICCP)
By Shenlong Wang,Lei Zhang,Raquel Urtasun
Issue Date:May 2014
pp. 1-8
In this paper we are interested in exploiting self-similarity information for discriminative image denoising. Towards this goal, we propose a simple yet powerful denoising method based on transductive Gaussian processes, which introduces self-similarity in...
   
A Sentence Is Worth a Thousand Pixels
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Sanja Fidler,Abhishek Sharma,Raquel Urtasun
Issue Date:June 2013
pp. 1995-2002
We are interested in holistic scene understanding where images are accompanied with text in the form of complex sentential descriptions. We propose a holistic conditional random field model for semantic parsing which reasons jointly about which objects are...
 
Bottom-Up Segmentation for Top-Down Detection
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Sanja Fidler,Roozbeh Mottaghi,Alan Yuille,Raquel Urtasun
Issue Date:June 2013
pp. 3294-3301
In this paper we are interested in how semantic segmentation can help object detection. Towards this goal, we propose a novel deformable part-based model which exploits region-based segmentation algorithms that compute candidate object regions by bottom-up...
 
Robust Monocular Epipolar Flow Estimation
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Koichiro Yamaguchi,David McAllester,Raquel Urtasun
Issue Date:June 2013
pp. 1862-1869
We consider the problem of computing optical flow in monocular video taken from a moving vehicle. In this setting, the vast majority of image flow is due to the vehicle's ego-motion. We propose to take advantage of this fact and estimate flow along the epi...
 
Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Roozbeh Mottaghi,Sanja Fidler,Jian Yao,Raquel Urtasun,Devi Parikh
Issue Date:June 2013
pp. 3143-3150
Recent trends in semantic image segmentation have pushed for holistic scene understanding models that jointly reason about various tasks such as object detection, scene recognition, shape analysis, contextual reasoning. In this work, we are interested in u...
 
Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Marcus A. Brubaker,Andreas Geiger,Raquel Urtasun
Issue Date:June 2013
pp. 3057-3064
In this paper we propose an affordable solution to self-localization, which utilizes visual odometry and road maps as the only inputs. To this end, we present a probabilistic model as well as an efficient approximate inference algorithm, which is able to u...
 
Non-linear matrix factorization with Gaussian processes
Found in: Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09)
By Neil D. Lawrence, Raquel Urtasun
Issue Date:June 2009
pp. 1-8
A popular approach to collaborative filtering is matrix factorization. In this paper we develop a non-linear probabilistic matrix factorization using Gaussian process latent variable models. We use stochastic gradient descent (SGD) to optimize the model. S...
     
 1