- Subscribe to this page:
- RSS
- Email Alert
graphics applications
(682 results)-
White Papers
Supporting 3D Route Planning in Indoor Space Based on the LEGO Representation
Nov 2010
With the prevalence of car navigation systems, indoor navigation systems are increasingly attracting attention in the indoor research area. However, the available models for indoor navigation...
Provided by Association for Computing Machinery
-
White Papers
Modeling Cardinal Directions in the 3D Space With the Objects Interaction Cube Matrix
Mar 2010
In GIS and spatial databases, cardinal directions are frequently used as selection and join criteria in query languages. However, most cardinal direction models are only able to handle...
Provided by Association for Computing Machinery
-
White Papers
Image Synthesis Using Adjoint Photons
Jan 2011
The most straightforward image synthesis algorithm is to follow photon-like particles from luminaires through the environment. These particles scatter or are absorbed when they interact with a...
Provided by University of Central Florida
-
White Papers
Effects of Interior Bezels of Tiled-Monitor Large Displays on Visual Search, Tunnel Steering, and Target Selection
Apr 2010
Tiled-monitor large displays are widely used in various application domains. However, how their interior bezels affect user performance and behavior has not been fully understood. The authors...
Provided by Association for Computing Machinery
-
White Papers
EverybodyLovesSketch: 3D Sketching for a Broader Audience
Oct 2009
The authors present EverybodyLovesSketch, a gesture-based 3D curve sketching system for rapid ideation and visualization of 3D forms, aimed at a broad audience. The authors first analyze...
Provided by Association for Computing Machinery
-
White Papers
Improving Visual Search With Image Segmentation
Apr 2009
People's ability to accurately locate target objects in images is severely affected by the prevalence of the sought objects. This negative effect greatly impacts critical real world tasks, such as...
Provided by Institute of Electrical and Electronics Engineers
-
White Papers
ILoveSketch: As-Natural-As-Possible Sketching System for Creating 3D Curve Models
Oct 2008
The authors present ILoveSketch, a 3D curve sketching system that captures some of the affordances of pen and paper for professional designers, allowing them to iterate directly on concept 3D...
Provided by Institute of Electrical and Electronics Engineers
-
White Papers
An Approach on Hardware Design for Computationally Intensive Image Processing Applications Based on Light Field Refocusing Algorithm
Jun 2010
This paper describes the performance analysis of the light field refocusing algorithm running on different hardware specifications, including the Intel Pentium 4, SSE2(Streaming SIMD Extensions),...
Provided by University of Virginia
-
White Papers
Breaking the Interactive Bottleneck in Multi-Class Classification With Active Selection and Binary Feedback
Jul 2010
Multi-class classification schemes typically require human input in the form of precise category names or numbers for each example to be annotated - providing this can be impractical for the user...
Provided by Mitsubishi Electric Research Laboratories
-
White Papers
Morphable Reflectance Fields for Enhancing Face Recognition
Jul 2010
In this paper, the authors present a novel framework to address the confounding effects of illumination variation in face recognition. By augmenting the gallery set with realistically relit...
Provided by Mitsubishi Electric Research Laboratories
-
White Papers
RelCom: Relational Combinatorics Features for Rapid Object Detection
Jul 2010
The authors present a simple yet elegant feature, RelCom, and a boosted selection method to achieve a very low complexity object detector. They generate combinations of low-level feature...
Provided by Mitsubishi Electric Research Laboratories
-
White Papers
Multi-Class Batch-Mode Active Learning for Image Classification
Jul 2010
Accurate image classification is crucial in many robotics and surveillance applications - for example, a vision system on a robot needs to accurately recognize the objects seen by its camera....
Provided by Mitsubishi Electric Research Laboratories
-
White Papers
Hiding Information Inside Structured Shapes
Mar 2010
This paper describes a new technique for embedding a message within structured shapes. It is desired that one changes in the shape owing to the embedded message are invisible to a casual observer...
Provided by Mitsubishi Electric Research Laboratories
-
White Papers
TV Architecture Supporting Multiple 3D Services
Mar 2010
This paper describes changes to the television architecture to support 3D video, with emphasis on the receiver and display processor. It is expected that multiple 3D services will be available in...
Provided by Mitsubishi Electric Research Laboratories
-
White Papers
Object Detection Via Boosted Deformable Features
Dec 2009
It is a common practice to model an object for detection tasks as a boosted ensemble of many models built on features of the object. In this paper, features are defined as subregions with fixed...
Provided by Mitsubishi Electric Research Laboratories
-
White Papers
Depth Reconstruction Filter and Down/Up Sampling for Depth Coding in 3D Video
Jul 2009
Depth images represent Three-Dimensional (3D) scene information and are commonly used for Depth Image Based Rendering (DIBR) to support 3D video and free-viewpoint video applications. The virtual...
Provided by Mitsubishi Electric
-
White Papers
Divide & Concur and Difference-Map BP Decoders for LDPC Codes
Jan 2011
The "Divide and Concur" (DC) algorithm, recently introduced by Gravel and Elser, can be considered a competitor to the Belief Propagation (BP) algorithm, in that both algorithms can be applied to...
Provided by Institute of Electrical and Electronics Engineers
-
White Papers
Intermediate View Generation for Perceived Depth Adjustment of Stereo Video
Jan 2011
There is significant industry activity on delivery of 3D video to the home. It is expected that 3D capable devices will be able to provide consumers with the ability to adjust the depth perceived...
Provided by Mitsubishi Electric
-
White Papers
Invertible Motion Blur in Video
Sep 2009
The authors show that motion blur in successive video frames is invertible even if the Point-Spread Function (PSF) due to motion smear in a single photo is non-invertible. Blurred photos exhibit...
Provided by Mitsubishi Electric
-
White Papers
3D Pose Estimation and Segmentation Using Specular Cues
Sep 2009
The authors demonstrated that specular reflections can be used for localization and pose estimation of specular objects using a known CAD model. They showed that simple feature/ intensity matching...
Provided by Mitsubishi Electric
-
White Papers
Hole-Filling Method Using Depth Based In-Painting for View Synthesis in Free Viewpoint Television (FTV) and 3D Video
Jun 2009
Depth Image-Based Rendering (DIBR) is generally used to synthesize a virtual view in Free Viewpoint Television (FTV) and 3D video. One of the key techniques in DIBR is how to fill the holes caused...
Provided by Mitsubishi Electric
-
White Papers
Shield Fields: Modeling and Capturing 3D Occluders
Dec 2008
The authors describe a unified representation of occluders in light transport and photography using shield fields: the 4D attenuation function which acts on any light field incident on an...
Provided by Mitsubishi Electric
-
White Papers
Touch-Display Keyboards and Their Integration With Graphical User Interfaces
Oct 2009
The authors introduce Touch-Display Keyboards (TDK) that retain the traditional physical key layout and in addition provide dynamic display and touch-sensing capability for each key. They...
Provided by Lancaster University
-
White Papers
24-GOPS 4.5-Mm2 Digital Cellular Neural Network for Rapid Visual Attention in an Object-Recognition SoC
Jan 2011
This paper presents the Visual Attention Engine (VAE), which is a digital Cellular Neural Network (CNN) that executes the VA algorithm to speed up object-recognition. The proposed Time-Multiplexed...
Provided by Institute of Electrical and Electronics Engineers
-
White Papers
A 152-MW Mobile Multimedia SoC With Fully Programmable 3-D Graphics and MPEG4/H.264/JPEG
Sep 2009
This paper presents a low power multimedia System-on-Chip (SoC) with full integration with fully programmable 3-D graphics, MPEG4 codec, H.264 decoder, and JPEG codec for mobile devices. The...
Provided by Institute of Electrical and Electronics Engineers
-
White Papers
A Low-Power Multimedia SoC With Fully Programmable 3D Graphics for Mobile Devices
Sep 2009
As the mobile-electronics market grows, third-generation terminals such as smart cell phones and personal multimedia players are becoming popular. Because users carry mobile devices all the time,...
Provided by Institute of Electrical and Electronics Engineers
-
White Papers
An Embedded Stream Processor Core Based on Logarithmic Arithmetic for a Low-Power 3-D Graphics SoC
May 2009
A low-power and high-performance 4-way 32-bit stream processor core is developed for handheld low-power 3-D graphics systems. It contains a floating-point unified matrix, vector, and elementary...
Provided by Institute of Electrical and Electronics Engineers
-
White Papers
A 200-Mbps 0.02-nJ/b Dual-Mode Inductive Coupling Transceiver for cm-Range Multimedia Application
May 2009
A 200-Mbps 0.02-nJ/b dual-mode inductive coupling transceiver is proposed for cm-range multimedia application. The inductive link geometry and the advantage of the pulse-based inductive coupling...
Provided by Institute of Electrical and Electronics Engineers
-
White Papers
A 195 MW, 9.1 MVertices/s Fully Programmable 3-D Graphics Processor for Low-Power Mobile Devices
Nov 2008
A 195 mW, 9.1 Mvertices/s fully programmable 3-D graphics processor is designed and implemented for mobile devices. The mobile unified shader provides programmable per-vertex operations and...
Provided by Institute of Electrical and Electronics Engineers
-
White Papers
A 195 MW/152 MW Mobile Multimedia SoC With Fully Programmable 3-D Graphics and MPEG4/H.264/JPEG
Sep 2008
In this paper, the authors present a low power multimedia SoC with fully programmable 3-D graphics, MPEG4 codec, H.264 decoder, and JPEG codec for mobile devices. The mobile unified shader in 3-D...
Provided by Institute of Electrical and Electronics Engineers
-
White Papers
Linear Spatial Pyramid Matching Using Sparse Coding for Image Classification
Apr 2009
In recent years the Bag-of-Features (BoF) model has been extremely popular in image categorization. The method treats an image as a collection of unordered appearance descriptors extracted from...
Provided by University of Illinois at Urbana-Champaign
-
White Papers
Multi-Label Sparse Coding for Automatic Image Annotation
Apr 2009
Automatic image annotation, whose goal is to automatically assign the images with the keywords, has been an active research topic owing to its great potentials in image retrieval and management...
Provided by National University of Singapore
-
White Papers
Support Vector Machines in Face Recognition With Occlusions
Mar 2009
Support Vector Machines (SVM) is one of the most useful techniques in classification problems. One clear example is face recognition. However, SVM cannot be applied when the feature vectors...
Provided by Ohio State University
-
White Papers
Observable Subspaces for 3D Human Motion Recovery
Jul 2009
The articulated body models used to represent human motion typically have many degrees of freedom, usually expressed as joint angles that are highly correlated. The true range of motion can...
Provided by UC Regents
-
White Papers
Blind Motion Deblurring From a Single Image Using Sparse Approximation
Mar 2010
Restoring a clear image from a single motion-blurred image due to camera shake has long been one challenging problem in digital imaging. Existing blind deblurring techniques either only can remove...
Provided by National University of Singapore
-
White Papers
Piecewise Planar City 3D Modeling From Street View Panoramic Sequences
Apr 2009
City environments often lack textured areas, contain repetitive structures, strong lighting changes and therefore are very difficult for standard 3D modeling pipelines. The authors present a novel...
Provided by George Mason University
-
White Papers
Learning Real-Time MRF Inference for Image Denoising
Mar 2009
Many computer vision problems can be formulated in a Bayesian framework with Markov Random Field (MRF) or Conditional Random Field (CRF) priors. Usually, the model assumes that a full Maximum A...
Provided by Florida State University
-
White Papers
Human Motion Synthesis From 3D Video
Mar 2009
Multiple view 3D video reconstruction of actor performance captures a level-of-detail for body and clothing movement which is time-consuming to produce using existing animation tools. In this...
Provided by University of Surrey
-
White Papers
Active Volume Models for 3D Medical Image Segmentation
Apr 2009
In this paper, the authors propose a novel predictive model for object boundary, which can integrate information from any sources. The model is a dynamic "Object" model whose manifestation...
Provided by Lehigh University
-
White Papers
Boosted Multi-Task Learning for Face Verification With Applications to Web Image and Video Search
Mar 2009
Face verification has many potential applications including filtering and ranking image/video search results on celebrities. Since these images/videos are taken under uncontrolled environments,...
Provided by Microsoft Research
-
Podcasts
ARCast.TV: UI of the New Era, Designing for Multiple Devices
Feb 2011
Computer screens in laptops, desktops and phones are now the targets for application developers yet they represent challenges as the resolution, size, among other factors. The speaker of this...
Provided by Microsoft
-
Podcasts
ARCast.TV: Sharp Dudes Discuss Silverlight Application Migration
Feb 2011
The speakers of this podcast discussed about their application migration experience moving from Microsoft Silverlight 3 to Silverlight 4. Using demos, they focused on discussing two common areas...
Provided by Microsoft
-
Podcasts
MSDN Radio: Silverlight, RIA and Windows Phone With Tim Huckaby
Feb 2011
The speaker of this podcast talks about Microsoft Silverlight, Rich Internet Application (RIA), Windows Phone and Touch Interfaces. The speaker of this podcast explores what's compelling and cool...
Provided by Microsoft
-
White Papers
Tree Histogram Coding for Mobile Image Matching
Feb 2010
For mobile image matching applications, a mobile device captures a query image, extracts descriptive features, and transmits these features wirelessly to a server. The server recognizes the query...
Provided by Stanford University
-
White Papers
Towards Chip-on-Chip Neuroscience: Fast Mining of Neuronal Spike Streams Using Graphics Hardware
May 2010
Computational neuroscience is being revolutionized with the advent of multi-electrode arrays that provide real-time, dynamic perspectives into brain function. Mining neuronal spike streams from...
Provided by Association for Computing Machinery
-
White Papers
Analyzing and Detecting Malicious Flash Advertisements
Jun 2010
The amount of dynamic content on the web has been steadily increasing. Scripting languages such as JavaScript and browser extensions such as Adobe's Flash have been instrumental in creating...
Provided by University of California
-
White Papers
iScope: Personalized Multi-Modality Image Search for Mobile Devices
Jun 2009
Mobile devices are becoming a primary medium for personal information gathering, management, and sharing. Managing personal image data on mobile platforms is a difficult problem due to large data...
Provided by Association for Computing Machinery
-
White Papers
Image-Based Rendering: A New Rendering Paradigm
Mar 2008
In the pursuit of photo-realism in conventional polygon-based computer graphics, models have become so complex that most of the polygons are smaller than one pixel in the final image. At the same...
Provided by Shaheed Udham Singh Group of Institutions
-
White Papers
Color Video Sequences Encryption/Decryption Processes Using Several Color Keys Images
Apr 2008
An optical encrypted color video sequence based on a spectral fusion of information has been proposed. Each color image of the sequence is decomposed into three basic color components. Pertinent...
Provided by Universite de Moncton
-
White Papers
High Speed and Area Efficient 2D DWT Processor Based Image Compression
Dec 2010
This paper presents a high speed and area efficient DWT processor based design for Image Compression applications. In this proposed design, pipelined partially serial architecture has been used to...
Provided by NITTTR
-
White Papers
Detection of a Virtual Passive Pointer
May 2009
The paper presents a methodology for detecting a virtual passive pointer. The passive pointer or device does not have any active energy source within it (as opposed to a laser pointer) and thus...
Provided by New York University
-
White Papers
Image Semantic Classification Using SVM in Image Retrieval
Dec 2009
There is a gap between low-level descriptions of image content and the semantic understanding of users to query image databases in the content-based image retrieval. In this paper, the authors put...
Provided by Academy Publisher
-
White Papers
Using Ontology to Create 3D Animations for Training Purposes
Jul 2007
3D Computer-based animations are nowadays used for training purposes in a wide range of industrial applications like assembly, maintenance and operations. Their creation, also known as authoring,...
Provided by University of Paderborn
-
White Papers
Digital Images Inpainting Using Modified Convolution Based Method
Nov 2008
Reconstruction of missing parts or scratches of digital images is an important field used extensively in artwork restoration. This restoration can be done by using two approaches, image inpainting...
Provided by Menofyia University
-
White Papers
Enhancing Visual Basic GUI Applications Using VRML Scenes
Sep 2010
Rapid Application Development (RAD) enables ever expanding needs for speedy development of computer application programs that are sophisticated, reliable, and full-featured. Visual Basic was the...
Provided by Mekelle University
-
White Papers
Temporal Modeling of Head Movement During Facial Expression Via Dual Pivot Tracking System - A Case of Disgust
Mar 2009
Temporal modeling of facial expression is very important in various fields which include expression recognition, realism in computer animation and behavioral study in psychological field. While...
Provided by Universiti Putra Malaysia
-
White Papers
Loop Back Connected Component Labeling Algorithm and Its Implementation in Detecting Face
Sep 2010
In this study, a Loop Back Algorithm for component connected labeling for detecting objects in a digital image is presented. The approach is using loop back connected component labeling algorithm...
Provided by Universiti Teknologi Malaysia
-
White Papers
Supercompression for Full-HD and 4k-3D (8k) Digital TV Systems
Jan 2011
In this work, the authors developed the concept of supercompression, i.e., compression above the compression standard used. In this context, both compression rates are multiplied. In fact,...
Provided by World Academy of Science, Engineering and Technology
-
White Papers
Single Frame Supercompression of Still Images, Video, High Definition TV and Digital Cinema
Dec 2010
Super-resolution is nowadays used for a high-resolution image produced from several low-resolution noisy frames. In this paper, the authors consider the problem of high-quality interpolation of a...
Provided by UNTREF
-
White Papers
VLSI Design for High-Speed Image Computing Using Fast Convolution-Based Discrete Wavelet Transform
May 2009
This paper presents a VLSI design for very high-speed image computing using discrete wavelet transform. The proposed architecture, based on new and fast convolution approach, reduces the hardware...
Provided by University of Quebec
-
White Papers
Reconstructed Color Image Segmentation
Oct 2009
This paper discusses a new color model for digital image, which can be used to separate low, and high frequencies in the image without loosing any information from the image. The proposed model...
Provided by Al al-Bayt University
-
White Papers
Image Segmentation Using Multi-Coloured Active Illumination
Nov 2007
In this paper, the use of active illumination is extended to image segmentation, specifically in the case of overlapping particles. This work is based on Multi-Flash Imaging (MFI), originally...
Provided by Academy Publisher
-
White Papers
Data Steganography for Optical Color Image Cryptosystems
Feb 2010
In this paper, an optical color image cryptosystem with a data hiding scheme is proposed. In the proposed optical cryptosystem, a confidential color image is embedded into the host image of the...
Provided by Asia University
-
Podcasts
Building Silverlight and Windows Phone Applications That Consume SQL Azure
Jan 2011
The attendees of this podcast will learn a great deal in a short time and covers a wide range of topics and technologies such as Microsoft SQL Azure, Windows Phone 7, ADO.NET Entity Framework and...
Provided by Microsoft
-
Podcasts
MSDN Radio: TFS Running on Azure With Brian Harry
Jan 2011
The recent release of Windows Azure 1.3 provides more possibilities including remote desktop to running instances, virtual machine role, new diagnostic information and more. At PDC 10 it was...
Provided by Microsoft
-
Podcasts
Native Extensions for Microsoft Silverlight (NESL) (Part 1 of 2)
Jan 2011
Native Extensions for Microsoft SilverLight (NESL) is an effort to incrementally build a library of components that expose select Windows 7 operating system features through COM automation, making...
Provided by Microsoft
-
Podcasts
SharePoint Ecosystem: Integrating SharePoint With Silverlight
Jan 2011
Now more than ever, it is easy to develop rich Microsoft SharePoint applications by using Microsoft Silverlight. But, most developers don't know how to get started. The presenters bring together...
Provided by Microsoft
-
Podcasts
Native Extensions for Microsoft Silverlight (NESL) (Part 2 of 2)
Jan 2011
Native Extensions for Microsoft Silverlight (NESL) is an effort to incrementally build a library of components that expose select Windows 7 operating system features through COM automation, making...
Provided by Microsoft
-
Podcasts
SharePoint 2010 FireStarter (Part 7 of 7): Integrating SharePoint With Silverlight
Feb 2011
Now, more than ever, it's easy to develop rich Microsoft SharePoint applications using Microsoft Silverlight. The attendee of this podcast learn how to get started as the presenters of this...
Provided by Microsoft
-
White Papers
Logarithmic Edge Detection With Applications
Sep 2008
In real world machine vision problems, numerous issues such as variable scene illumination make edge and object detection difficult. There exists no universal edge detection method which works...
Provided by Academy Publisher
-
White Papers
Efficient Sparse Voxel Octrees
Feb 2010
In this paper the authors examine the possibilities of using voxel representations as a generic way for expressing complex and feature-rich geometry on current and future GPUs. They present in...
Provided by NVIDIA
-
White Papers
Visualization Viewpoints: From Abstract Painting to Information Visualization
Jun 2007
The well-established theory and techniques in abstract painting and practice can benefit information visualization - even though the two fields have significantly different objectives. This...
Provided by Institute of Electrical and Electronics Engineers
-
White Papers
Computing Two-Dimensional Delaunay Triangulation Using Graphics Hardware
Aug 2008
This paper presents a novel approach to compute, for a given point set S in R2, its Delaunay triangulation T (S). Though prior work mentions the possibility of using the Graphics Processing Unit...
Provided by Association for Computing Machinery
-
White Papers
Reviving a Tangible Interface Affording 3D Spatial Interaction
Jan 2011
Tangible interfaces offer natural means of human computer interaction and have already been shown to simplify existing computerized applications and offer solutions for tasks that were considered...
Provided by University of Alberta
-
White Papers
Visualization and the Larger World of Computer Graphics: What's Happening Out There?
Oct 2007
Visualization based on computer graphics and interactive techniques was formally defined 20 years ago in a landmark report sponsored by the National Science Foundation, "Visualization in...
Provided by North Carolina State University
-
White Papers
Engaging Viewers Through Nonphotorealistic Visualizations
May 2007
Research in human visual cognition suggests that beautiful images can engage the visual system, encouraging it to linger in certain locations in an image and absorb subtle details. By developing...
Provided by North Carolina State University
-
White Papers
An Efficient Algorithm for Co-Segmentation
Jul 2009
This paper is focused on the Co-segmentation problem - where the objective is to segment a similar object from a pair of images. The background in the two images may be arbitrary; therefore,...
Provided by University of Wisconsin
-
White Papers
A Parallel Multigrid Poisson Solver for Fluids Simulation on Large Grids
May 2010
The authors present a highly efficient numerical solver for the Poisson equation on irregular voxelized domains supporting an arbitrary mix of Neumann and Dirichlet boundary conditions. The...
Provided by EUROGRAPHICS Association
-
White Papers
Graphical Models for Online Solutions to Interactive POMDPs
May 2007
The authorsdevelop a new graphical representation for Interactive Partially Observable Markov Decision Processes (I-POMDPs) that is significantly more transparent and semantically clear than the...
Provided by Association for Computing Machinery
-
White Papers
Toward a Multicore Architecture for Real-Time Ray-Tracing
Sep 2008
Significant improvement to visual quality for real-time 3D graphics requires modeling of complex illumination effects like soft-shadows, reflections, and diffuse lighting interactions. The...
Provided by University of Wisconsin
-
White Papers
A 200-Mbps 0.02-nJ/b Dual-Mode Inductive Coupling Transceiver for cm-Range Multimedia Application
May 2009
A 200-Mbps 0.02-nJ/b dual-mode inductive coupling transceiver is proposed for cm-range multimedia application. The inductive link geometry and the advantage of the pulse-based inductive coupling...
Provided by Institute of Electrical and Electronics Engineers
-
White Papers
A 195 MW, 9.1 MVertices/s Fully Programmable 3-D Graphics Processor for Low-Power Mobile Devices
Nov 2008
A 195 mW, 9.1 Mvertices/s fully programmable 3-D graphics processor is designed and implemented for mobile devices. The mobile unified shader provides programmable per-vertex operations and...
Provided by Institute of Electrical and Electronics Engineers
-
White Papers
A 195 MW/152 MW Mobile Multimedia SoC With Fully Programmable 3-D Graphics and MPEG4/H.264/JPEG
Sep 2008
In this paper, the authors present a low power multimedia SoC with fully programmable 3-D graphics, MPEG4 codec, H.264 decoder, and JPEG codec for mobile devices. The mobile unified shader in 3-D...
Provided by Institute of Electrical and Electronics Engineers
-
White Papers
Linear Spatial Pyramid Matching Using Sparse Coding for Image Classification
Apr 2009
In recent years the Bag-of-Features (BoF) model has been extremely popular in image categorization. The method treats an image as a collection of unordered appearance descriptors extracted from...
Provided by University of Illinois at Urbana-Champaign
-
White Papers
Multi-Label Sparse Coding for Automatic Image Annotation
Apr 2009
Automatic image annotation, whose goal is to automatically assign the images with the keywords, has been an active research topic owing to its great potentials in image retrieval and management...
Provided by National University of Singapore
-
White Papers
Support Vector Machines in Face Recognition With Occlusions
Mar 2009
Support Vector Machines (SVM) is one of the most useful techniques in classification problems. One clear example is face recognition. However, SVM cannot be applied when the feature vectors...
Provided by Ohio State University
-
White Papers
Observable Subspaces for 3D Human Motion Recovery
Jul 2009
The articulated body models used to represent human motion typically have many degrees of freedom, usually expressed as joint angles that are highly correlated. The true range of motion can...
Provided by UC Regents
-
White Papers
Blind Motion Deblurring From a Single Image Using Sparse Approximation
Mar 2010
Restoring a clear image from a single motion-blurred image due to camera shake has long been one challenging problem in digital imaging. Existing blind deblurring techniques either only can remove...
Provided by National University of Singapore
-
White Papers
Piecewise Planar City 3D Modeling From Street View Panoramic Sequences
Apr 2009
City environments often lack textured areas, contain repetitive structures, strong lighting changes and therefore are very difficult for standard 3D modeling pipelines. The authors present a novel...
Provided by George Mason University
-
White Papers
Learning Real-Time MRF Inference for Image Denoising
Mar 2009
Many computer vision problems can be formulated in a Bayesian framework with Markov Random Field (MRF) or Conditional Random Field (CRF) priors. Usually, the model assumes that a full Maximum A...
Provided by Florida State University
-
White Papers
Human Motion Synthesis From 3D Video
Mar 2009
Multiple view 3D video reconstruction of actor performance captures a level-of-detail for body and clothing movement which is time-consuming to produce using existing animation tools. In this...
Provided by University of Surrey
-
White Papers
Active Volume Models for 3D Medical Image Segmentation
Apr 2009
In this paper, the authors propose a novel predictive model for object boundary, which can integrate information from any sources. The model is a dynamic "Object" model whose manifestation...
Provided by Lehigh University
-
White Papers
Boosted Multi-Task Learning for Face Verification With Applications to Web Image and Video Search
Mar 2009
Face verification has many potential applications including filtering and ranking image/video search results on celebrities. Since these images/videos are taken under uncontrolled environments,...
Provided by Microsoft Research
-
White Papers
Building a Database of 3D Scenes From User Annotations
Apr 2009
In this paper, the authors wish to build a high quality database of images depicting scenes, along with their real-world Three-Dimensional (3D) coordinates. Such a database is useful for a variety...
Provided by INRIA
-
White Papers
A Robust Approach for Automatic Registration of Aerial Images With Untextured Aerial LiDAR Data
Apr 2009
Airborne LiDAR technology draws increasing interest in large-scale 3D urban modeling in recent years. 3D Li-DAR data typically has no texture information. To generate photo-realistic 3D models,...
Provided by University of Southern California
-
White Papers
A Local Image Reconstruction Algorithm for Stochastic Rendering
Feb 2011
Stochastic renderers produce unbiased but noisy images of scenes that include the advanced camera effects of motion and defocus blur and possibly other effects such as transparency. The authors...
Provided by Association for Computing Machinery
-
White Papers
The Light-Path Less Traveled
Apr 2011
This paper extends classical object pose and relative camera motion estimation algorithms for imaging sensors sampling the scene through light-paths. Many algorithms in multi-view geometry assume...
Provided by Mitsubishi Electric Research Laboratories
-
White Papers
Unsupervised Auxiliary Visual Words Discovery for Large-Scale Image Object
Feb 2011
Image object retrieval - locating image occurrences of specific objects in large-scale image collections - is essential for manipulating the sheer amount of photos. Current solutions, mostly based...
Provided by National Taiwan University
-
White Papers
Real-Time Human Pose Recognition in Parts From Single Depth Images
Mar 2011
The authors propose a new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. They take an object recognition approach,...
Provided by Microsoft Research
-
White Papers
Sparsity-Based Image Denoising Via Dictionary Learning and Structural Clustering
Feb 2011
Where does the sparsity in image signals come from? Local and nonlocal image models have supplied complementary views toward the regularity in natural images - the former attempts to construct or...
Provided by Xidian University
-
White Papers
What Makes a Chair a Chair?
Apr 2011
Many object classes are primarily defined by their functions. However, this fact has been left largely unexploited by visual object categorization or detection systems. The authors propose a...
Provided by ETH Zurich
-
White Papers
Recognizing Human Actions by Attributes
Apr 2011
In this paper, the authors explore the idea of using high-level se-mantic concepts, also called attributes, to represent human actions from videos and argue that attributes enable the construction...
Provided by University of Michigan
-
White Papers
Learning Better Image Representations Using 'Flobject Analysis'
May 2011
Unsupervised learning can be used to extract image representations that are useful for various and diverse vision tasks. After noticing that most biological vision systems for interpreting static...
Provided by University of Toronto
-
White Papers
Sparse Image Representation With Epitomes
Apr 2011
Sparse coding, which is the decomposition of a vector using only a few basis elements, is widely used in machine learning and image processing. The basis set, also called dictionary, is learned to...
Provided by INRIA
-
White Papers
Unsupervised Local Color Correction for Coarsely Registered Images
Mar 2011
The current paper proposes a new parametric local color correction technique. Initially, several color transfer functions are computed from the output of the mean shift color segmentation...
Provided by University of Aveiro
-
White Papers
A Multichannel Edge-Weighted Centroidal Voronoi Tessellation Algorithm for 3D Super-Alloy Image Segmentation
Mar 2011
In material science and engineering, the grain structure inside a super-alloy sample determines its mechanical and physical properties. In this paper, the authors develop a new MultiChannel...
Provided by Wuhan University
-
White Papers
A Generative Model for 3D Urban Scene Understanding From Movable Platforms
Apr 2011
3D scene understanding is key for the success of applications such as autonomous driving and robot navigation. However, existing approaches produce a mild level of understanding, e.g.,...
Provided by Karlsruhe Institute of Technology (KIT)
-
White Papers
Are Sparse Representations Really Relevant for Image Classification?
Mar 2011
Recent years have seen an increasing interest in sparse representations for image classification and object recognition, probably motivated by evidence from the analysis of the primate visual...
Provided by Ecole Polytechnique Federale de Lausanne
-
White Papers
Image Ranking and Retrieval Based on Multi-Attribute Queries
Mar 2011
The authors propose a novel approach for ranking and retrieval of images based on multi-attribute queries. Existing image retrieval methods train separate classifiers for each word and...
Provided by University of Maryland
-
White Papers
Importance Filtering for Image Retargeting
Apr 2011
Content-aware image retargeting has attracted a lot of interests recently. The key and most challenging issue for this task is how to balance the tradeoff between preserving the important contents...
Provided by University of Delaware
-
White Papers
Learning Structured Prediction Models for Interactive Image Labeling
May 2011
The authors propose structured models for image labeling that take into account the dependencies among the image labels explicitly. These models are more expressive than independent label...
Provided by INRIA
-
White Papers
Distributed Message Passing for Large Scale Graphical Models
Jun 2011
In this paper, the authors propose a distributed message-passing algorithm for inference in large scale graphical models. Their method can handle large problems efficiently by distributing and...
Provided by ETH Zurich
-
White Papers
Learning Non-Local Range Markov Random Field for Image Restoration
Mar 2011
In this paper, the authors design a novel MRF framework which is called Non-Local Range Markov Random Field (NLRMRF). The local spatial range of clique in traditional MRF is extended to the...
Provided by University of Central Florida
-
White Papers
Local Isomorphism to Solve the Pre-Image Problem in Kernel Methods
Apr 2011
Kernel methods have been popular over the last decade to solve many computer vision, statistics and machine learning problems. An important, both theoretically and practically, open problem in...
Provided by Carnegie Mellon University
-
White Papers
Simulating Human Saccadic Scanpaths on Natural Images
Apr 2011
Human saccade is a dynamic process of information pursuit. Based on the principle of information maximization, the authors propose a computational model to simulate human saccadic scanpaths on...
Provided by Peking University
-
White Papers
On Deep Generative Models With Applications to Recognition
Apr 2011
The most popular way to use probabilistic models in vision is first to extract some descriptors of small image patches or object parts using well-engineered features, and then to use statistical...
Provided by University of Toronto
-
White Papers
Object Stereo- Joint Stereo Matching and Object Segmentation
Apr 2011
This paper presents a method for joint stereo matching and object segmentation. In the authors' approach a 3D scene is represented as a collection of visually distinct and spatially coherent...
Provided by Vienna University of Technology
-
White Papers
3D Motion Reconstruction for Real-World Camera Motion
Apr 2011
This paper addresses the problem of 3D motion reconstruction from a series of 2D projections under low reconstructibility. Reconstructibility defines the accuracy of a 3D reconstruction from 2D...
Provided by University of Queensland
-
White Papers
A General Method for the Point of Regard Estimation in 3D Space
Feb 2011
A novel approach to 3D gaze estimation for wearable multi-camera devices is proposed and its effectiveness is demonstrated both theoretically and empirically. The proposed approach, firmly...
Provided by Sapienza Università di Roma
-
White Papers
Joint Face Alignment With a Generic Deformable Face Model
Apr 2011
As having multiple images of an object is practically convenient nowadays, to jointly align them is important for subsequent studies and a wide range of applications. In this paper, the authors...
Provided by Chinese University of Hong Kong
