Sciweavers

CVPR
2009
IEEE
15 years 5 months ago
Learning Semantic Visual Vocabularies Using Diffusion Distance
In this paper, we propose a novel approach for learning generic visual vocabulary. We use diffusion maps to au-tomatically learn a semantic visual vocabulary from ab-undant quantiz...
Jingen Liu (University of Central Florida), Yang Y...
CVPR
2009
IEEE
15 years 5 months ago
View-Invariant Dynamic Texture Recognition using a Bag of Dynamical Systems
In this paper, we consider the problem of categorizing videos of dynamic textures under varying view-point. We propose to model each video with a collection of Linear Dynamics S...
Avinash Ravichandran, René Vidal, Rizwan Ch...
CVPR
2009
IEEE
3538views Computer Vision» more  CVPR 2009»
15 years 5 months ago
Markerless Motion Capture with Unsynchronized Moving Cameras
In this work we present an approach for markerless motion capture (MoCap) of articulated objects, which are recorded with multiple unsynchronized moving cameras. Instead of usin...
Bodo Rosenhahn, Hans-Peter Seidel, Juergen Gall, M...
CVPR
2009
IEEE
1351views Computer Vision» more  CVPR 2009»
15 years 5 months ago
Support Vector Machines in Face Recognition with Occlusions
Support Vector Machines (SVM) are one of the most useful techniques in classification problems. One clear example is face recognition. However, SVM cannot be applied when the fe...
Aleix M. Martínez, Hongjun Jia
CVPR
2009
IEEE
15 years 5 months ago
Efficient Planar Graph Cuts with Applications in Computer Vision
We present a fast graph cut algorithm for planar graphs. It is based on the graph theoretical work [2] and leads to an efficient method that we apply on shape matching and im- a...
Daniel Cremers, Eno Töppe, Frank R. Schmidt
CVPR
2009
IEEE
1599views Computer Vision» more  CVPR 2009»
15 years 5 months ago
Multi-Label Sparse Coding for Automatic Image Annotation
In this paper, we present a multi-label sparse coding framework for feature extraction and classification within the context of automatic image annotation. First, each image is ...
Changhu Wang (University of Science and Technology...
CVPR
2009
IEEE
15 years 5 months ago
Dense 3D Motion Capture for Human Faces
This paper proposes a novel approach to motion capture from multiple, synchronized video streams, specifically aimed at recording dense and accurate models of the structure and ...
Yasutaka Furukawa (University of Washington), Jean...
CVPR
2009
IEEE
15 years 5 months ago
Manhattan-world Stereo
Multi-view stereo (MVS) algorithms now produce reconstructions that rival laser range scanner accuracy. However, stereo algorithms require textured surfaces, and therefore work ...
Brian Curless, Richard Szeliski, Steven M. Seitz, ...
CVPR
2009
IEEE
15 years 5 months ago
Robust Multi-Class Transductive Learning with Graphs
Graph-based methods form a main category of semisupervised learning, offering flexibility and easy implementation in many applications. However, the performance of these methods...
Wei Liu (Columbia University), Shih-fu Chang (Colu...
CVPR
2009
IEEE
15 years 5 months ago
Learning General Optical Flow Subspaces for Egomotion Estimation and Detection of Motion Anomalies
This paper deals with estimation of dense optical flow and ego-motion in a generalized imaging system by exploiting probabilistic linear subspace constraints on the flow. We dea...
Richard Roberts (Georgia Institute of Technology),...