Sciweavers

ICCV
2009
IEEE
15 years 5 months ago
Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations
We address the classic problems of detection, segmenta- tion and pose estimation of people in images with a novel definition of a part, a poselet. We postulate two criteria (1) ...
Lubomir Bourdev, Jitendra Malik
ICCV
2009
IEEE
15 years 5 months ago
Time Series Prediction by Chaotic Modeling of Nonlinear Dynamical Systems
We use concepts from chaos theory in order to model nonlinear dynamical systems that exhibit deterministic behavior. Observed time series from such a system can be embedded into...
Arslan Basharat, Mubarak Shah
ICCV
2009
IEEE
15 years 5 months ago
Diagram Techniques for Multiple View Geometry
Multilinear algebra is a powerful theoretical tool for visual geometry, but widespread usage of traditional typographical notation often hides its conceptual elegance and simpli...
Alberto Ruiz, Pedro E. Lopez-de-Teruel
ICCV
2009
IEEE
15 years 5 months ago
Weakly supervised discriminative localization and classification: a joint learning process
Visual categorization problems, such as object classification or action recognition, are increasingly often approached using a detection strategy: a classifier function is first ...
Minh Hoai Nguyen, Lorenzo Torresani, Fernando de l...
ICCV
2009
IEEE
15 years 5 months ago
A Global Perspective on MAP Inference for Low-Level Vision
In recent years the Markov Random Field (MRF) has become the de facto probabilistic model for low-level vision applications. However, in a maximum a posteriori (MAP) framework, ...
Oliver J. Woodford, Carsten Rother, Vladimir Kolmo...
ICCV
2009
IEEE
15 years 5 months ago
The Dimensionality of Scene Appearance
Low-rank approximation of image collections (e.g., via PCA) is a popular tool in many areas of computer vision. Yet, surprisingly little is known justifying the observation that...
Rahul Garg, Hao Du, Steven M. Seitz, Noah Snavely
ICCV
2009
IEEE
15 years 5 months ago
Saliency Driven Total Variation Segmentation
This paper introduces an unsupervised color segmentation method. The underlying idea is to segment the input image several times, each time focussing on a different salient part...
Michael Donoser, Martin Urschler, Martin Hirzer an...
ICCV
2009
IEEE
15 years 5 months ago
Mode-Detection via Median-Shift
Median-shift is a mode seeking algorithm that relies on computing the median of local neighborhoods, instead of the mean. We further combine median-shift with Locality Sensitive...
Lior Shapira, Shai Avidan, Ariel Shamir
ICCV
2009
IEEE
6637views Computer Vision» more  ICCV 2009»
15 years 5 months ago
A Markov Clustering Topic Model for Mining Behaviour in Video
This paper addresses the problem of fully automated mining of public space video data. A novel Markov Clustering Topic Model (MCTM) is introduced which builds on existing Dynami...
Timothy Hospedales, Shaogang Gong, Tao Xiang
ICCV
2009
IEEE
15 years 5 months ago
Shape-based Recognition of 3D Point Clouds in Urban Environments
This paper investigates the design of a system for recognizing objects in 3D point clouds of urban environments. The system is decomposed into four steps: locating, segmenting, ...
Aleksey Golovinskiy, Vladimir G. Kim, Thomas Funkh...