Sciweavers

ICCV
2011
IEEE
13 years 14 days ago
Active Geodesics: Region based Active Contour Segmentation with a Global Edge based Constraint
We present an active geodesic contour model in which we constrain the evolving active contour to be a geodesic with respect to a weighted edge-based energy through its entire evol...
Vikram Appia, Anthony Yezzi
ICCV
2011
IEEE
13 years 14 days ago
A Convex Framework for Image Segmentation with Moment Constraints
Convex relaxation techniques have become a popular approach to image segmentation as they allow to compute solutions independent of initialization to a variety of image segmentati...
Maria Klodt, Daniel Cremers
ICCV
2011
IEEE
13 years 14 days ago
Image Segmentation by Figure-Ground Composition into Maximal Cliques
We propose a mid-level statistical model for image segmentation that composes multiple figure-ground hypotheses (FG) obtained by applying constraints at different locations and s...
Adrian Ion, Joao Carreira, Cristian Sminchisescu
ICCV
2011
IEEE
13 years 14 days ago
Generalized Roof Duality for Pseudo-Boolean Optimization
The number of applications in computer vision that model higher-order interactions has exploded over the last few years. The standard technique for solving such problems is to red...
Fredrik Kahl, Petter Strandmark
ICCV
2011
IEEE
13 years 14 days ago
Tight Convex Relaxations for Vector-Valued Labeling Problems
The multi-label problem is of fundamental importance to computer vision, yet finding global minima of the associated energies is very hard and usually impossible in practice. Rec...
Evgeny Strekalovskiy, Bastian Goldluecke, Daniel C...
ICCV
2011
IEEE
13 years 14 days ago
Conditional Random Fields for Multi-Camera Object Detection
We formulate a model for multi-class object detection in a multi-camera environment. From our knowledge, this is the first time that this problem is addressed taken into account ...
Xavier Boix, Gemma Roig, Horesh Ben Shitrit, Pasca...
ICCV
2011
IEEE
13 years 14 days ago
Annotator Rationales for Visual Recognition
Traditional supervised visual learning simply asks annotators “what” label an image should have. We propose an approach for image classification problems requiring subjective...
Jeff Donahue, Kristen Grauman
ICCV
2011
IEEE
13 years 14 days ago
Evaluation of Image Features Using a Photorealistic Virtual World
Image features are widely used in computer vision applications. They need to be robust to scene changes and image transformations. Designing and comparing feature descriptors requ...
Biliana Kaneva, Antonio Torralba, Bill Freeman
ICCV
2011
IEEE
13 years 14 days ago
In Defense of Soft-assignment Coding
In object recognition, soft-assignment coding enjoys computational efficiency and conceptual simplicity. However, its classification performance is inferior to the newly develop...
Lingqiao Liu, Lei Wang, Xinwang Liu
ICCV
2011
IEEE
13 years 14 days ago
Learning a Category Independent Object Detection Cascade
Cascades are a popular framework to speed up object detection systems. Here we focus on the first layers of a category independent object detection cascade in which we sample a l...
Esa Rahtu, Juho Kannala, Matthew Blaschko