Sciweavers

CVPR
2010
IEEE
13 years 6 months ago
Image restoration and disparity estimation from an uncalibrated multi-layered image
Watching a reflection in a glass window, one can often observe a multi-layered image consisting of a frontsurface reflection from the glass and a rear-surface reflection through t...
Takahiro Yano, Masao Shimizu, Masatoshi Okutomi
CVPR
2010
IEEE
13 years 6 months ago
Growing semantically meaningful models for visual SLAM
Though modern Visual Simultaneous Localisation and Mapping (vSLAM) systems are capable of localising robustly and efficiently even in the case of a monocular camera, the maps prod...
Alexander Flint, Christopher Mei, Ian D. Reid, Dav...
BMVC
2010
13 years 6 months ago
StyP-Boost: A Bilinear Boosting Algorithm for Learning Style-Parameterized Classifiers
We introduce a novel bilinear boosting algorithm, which extends the multi-class boosting framework of JointBoost to optimize a bilinear objective function. This allows style param...
Jonathan Warrell, Philip H. S. Torr, Simon Prince
BMVC
2010
13 years 6 months ago
Improving bag-of-features action recognition with non-local cues
Local space-time features have recently shown promising results within Bag-of-Features (BoF) approach to action recognition in video. Pure local features and descriptors, however,...
Muhammad Muneeb Ullah, Sobhan Naderi Parizi, Ivan ...
APWCS
2010
13 years 6 months ago
A Survey on the Development of Multi-touch Technology
Although multi-touch technology is currently a research focus in the field of Human-Computer Interaction, its relative research, however, is still comparatively few in China. In th...
Rong Chang, Feng Wang, Pengfei You
ACIVS
2010
Springer
13 years 6 months ago
Watershed Based Document Image Analysis
Document image analysis is used to segment and classify regions of a document image into categories such as text, graphic and background. In this paper we first review existing doc...
Pasha Shadkami, Nicolas Bonnier
CVPR
2011
IEEE
13 years 6 months ago
Where's Waldo: Matching People in Images of Crowds
Given a community-contributed set of photos of a crowded public event, this paper addresses the problem of finding all images of each person in the scene. This problem is very ch...
Rahul Garg, Deva Ramanan, Steve Seitz, Noah Snavel...
CVPR
2011
IEEE
13 years 6 months ago
Distributed Message Passing for Large Scale Graphical Models
In this paper we propose a distributed message-passing algorithm for inference in large scale graphical models. Our method can handle large problems efficiently by distributing a...
Alexander Schwing, Hazan Tamir, Marc Pollefeys, Ra...
ACIVS
2009
Springer
13 years 6 months ago
Enhanced Low-Resolution Pruning for Fast Full-Search Template Matching
Abstract. Gharavi-Alkhansari [1] proposed a full-search equivalent algorithm for speeding-up template matching based on Lp-norm distance measures. This algorithm performs a pruning...
Stefano Mattoccia, Federico Tombari, Luigi di Stef...
CVPR
2011
IEEE
13 years 6 months ago
Dynamic Batch Mode Active Learning
Active learning techniques have gained popularity in reducing human effort to annotate data instances for inducing a classifier. When faced with large quantities of unlabeled dat...
Shayok Chakraborty, Vineeth Balasubramanian, Sethu...