Sciweavers

ICPR
2010
IEEE
13 years 12 months ago
Quasi-Dense Wide Baseline Matching for Three Views
This paper proposes a method for computing a quasi-dense set of matching points between three views of a scene. The method takes a sparse set of seed matches between pairs of view...
Pekka Koskenkorva, Juho Kannala, Sami Sebastian Br...
ICPR
2010
IEEE
13 years 12 months ago
Cluster-Pairwise Discriminant Analysis
Pattern recognition problems often suffer from the larger intra-class variation due to situation variations such as pose, walking speed, and clothing variations in gait recognition...
Yasushi Makihara, Yasushi Yagi
ICPR
2010
IEEE
13 years 12 months ago
Arbitrary Stereoscopic View Generation Using Multiple Omnidirectional Image Sequences
Abstract--This paper proposes a novel method for generating arbitrary stereoscopic view from multiple omnidirectional image sequences. Although conventional methods for arbitrary v...
Maiya Hori, Masayuki Kanbara, Naokazu Yokoya
ACMACE
2009
ACM
13 years 12 months ago
Enhancing a motion capture interface by introducing context management
Nowadays, video games propose rich scenarios with movementsbased game play, through the manipulation of dedicated devices. The motivation of this study is the elaboration of a com...
Francois Picard, Pascal Estraillier
ACIVS
2009
Springer
13 years 12 months ago
Unsupervised Detection of Gradual Video Shot Changes with Motion-Based False Alarm Removal
The temporal segmentation of a video into shots is a fundamental prerequisite for video retrieval. There are two types of shot boundaries: abrupt shot changes (“cuts”) and grad...
Ralph Ewerth, Bernd Freisleben
ECCV
2010
Springer
13 years 12 months ago
Disparity statistics for pedestrian detection: Combining appearance, motion, and stereo
Pedestrian detection is an important problem in computer vision due to its importance for applications such as visual surveillance, robotics, and automotive safety. This paper push...
ECCV
2010
Springer
13 years 12 months ago
Exploring Ambiguities for Monocular Non-Rigid Shape Estimation
Recovering the 3D shape of deformable surfaces from single images is difficult because many different shapes have very similar projections. This is commonly addressed by restricti...
ECCV
2010
Springer
13 years 12 months ago
What does classifying more than 10,000 image categories tell us?
Image classification is a critical task for both humans and computers. One of the challenges lies in the large scale of the semantic space. In particular, humans can recognize tens...
ECCV
2010
Springer
13 years 12 months ago
Descattering Transmission via Angular Filtering
Abstract. We describe a single-shot method to differentiate unscattered and scattered components of light transmission through a heterogeneous translucent material. Directly-transm...