Sciweavers

ICCV
2011
IEEE
12 years 8 months ago
Modeling Temporal Coherence for Optical Flow
Despite the fact that temporal coherence is undeniably one of the key aspects when processing video data, this concept has hardly been exploited in recent optical flow methods. I...
Sebastian Volz, Andres Bruhn, Levi Valgaerts, Henn...
ICCV
2011
IEEE
12 years 8 months ago
Probabilistic Group-Level Motion Analysis and Scenario Recognition
This paper addresses the challenge of recognizing behavior of groups of individuals in unconstraint surveillance environments. As opposed to approaches that rely on agglomerative ...
Ming-Ching Chang, Nils Krahnstoever, Weina Ge
ICCV
2011
IEEE
12 years 8 months ago
Automatic Construction of an Action Video Shot Database using Web Videos
There are a huge number of videos with text tags on the Web nowadays. In this paper, we propose a method of automatically extracting from Web videos video shots corresponding to s...
Do Hang Nga, Keiji Yanai
ICCV
2011
IEEE
12 years 8 months ago
What Characterizes a Shadow Boundary under the Sun and Sky?
Despite decades of study, robust shadow detection remains difficult, especially within a single color image. We describe a new approach to detect shadow boundaries in images of o...
Xiang Huang, Gang Hua, Jack Tumblin, Lance William...
ICCV
2011
IEEE
12 years 8 months ago
Center-surround Divergence of Feature Statistics for Salient Object Detection
In this paper, we introduce a new method to detect salient objects in images. The approach is based on the standard structure of cognitive visual attention models, but realizes th...
Dominik A. Klein, Simone Frintrop
ICCV
2011
IEEE
12 years 8 months ago
Simultaneous Multi-Body Stereo and Segmentation
This paper presents a novel multi-body multi-view stereo method to simultaneously recover dense depth maps and perform segmentation with the input of a monocular image sequence. U...
Guofeng Zhang, Jiaya Jia, Hujun Bao
ICCV
2011
IEEE
12 years 8 months ago
Automatic Salient Object Extraction with Contextual Cue
We present a method for automatically extracting salient object from a single image, which is cast in an energy minimization framework. Unlike most previous methods that only leve...
Le Wang, IAIR, XJTU, Jianru Xue, Nanning Zheng, Ga...
ICCV
2011
IEEE
12 years 8 months ago
Manhattan Scene Understanding Using Monocular, Stereo, and 3D Features
This paper addresses scene understanding in the context of a moving camera, integrating semantic reasoning ideas from monocular vision with 3D information available through struct...
Alex Flint, David Murray, Ian Reid
ICCV
2011
IEEE
12 years 8 months ago
Realtime Multibody Visual SLAM with a Smoothly Moving Monocular Camera
This paper presents a realtime, incremental multibody visual SLAM system that allows choosing between full 3D reconstruction or simply tracking of the moving objects. Motion recon...
Abhijit Kundu, Madhava Krishna, C. V. Jawahar
ICCV
2011
IEEE
12 years 8 months ago
Self-Calibrating Depth from Refraction
In this paper, we introduce a novel method for depth acquisition based on refraction of light. A scene is captured twice by a fixed perspective camera, with the first image capt...
Zhihu Chen, Kwan-Yee Wong, Yasuyuki Matsushita, Xi...