Sciweavers

2025 search results - page 346 / 405
» Minimal-Cut Model Composition
Sort
View
ECCV
2008
Springer
14 years 9 months ago
What Is a Good Image Segment? A Unified Approach to Segment Extraction
Abstract. There is a huge diversity of definitions of "visually meaningful" image segments, ranging from simple uniformly colored segments, textured segments, through sym...
Shai Bagon, Oren Boiman, Michal Irani
ECCV
2006
Springer
14 years 9 months ago
Background Cut
Abstract. In this paper, we introduce background cut, a high quality and realtime foreground layer extraction algorithm. From a single video sequence with a moving foreground objec...
Jian Sun, Weiwei Zhang, Xiaoou Tang, Heung-Yeung S...
ICIP
2008
IEEE
14 years 9 months ago
Learning action dictionaries from video
Summarizing the contents of a video containing human activities is an important problem in computer vision and has important applications in automated surveillance systems. Summar...
Pavan K. Turaga, Rama Chellappa
ICIP
1998
IEEE
14 years 9 months ago
Semantic Visual Templates: Linking Visual Features to Semantics
The rapid growth of visual data over the last few years has lead to many schemes for retrieving such data. With content-based systems today, there exists a significant gap between...
Shih-Fu Chang, William Chen, Hari Sundaram
ICML
2008
IEEE
14 years 8 months ago
Adaptive p-posterior mixture-model kernels for multiple instance learning
In multiple instance learning (MIL), how the instances determine the bag-labels is an essential issue, both algorithmically and intrinsically. In this paper, we show that the mech...
Hua-Yan Wang, Qiang Yang, Hongbin Zha