Sciweavers

2025 search results - page 346 / 405
» Minimal-Cut Model Composition
Sort
View
ECCV
2008
Springer
15 years 11 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
15 years 11 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
15 years 11 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
15 years 11 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
15 years 10 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