Sciweavers

843 search results - page 58 / 169
» Learning aspect models with partially labeled data
Sort
View
TIP
2010
155views more  TIP 2010»
15 years 2 months ago
Laplacian Regularized D-Optimal Design for Active Learning and Its Application to Image Retrieval
—In increasingly many cases of interest in computer vision and pattern recognition, one is often confronted with the situation where data size is very large. Usually, the labels ...
Xiaofei He
ICMCS
2009
IEEE
97views Multimedia» more  ICMCS 2009»
15 years 1 months ago
Some new directions in graph-based semi-supervised learning
In this position paper, we first review the state-of-the-art in graph-based semi-supervised learning, and point out three limitations that are particularly relevant to multimedia ...
Xiaojin Zhu, Andrew B. Goldberg, Tushar Khot
ECCV
2006
Springer
16 years 6 months ago
Learning and Incorporating Top-Down Cues in Image Segmentation
Abstract. Bottom-up approaches, which rely mainly on continuity principles, are often insufficient to form accurate segments in natural images. In order to improve performance, rec...
Xuming He, Richard S. Zemel, Debajyoti Ray
CVPR
2010
IEEE
16 years 13 days ago
Nonparametric Higher-Order Learning for Interactive Segmentation
In this paper, we deal with a generative model for multi-label, interactive segmentation. To estimate the pixel likelihoods for each label, we propose a new higher-order formulatio...
Tae Hoon Kim (Seoul National University), Kyoung M...
ECCV
2010
Springer
15 years 7 months ago
Automatic Learning of Background Semantics in Generic Surveilled Scenes
Advanced surveillance systems for behavior recognition in outdoor traffic scenes depend strongly on the particular configuration of the scenario. Scene-independent trajectory analy...
Carles Fernández, Jordi Gonzàlez, Xavier Roca