Sciweavers

3449 search results - page 18 / 690
» A Framework for Multiple-Instance Learning
Sort
View
ICDM
2009
IEEE
112views Data Mining» more  ICDM 2009»
14 years 2 months ago
Spatio-temporal Multi-dimensional Relational Framework Trees
—The real world is composed of sets of objects that move and morph in both space and time. Useful concepts can be defined in terms of the complex interactions between the multi-...
Matthew Bodenhamer, Samuel Bleckley, Daniel Fennel...
MM
2006
ACM
152views Multimedia» more  MM 2006»
14 years 1 months ago
Multimodal fusion using learned text concepts for image categorization
Conventional image categorization techniques primarily rely on low-level visual cues. In this paper, we describe a multimodal fusion scheme which improves the image classification...
Qiang Zhu, Mei-Chen Yeh, Kwang-Ting Cheng
SDM
2010
SIAM
195views Data Mining» more  SDM 2010»
13 years 9 months ago
Adaptive Informative Sampling for Active Learning
Many approaches to active learning involve periodically training one classifier and choosing data points with the lowest confidence. An alternative approach is to periodically cho...
Zhenyu Lu, Xindong Wu, Josh Bongard
ECCV
2008
Springer
14 years 9 months ago
Weakly Supervised Object Localization with Stable Segmentations
Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
Carolina Galleguillos, Boris Babenko, Andrew Rabin...
ICCV
2009
IEEE
15 years 21 days ago
Action Detection in Complex Scenes with Spatial and Temporal Ambiguities
In this paper, we investigate the detection of semantic human actions in complex scenes. Unlike conventional action recognition in well-controlled environments, action detection...
Yuxiao Hu, Liangliang Cao, Fengjun Lv, Shuicheng Y...