Sciweavers

171 search results - page 28 / 35
» A Boosting Approach to Multiple Instance Learning
Sort
View
AAAI
2008
13 years 10 months ago
Multimodal People Detection and Tracking in Crowded Scenes
This paper presents a novel people detection and tracking method based on a multi-modal sensor fusion approach that utilizes 2D laser range and camera data. The data points in the...
Luciano Spinello, Rudolph Triebel, Roland Siegwart
CVPR
2008
IEEE
13 years 9 months ago
Optimizing discrimination-efficiency tradeoff in integrating heterogeneous local features for object detection
A large variety of image features has been invented for detection of objects of a known class. We propose a framework to optimize the discrimination-efficiency tradeoff in integra...
Bo Wu, Ram Nevatia
PRIB
2010
Springer
242views Bioinformatics» more  PRIB 2010»
13 years 6 months ago
Consensus of Ambiguity: Theory and Application of Active Learning for Biomedical Image Analysis
Abstract. Supervised classifiers require manually labeled training samples to classify unlabeled objects. Active Learning (AL) can be used to selectively label only “ambiguous...
Scott Doyle, Anant Madabhushi
ILP
1998
Springer
13 years 12 months ago
Learning Structurally Indeterminate Clauses
This paper describes a new kind of language bias, S-structural indeterminate clauses, which takes into account the meaning of predicates that play a key role in the complexity of l...
Jean-Daniel Zucker, Jean-Gabriel Ganascia
CVPR
2008
IEEE
14 years 9 months ago
Decomposition, discovery and detection of visual categories using topic models
We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...
Mario Fritz, Bernt Schiele