Sciweavers

61 search results - page 6 / 13
» Subset Selection for Active Object Recognition
Sort
View
ICASSP
2009
IEEE
14 years 29 days ago
Maximizing global entropy reduction for active learning in speech recognition
We propose a new active learning algorithm to address the problem of selecting a limited subset of utterances for transcribing from a large amount of unlabeled utterances so that ...
Balakrishnan Varadarajan, Dong Yu, Li Deng, Alex A...
ICRA
2009
IEEE
174views Robotics» more  ICRA 2009»
14 years 27 days ago
Environment adapted active multi-focal vision system for object detection
— A biologically inspired foveated attention system in an object detection scenario is proposed. Thereby, a highperformance active multi-focal camera system imitates visual behav...
Tingting Xu, Hao Wu, Tianguang Zhang, Kolja Kü...
CSL
2010
Springer
13 years 6 months ago
Active learning and semi-supervised learning for speech recognition: A unified framework using the global entropy reduction maxi
We propose a unified global entropy reduction maximization (GERM) framework for active learning and semi-supervised learning for speech recognition. Active learning aims to select...
Dong Yu, Balakrishnan Varadarajan, Li Deng, Alex A...
PAMI
2011
13 years 1 months ago
Eye Movement Analysis for Activity Recognition Using Electrooculography
—In this work, we investigate eye movement analysis as a new sensing modality for activity recognition. Eye movement data were recorded using an electrooculography (EOG) system. ...
Andreas Bulling, Jamie A. Ward, Hans Gellersen, Ge...
DAGM
2009
Springer
14 years 24 days ago
Active Structured Learning for High-Speed Object Detection
High-speed smooth and accurate visual tracking of objects in arbitrary, unstructured environments is essential for robotics and human motion analysis. However, building a system th...
Christoph H. Lampert, Jan Peters