Sciweavers

163 search results - page 15 / 33
» Average-Case Active Learning with Costs
Sort
View

Publication
200views
12 years 3 months ago
Learning Tags from Unsegmented Videos of Multiple Human Actions
Providing methods to support semantic interaction with growing volumes of video data is an increasingly important challenge for data mining. To this end, there has been some succes...
Timothy Hospedales, Shaogang Gong, Tao Xiang
ECTEL
2006
Springer
13 years 11 months ago
Who Needs "Blended Learning"? Some Thoughts on a Political Concept
The paper covers the topic from an e-learning provider's perspective on the basis of practical experience and discussions with corporate and SME partners. In this paper the au...
Ray Mary Rosdale
ICRA
2005
IEEE
129views Robotics» more  ICRA 2005»
14 years 1 months ago
Fast Computational Methods for Visually Guided Robots
— This paper proposes numerical algorithms for reducing the computational cost of semi-supervised and active learning procedures for visually guided mobile robots from O(M3 ) to ...
Maryam Mahdaviani, Nando de Freitas, Bob Fraser, F...
ICASSP
2008
IEEE
14 years 1 months ago
Learning with noisy supervision for Spoken Language Understanding
Data-driven Spoken Language Understanding (SLU) systems need semantically annotated data which are expensive, time consuming and prone to human errors. Active learning has been su...
Christian Raymond, G. Riccardfi
LREC
2008
183views Education» more  LREC 2008»
13 years 9 months ago
Active Annotation in the LUNA Italian Corpus of Spontaneous Dialogues
In this paper we present an active approach to annotate with lexical and semantic labels an Italian corpus of conversational human-human and Wizard-of-Oz dialogues. This procedure...
Christian Raymond, Kepa Joseba Rodriguez, Giuseppe...