Sciweavers

2903 search results - page 295 / 581
» The Dark Side of Object Learning: Learning Objects
Sort
View
192
Voted

Publication
200views
13 years 11 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
CVPR
2009
IEEE
16 years 11 months ago
Learning Invariant Features Through Topographic Filter Maps
Several recently-proposed architectures for highperformance object recognition are composed of two main stages: a feature extraction stage that extracts locallyinvariant feature...
Koray Kavukcuoglu, Marc'Aurelio Ranzato, Rob Fergu...
ICCV
2003
IEEE
16 years 6 months ago
Automatically Labeling Video Data Using Multi-class Active Learning
Labeling video data is an essential prerequisite for many vision applications that depend on training data, such as visual information retrieval, object recognition, and human act...
Rong Yan, Jie Yang, Alexander G. Hauptmann
ICML
2004
IEEE
16 years 4 months ago
Learning random walk models for inducing word dependency distributions
Many NLP tasks rely on accurately estimating word dependency probabilities P(w1|w2), where the words w1 and w2 have a particular relationship (such as verb-object). Because of the...
Kristina Toutanova, Christopher D. Manning, Andrew...
WWW
2009
ACM
16 years 4 months ago
Learning to tag
Social tagging provides valuable and crucial information for large-scale web image retrieval. It is ontology-free and easy to obtain; however, irrelevant tags frequently appear, a...
Lei Wu, Linjun Yang, Nenghai Yu, Xian-Sheng Hua