Sciweavers

391 search results - page 35 / 79
» Graph based multi-modality learning
Sort
View
ICRA
2010
IEEE
170views Robotics» more  ICRA 2010»
13 years 6 months ago
Categorizing object-action relations from semantic scene graphs
— In this work we introduce a novel approach for detecting spatiotemporal object-action relations, leading to both, action recognition and object categorization. Semantic scene g...
Eren Erdal Aksoy, Alexey Abramov, Florentin Wö...
MIR
2006
ACM
223views Multimedia» more  MIR 2006»
14 years 1 months ago
Adaptive image retrieval using a Graph model for semantic feature integration
The variety of features available to represent multimedia data constitutes a rich pool of information. However, the plethora of data poses a challenge in terms of feature selectio...
Jana Urban, Joemon M. Jose
LREC
2010
197views Education» more  LREC 2010»
13 years 9 months ago
Automatic Annotation of Co-Occurrence Relations
We introduce a method for automatically labelling edges of word co-occurrence graphs with semantic relations. Therefore we only make use of training data already contained within ...
Dirk Goldhahn, Uwe Quasthoff
ICCV
2009
IEEE
15 years 18 days ago
Domain Adaptive Semantic Diffusion for Large Scale Context-Based Video Annotation
Learning to cope with domain change has been known as a challenging problem in many real-world applications. This paper proposes a novel and efficient approach, named domain ada...
Yu-Gang Jiang, Jun Wang, Shih-Fu Chang, Chong-Wah ...
CIKM
2011
Springer
12 years 7 months ago
Semi-supervised multi-task learning of structured prediction models for web information extraction
Extracting information from web pages is an important problem; it has several applications such as providing improved search results and construction of databases to serve user qu...
Paramveer S. Dhillon, Sundararajan Sellamanickam, ...