Sciweavers

391 search results - page 35 / 79
» Graph based multi-modality learning
Sort
View
ICRA
2010
IEEE
170views Robotics» more  ICRA 2010»
14 years 8 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»
15 years 3 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»
14 years 11 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
16 years 2 months 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
13 years 10 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, ...