Modeling visual concepts using supervised or unsupervised machine learning approaches are becoming increasing important for video semantic indexing, retrieval, and filtering appli...
For a social robot, the ability of learning tasks via human demonstration is very crucial. But most current approaches suffer from either the demanding of the huge amount of label...
Zhe Li, Sven Wachsmuth, Jannik Fritsch, Gerhard Sa...
Domain ontology has been used in many Semantic Web applications. However, few applications explore the use of ontology for personalized services. This paper proposes an ontology b...
This paper considers the problems of feature variation and concept uncertainty in typical learning-based video semantic classification schemes. We proposed a new online semantic c...
This paper explores the use of the homotopy method for training a semi-supervised Hidden Markov Model (HMM) used for sequence labeling. We provide a novel polynomial-time algorith...