Online multi-task learning for semantic concept detection in video

Foteini Markatopoulou, Vasileios Mezaris, Ioannis Patras

Abstract

In this paper we propose an online multi-task learning algorithm for video concept detection. In particular, we extend the Efficient Lifelong Learning Algorithm (ELLA) in the following ways: (a) we solve the objective function of ELLA using quadratic programming instead of solving the Lasso problem, (b) we add a new label-based constraint that considers concept correlations, (c) we use linear SVMs as base learners instead of logistic regression. Experimental results show improvement over both the single-task learning methods typically used in this problem and the original ELLA algorithm.
BibTeX
@inproceedings{markatopoulou2016online,
  author = {Foteini Markatopoulou and Vasileios Mezaris and Ioannis Patras},
  title = {{Online multi-task learning for semantic concept detection in video}},
  booktitle = {ICIP},
  year = {2016},
  doi = {10.1109/icip.2016.7532344},
}

Loading related content...

Figure