Active Learning Based Semantic Video Retrieval Using Single Graph

Main Article Content

M. Ravinder
Dr.T.Venu Gopal


A multimedia record has grown-up significantly over the last few years. Active learning and semi-supervised learning are significant
machine learning techniques when labeled data is limited or costly to obtain. As an option of passively taking the training samples provided by
the users, a model could be designed to actively seek the majority informative samples for training. We take up a graph based framework with
semi-supervised learning method where each video shot is represented by a node in the graph and they are connected with edges weighted by
their similarities. We apply active learning methods to select the most informative samples according to the graph structure and the current state
of learning model.



Keywords-video indexing ; retrieval ; learning algorithm; single graph


Download data is not yet available.

Article Details