Concept-oriented video skimming and adaptation via semantic classification

Abstract

Concept-oriented video skimming and adaptation plays an important role in enabling online medical education by selecting and transmitting the suitable medical video clips to the students over network. In this paper, we propose a novel framework to enable concept-oriented video skimming and adaptation in a specific domain of medical education video. Specifically, this framework includes: (a) A novel semantic-sensitive framework for video content characterization and representation by using principal video shots to enhance the quality of features on discriminating between different semantic video concepts. (b) A novel technique for semantic medical concept interpretation by using finite mixture models to approximate the class distributions of the relevant principal video shots. (c) A novel classifier training scheme by using an adaptive Expectation-Maximization (EM) algorithm for automatic parameter estimation and model selection (i.e., selecting the optimal number of mixture Gaussian components). (d) Subjective driven concept-oriented video skimming algorithm via semantic video classification