Web video categorization using category-predictive classifiers and category-specific concept classifiers

In this era, automatic Web video categorization has become an important multimedia task for organizing and retrieving the plentiful videos on the Web. Due to unbounded variation in both content and quality of Web videos and deficiency in precisely labeled training data, Web video categorization remains a challenging task. In this paper, a novel three-stage framework is proposed for Web video classification using category-predictive classifiers and category-specific concept classifiers, which integrates contextual features and concept-level semantics induced from visual content. First, a content-based category-predictive (CNC) classifier is trained for each category by exploiting visual features to classify Web videos. Second, the significance of concepts for categories is measured with category-specific concept (CSC) classifiers, and it is adopted to refine CNC classifiers at keyframe-level. Third, the context-based category-predictive (CXC) classifiers induced from titles and tags are further combined with the refined CNC classifiers to reinforce the performance. Experiments on two large scale Web video datasets, MCG-WEBV and CCV, demonstrate that the proposed approach achieves promising performance. Propose novel fusion of category and concept classifiers for web video classification.Exploit Flickr enriched context space for category relevant concept selection.Fuse content and context based category-predictive classifiers to enhance performance.