Integration of Visual Temporal and Textual Distribution Information for News Video Mining

News web videos exhibit several characteristics, including a limited number of features, noisy text information, and error in near-duplicate key frames (NDK) detection. In this paper, a novel framework is proposed to better group the associated web videos to events. First, the data preprocessing stage performs feature selection and tag relevance learning. Next, multiple correspondence analysis is applied to explore the correlations between terms and events with the assistance of visual information. Finally, a probabilistic model is proposed for news web video event mining, where both visual temporal information and textual distribution information are integrated. . Co-occurrence and visual near duplicate feature trajectory induced from NDKs are combined to calculate the similarity between NDKs and events. It is needed urgently the advanced technologies for organizing, analyzing, representing, indexing, filtering, retrieving and mining the vast amount of videos to retrieve specific information based on video content effectively, and to provide better ways for entertainment and multimedia applications.