Abstract: Dance videos are interesting and semantics-intensive. At the same time, they are the complex type of
videos compared to all other types such as sports, news and movie videos. In fact, dance video is the one which
is less explored by the researchers across the globe. Dance videos exhibit rich semantics such as macro features
and micro features and can be classified into several types. Hence, the conceptual modeling of the expressive
semantics of the dance videos is very crucial and complex. This paper presents a generic Dance Video
Semantics Model (DVSM) in order to represent the semantics of the dance videos at different granularity levels,
identified by the components of the accompanying song. This model incorporates both syntactic and semantic
features of the videos and introduces a new entity type called, Agent, to specify the micro features of the dance
videos. The instantiations of the model are expressed as graphs. The model is implemented as a tool using J2SE
and JMF to annotate the macro and micro features of the dance videos. Finally examples and evaluation results
are provided to depict the effectiveness of the proposed dance video model.
ACM Classification: J.5 Arts and Humanities: Performing Arts; H.5.4 Information Interface and Presentation:
Keywords: Agents, Dance videos, Macro features, Micro features, Video annotation, Video semantics.
MODELING AND ANNOTATING THE EXPRESSIVE SEMANTICS OF DANCE VIDEOS
Balakrishnan Ramadoss, Kannan Rajkumar