Large-scale dynamic relational data visualization has attracted considerable research attention recently. We introduce dynamic data visualization into the multimedia domain, and present an interactive and scalable sys...Large-scale dynamic relational data visualization has attracted considerable research attention recently. We introduce dynamic data visualization into the multimedia domain, and present an interactive and scalable system, Video Map, for exploring large-scale video content. A long video or movie has much content; the associations between the content are complicated. Video Map uses new visual representations to extract meaningful information from video content. Map-based visualization naturally and easily summarizes and reveals important features and events in video. Multi-scale descriptions are used to describe the layout and distribution of temporal information, spatial information, and associations between video content. Firstly, semantic associations are used in which map elements correspond to video contents. Secondly, video contents are visualized hierarchically from a large scale to a fine-detailed scale. Video Map uses a small set of sketch gestures to invoke analysis, and automatically completes charts by synthesizing visual representations from the map and binding them to the underlying data. Furthermore,Video Map allows users to use gestures to move and resize the view, as when using a map, facilitating interactive exploration. Our experimental evaluation of Video Map demonstrates how the system can assist in exploring video content as well as significantly reducing browsing time when trying to understand and find events of interest.展开更多
基金supported by the National Natural Science Foundation of China (Project Nos. U1435220, 61232013)
文摘Large-scale dynamic relational data visualization has attracted considerable research attention recently. We introduce dynamic data visualization into the multimedia domain, and present an interactive and scalable system, Video Map, for exploring large-scale video content. A long video or movie has much content; the associations between the content are complicated. Video Map uses new visual representations to extract meaningful information from video content. Map-based visualization naturally and easily summarizes and reveals important features and events in video. Multi-scale descriptions are used to describe the layout and distribution of temporal information, spatial information, and associations between video content. Firstly, semantic associations are used in which map elements correspond to video contents. Secondly, video contents are visualized hierarchically from a large scale to a fine-detailed scale. Video Map uses a small set of sketch gestures to invoke analysis, and automatically completes charts by synthesizing visual representations from the map and binding them to the underlying data. Furthermore,Video Map allows users to use gestures to move and resize the view, as when using a map, facilitating interactive exploration. Our experimental evaluation of Video Map demonstrates how the system can assist in exploring video content as well as significantly reducing browsing time when trying to understand and find events of interest.
