摘要 |
Disclosed are an information processing device, a method of processing information, and a program whereby an annotation is easily applied to content and an application using the annotation can be provided. A learning device (312) extracts an image feature amount from each frame in an image of learning content, while extracting as a text feature amount of an explanatory text the word frequency information associated with the frequency of each word appearing in an explanatory text explaining the content of the image in the learning content, and learns an annotation model that is a multi-stream HMM by using the multi-stream including the image feature amount and the text feature amount. A browsing control device (314) extracts by using the annotation model from the target content a scene that is a gathering of one or more frames continuing time sequentially, and displays the representative image of the scene being arranged in time order. The present invention can be applied, for example, when an annotation is added to content. |