Automatic Semantic Analysis of Television News Captions
نویسندگان
چکیده
Automatic indexing to image data is in strong demand. Utilizing accompanying natural language information is considered e ective to accomplish the task. As a basis for semantic indexing, we propose an automatic television caption semantic analysis method, which analyzes semantic attributes of Japanese television news captions referring to su xes. This is a basic pre-process required to enable advanced indexing, which considers semantic attributes of keywords. Classi cation in conventional concept-based dictionaries are not fully applicable for such purpose, thus we extracted such su xes from corpora. The result was applied to actual television news programs for evaluation, which showed fairly high recognition rates.
منابع مشابه
News Video Classi cation based on Semantic Attributes of Captions
As a basis for automatic indexing to video data based on shot classi cation, we will present a graphical classi cation rule acquisition method based on semantics of accompanying natural language data i.e. captions. A preliminary experiment to actual television news programs showed good correspondence between graphical characteristics and semantic attributes of captions.
متن کاملAutomatic Video Indexing Based on Shot Classification
Automatic indexing to video data is in strong demand to cope with the increasing amount. We propose an automatic indexing method for television news video, which indexes to shots considering the correspondence of image contents and semantic attributes of keywords. This is realized by rst, (1) classifying shots by graphical feature, and (2) analyzing semantic attributes of accompanying captions....
متن کاملCompilation of dictionaries for semantic attribute analysis of television news captions
With the increase in the amount of video that is broadcast daily, there is an increasing need for storage of video in a systematic way for future reuse and retrieval. In particular, from the viewpoint of importance and usability, it is desirable to index news videos. For adequate automatic indexing based on the text information in the video, it is not sufficient to apply the simple index extrac...
متن کاملIntegrating multi-modal content analysis and hyperbolic visualization for large-scale news video retrieval and exploration
In this paper, we have developed a novel scheme to achieve more effective analysis, retrieval and exploration of large-scale news video collections by performing multi-modal video content analysis and synchronization. First, automatic keyword extraction is performed on news closed captions and audio channels to detect the most interesting news topics (i.e., keywords for news topic interpretatio...
متن کاملLaughter extracted from television closed captions as speech recognizer training data
Closed captions in television broadcasts, intended to aid the hearing impaired, also have potential as training data for speech-recognition software. Use of closed captions for automatic extraction of virtually unlimited training data has already been demonstrated [1]. This paper reports some preliminary work on the use of non-speech sound tokens included in closed captions to extract training ...
متن کامل