“…As part of the Carnegie Mellon University's Informedia project, Christel et al proposed a news video browsing interface that visualizes news stories based on the combinations of the 3Ws focusing especially on the "Where" attribute [24], [25]. We focused on the cooccurrence of the "Who" attribute, and proposed a news video browsing interface by exploring the social network in news contents [26].…”
Section: Work On the Visualization Of News Structurementioning
“…As part of the Carnegie Mellon University's Informedia project, Christel et al proposed a news video browsing interface that visualizes news stories based on the combinations of the 3Ws focusing especially on the "Where" attribute [24], [25]. We focused on the cooccurrence of the "Who" attribute, and proposed a news video browsing interface by exploring the social network in news contents [26].…”
Section: Work On the Visualization Of News Structurementioning
“…Providing summarization and visualization of large-scale news videos is an important task, which aims at saving time for general audiences in searching and reading news of interest. One solution for this task is to let the audience track up and down the topic thread structure originating from a specified story [6,10]. However, in a large-scale broadcast video database, there are tens or hundreds of news stories depicting the same topic.…”
To make full use of the overwhelming volume of news videos available today, it is necessary to track the development of news stories from different channels, mine their dependencies, and organize them in a semantic way. We propose a novel news topic tracking and re-ranking system. The main contributions include: (1) a novel scheme of mining topicrelated stories through tracking and re-ranking on the basis of near duplicates built on top of text, (2) a proposed simple but effective query-expansion algorithm for improving the representativeness of a search query, (3) a large-scale broadcast video database containing more than 34,000 news stories constructed for experimentation, and (4) a novel keyscene ranking scheme for analyzing both text similarity and video near-duplicate constraints.
“…Ozkan and Duygulu proposed a method for extracting facial images from news videos with the name of a person [2]. Ide et al proposed a method for extracting human relationships from news videos [3]. In this paper, we focus on the extraction of speech shots such as interviews, press conferences, and public speakings, from news videos.…”
We propose a method for discriminating between a speech shot and a narrated shot to extract genuine speech shots from a broadcast news video. Speech shots in news videos contain a wealth of multimedia information of the speaker, and could thus be considered valuable as archived material. In order to extract speech shots from news videos, there is an approach that uses the position and size of a face region. However, it is difficult to extract them with only such an approach, since news videos contain non-speech shots where the speaker is not the subject that appears in the screen, namely, narrated shots. To solve this problem, we propose a method to discriminate between a speech shot and a narrated shot in two stages. The first stage of the proposed method directly evaluates the inconsistency between a subject and a speaker based on the co-occurrence between lip motion and voice. The second stage of the proposed method evaluates based on the intra- and inter-shot features that focus on the tendency of speech shots. With the combination of both stages, the proposed method accurately discriminates between a speech shot and a narrated shot. In the experiments, the overall accuracy of speech shots extraction by the proposed method was 0.871. Therefore, we confirmed the effectiveness of the proposed method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.