Efficient Tracking of News Topics Based on Chronological Semantic Structures in a Large-Scale News Video Archive

Ide, Ichiro; Kinoshita, Tomoyoshi; Takahashi, Tomokazu; Mo, Hiroshi; Katayama, Norio; Satoh, Shin’ichi; Murase, Hiroshi

doi:10.1587/transinf.e95.d.1288

Cited by 7 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As pre-processing, we construct a directed graph structure representing semantic and temporal relations between news stories called a``topic thread structure" as shown in Fig. 3 by the method proposed by Ide et al [14].…”

Section: Summarization Of Multiple News Videos Considering Consistencmentioning

confidence: 99%

“…Since one topic can develop into another topic, a topic thread could include multiple topics by linking locally related news stories. In the proposed method, we applied the method proposed by Ide et al [14] to¯rst construct a topic thread structure originating from a speci¯ed news story, and then select one representative topic thread from it. The topic thread structure represents local relations between individual news stories as directed edges, and at the same time a global trend of topics as a directed graph.…”

Section: Topic Threadingmentioning

confidence: 99%

“…When considering news videos, it is necessary to be handled as a series of events that occur along time rather than individual events. Considering this requirement, Ide et al have proposed an interface that allows the users to track the development of news topics [14] based on a structure built by considering the chronological and semantic relations between news stories. They named the structure a``Topic thread" and according to the statistics shown in the work [14], an average topic thread will be composed of 2,770 s. of video footage.…”

Section: Introductionmentioning

confidence: 99%

“…Considering this requirement, Ide et al have proposed an interface that allows the users to track the development of news topics [14] based on a structure built by considering the chronological and semantic relations between news stories. They named the structure a``Topic thread" and according to the statistics shown in the work [14], an average topic thread will be composed of 2,770 s. of video footage. In order to view the development of a news topic from its beginning to the end, it will take on average roughly 45 min.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Summarization of Multiple News Videos Considering the Consistency of Audio-Visual Contents

Zhang

Tanishige²,

Ide

et al. 2019

Int. J. Semantic Computing

Self Cite

View full text Add to dashboard Cite

News videos are valuable multimedia information on real-world events. However, due to the incremental nature of the contents, a sequence of news videos on a related news topic could be redundant and lengthy. Thus, a number of methods have been proposed for their summarization. However, there is a problem that most of these methods do not consider the consistency between the auditory and visual contents. This becomes a problem in the case of news videos, since both contents do not always come from the same source. Considering this, in this paper, we propose a method for summarizing a sequence of news videos considering the consistency of auditory and visual contents. The proposed method first selects key-sentences from the auditory contents (Closed Caption) of each news story in the sequence, and next selects a shot in the news story whose “Visual Concepts” detected from the visual contents are the most consistent with the selected key-sentence. In the end, the audio segment corresponding to each key-sentence is synthesized with the selected shot, and then these clips are concatenated into a summarized video. Results from subjective experiments on summarized videos on several news topics show the effectiveness of the proposed method.

show abstract

Section: Summarization Of Multiple News Videos Considering Consistencmentioning

confidence: 99%

Section: Topic Threadingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Summarization of Multiple News Videos Considering the Consistency of Audio-Visual Contents

Zhang

Tanishige²,

Ide

et al. 2019

Int. J. Semantic Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…The problem with these approaches is that they mainly focus either on the structural extraction of a single news show or try to concatenate the different threads of one news story over time. The combination of different story threads is so far not addressed, though the work of Ide et al on "mediaWalker" 13) is the closest reaching into this direction. Its aim is to establish and exploit the chronological semantic structure in a large-scale broadcast news video archive.…”

Section: Related Workmentioning

confidence: 99%

[Invited Paper] Explain This to Me!

Ide¹,

Nack²

2013

MTA

Self Cite

View full text Add to dashboard Cite

This paper addresses a framework that facilitates the semi-automated authoring of already edited new stories available in the repository of a news corporation or a public broadcast video archive. The newly generated video explains the chronological development of a current event, such as the resignation of a Prime Minister. The aim is to facilitate a journalist with an audio-visual body based on which he/she can finalize the explanatory piece. The framework introduces techniques that exploit demoscopic data in form of polls for the development of the general story outline; the automatic retrieval of relevant material by using a combination of event templates and automatic news summarization over topic threads; and the generation of the final video by applying a set of trimming rules. Example generations are presented and discussed, and an outline of future work is presented.

show abstract

Recompilation of Broadcast Videos Based on Real-World Scenarios

Ide

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Efficient Tracking of News Topics Based on Chronological Semantic Structures in a Large-Scale News Video Archive

Cited by 7 publications

References 24 publications

Summarization of Multiple News Videos Considering the Consistency of Audio-Visual Contents

Summarization of Multiple News Videos Considering the Consistency of Audio-Visual Contents

[Invited Paper] Explain This to Me!

Recompilation of Broadcast Videos Based on Real-World Scenarios

Contact Info

Product

Resources

About