A hierarchical approach to story segmentation of large broadcast news video corpus

Chaisorn, Lekha; Chua, Tat-Seng; Lee, Chin‐Hui

doi:10.1109/icme.2004.1394401

Cited by 17 publications

(32 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chaisorn et al [4] describe a system that segments television news using a wide range of cues, including analysis of the television picture, and the captions that appear on it. These supplement segmentation that is based on the analysis of a transcription produced using ASR (automatic speech recognition).…”

Section: Topical Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Web-assisted annotation, semantic indexing and search of television and radio news

Dowman

Tablan

Cunningham

et al. 2005

Proceedings of the 14th International Conference on World Wide Web - WWW '05

View full text Add to dashboard Cite

The Rich News system, that can automatically annotate radio and television news with the aid of resources retrieved from the World Wide Web, is described. Automatic speech recognition gives a temporally precise but conceptually inaccurate annotation model. Information extraction from related web news sites gives the opposite: conceptual accuracy but no temporal data. Our approach combines the two for temporally accurate conceptual semantic annotation of broadcast news. First low quality transcripts of the broadcasts are produced using speech recognition, and these are then automatically divided into sections corresponding to individual news stories. A key phrases extraction component finds key phrases for each story and uses these to search for web pages reporting the same event. The text and meta-data of the web pages is then used to create index documents for the stories in the original broadcasts, which are semantically annotated using the KIM knowledge management platform. A web interface then allows conceptual search and browsing of news stories, and playing of the parts of the media files corresponding to each news story. The use of material from the World Wide Web allows much higher quality textual descriptions and semantic annotations to be produced than would have been possible using the ASR transcript directly. The semantic annotations can form a part of the Semantic Web, and an evaluation shows that the system operates with high precision, and with a moderate level of recall.

show abstract

Section: Topical Segmentationmentioning

confidence: 99%

“…Searches were conducted using Google, which was accessed via the Google Web API 4 . Searches were restricted to the news section of the BBC website, by adding the term site:news.bbc.co.uk to each search.…”

Section: Search Of the Web For Related Documentsmentioning

confidence: 99%

Web-assisted annotation, semantic indexing and search of television and radio news

Dowman

Tablan

Cunningham

et al. 2005

Proceedings of the 14th International Conference on World Wide Web - WWW '05

View full text Add to dashboard Cite

show abstract

“…STD aims to detect scenes on the basis of computable audiovisual characteristics and production rules. There has been lots of prior work on STD concentrating on sitcoms, movies [5] - [9], or broadcast news video [10] [11].…”

Section: Challengesmentioning

confidence: 99%

Segmentation, categorization, and identification of commercial clips from TV streams using multimodal analysis

Duan

Wang

Yong

et al. 2006

Proceedings of the 14th ACM International Conference on Multimedia

View full text Add to dashboard Cite

TV advertising is ubiquitous, perseverant, and economically vital. Millions of people's living and working habits are affected by TV commercials. In this paper, we present a multimodal ("visual + audio + text") commercial video digest scheme to segment individual commercials and carry out semantic content analysis within a detected commercial segment from TV streams.Two challenging issues are addressed. Firstly, we propose a multimodal approach to robustly detect the boundaries of individual commercials. Secondly, we attempt to classify a commercial with respect to advertised products/services. For the first, the boundary detection of individual commercials is reduced to the problem of binary classification of shot boundaries via the mid-level features derived from two concepts: Image Frames Marked with Product Information (FMPI) and Audio Scene Change Indicator (ASCI). Moreover, the accurate individual boundary enables us to perform commercial identification by clip matching via a spatial-temporal signature. For the second, commercial classification is formulated as the task of text categorization by expanding sparse texts from ASR/OCR with external knowledge. Our boundary detection has achieved a good result of F1 = 93.7% on the dataset comprising 499 individual commercials from TRECVID'05 video corpus. Commercial classification has obtained a promising accuracy of 80.9% on 141 distinct ones. Based on these achievements, various applications such as an intelligent digital TV set-top box can be accomplished to enhance the TV viewer's capabilities in monitoring and managing commercials from TV streams.

show abstract

“…Many approaches to topical segmentation have used textual cues but often they have been in conjunction with cues from non-textual sources. The system described by Chaisorn et al [2] segments television news using a wide range of cues, such as analysis of the television picture, and the captions that appear on it. These cues supplement the segmentation which is based on the analysis of a transcription produced using a speech recognizer.…”

Section: Metadata Storagementioning

confidence: 99%

“…Such methods segment based on an analysis of the text as a whole, and so should be relatively robust even when words at topic boundaries have been misrecognised. It was therefore decided to proceed using such an approach, and the specific segmentation algorithm used was the C99 segmenter [2].…”

Section: Metadata Storagementioning

confidence: 99%

Semantic analysis for tomorrow's audio-visual digital archives

Ursu

Tablan

Cunningham

2005

2nd European Workshop on the Integration of Knowledge, Semantics and Digital Media Technology (EWIMT 2005)

View full text Add to dashboard Cite

PrestoSpace 1 is a European-funded research project that aims at addressing the problem of decaying audio-visual archives throughout Europe by means of digitisation for preservation and access. One of the work areas within the project is Metadata Access and Delivery (MAD) which employs innovative methods of generating metadata for the digitised media in order to enhance the resulting archives and to ease access to the stored material. One such method is the use of automatic semantic analysis using natural language processing techniques in the process of creating analytical metadata for the preserved essence.

show abstract

A hierarchical approach to story segmentation of large broadcast news video corpus

Cited by 17 publications

References 3 publications

Web-assisted annotation, semantic indexing and search of television and radio news

Web-assisted annotation, semantic indexing and search of television and radio news

Segmentation, categorization, and identification of commercial clips from TV streams using multimodal analysis

Semantic analysis for tomorrow's audio-visual digital archives

Contact Info

Product

Resources

About