Content-Based TV Stream Analysis Techniques toward Building a Catch-Up TV Service

Naturel, Xavier; Berrani, Sid-Ahmed

doi:10.1109/ism.2009.99

Cited by 3 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We recall that the goal of the TV stream macro-segmentation is to determine precisely the start and the end times of each TV program in the stream. We use in this experiment the TV stream macrosegmentation method proposed in [7]. Although the goal is to detect program boundaries, this system focuses on detecting inter-programs (commercials, trailers, etc.).…”

Section: B Tv Stream Macro-segmentation Improvement Using Credits Dementioning

confidence: 99%

“…In this experiment, program boundaries detected with the Naturel et al [7] method are replaced with the boundaries of the detected credits. For example, if the boundaries of a program have been extracted by the method of Naturel et al, and one or both of the credits of the same program have been detected by our technique, then the boundaries of the programs are modified to those derived from the detected credits.…”

Section: B Tv Stream Macro-segmentation Improvement Using Credits Dementioning

confidence: 99%

“…This trailer lasts however only five seconds. Naturel et al [7] Naturel et al [7] + detected credits Then, we present in Table IV the macro-segmentation accuracy. It shows the macro-segmentation imprecision of the detected programs start and end times.…”

Section: B Tv Stream Macro-segmentation Improvement Using Credits Dementioning

confidence: 99%

“…end) time. Table IV compares the accuracy obtained with the Naturel et al [7] method and their method refined with the detected credits by our technique. The imprecision of the start time has been decreased to 0 second with the creditsbased refinement while the end time imprecision concerning TV series has been decreased from 34 seconds to 3 seconds.…”

Section: B Tv Stream Macro-segmentation Improvement Using Credits Dementioning

confidence: 99%

“…We present in Table V the credit detection performance Table IV IMPACT OF CREDIT DETECTION ON THE IMPRECISION OF MACRO-SEGMENTATION. Naturel et al [7] Naturel et al [7] + detected credits varying the amount of accumulated stream on which the repeated sequence detection is performed. First, the Precision/Recall measures trend changes from the eighth day.…”

Section: Analysis On the Amount Of Accumulated Tv Streammentioning

confidence: 99%

See 4 more Smart Citations

Unsupervised Credit Detection in TV Broadcast Streams

Benezeth

Berrani

2010

2010 IEEE International Symposium on Multimedia

Self Cite

View full text Add to dashboard Cite

Abstract-This paper proposes an unsupervised method for detecting credits in TV streams. Identifying credits in TV streams allows to precisely determining boundaries of TV programs and hence, to extract specific and high valuable TV programs. The proposed detection solution is based on the temporal stability of opening and closing credits. Consequently, from a linear TV stream, we detect sequences that are broadcasted several times on a stable schedule with a clustering-based approach. These repeated sequences include opening and closing credits but also commercials, trailers etc. In order to select, among repeated sequences, those which are effectively credits, their temporal stability and their metadata consistency are analyzed. Since recurring programs are usually broadcasted at the same time(s) of the day, the temporal distribution of occurrences of each repeated sequence is studied. The Electronic Program Guide (EPG) is then used to validate the selected sequences and to distinguish between opening and closing credits. This method is entirely unsupervised and no prior information is required. Extensive experimental results validating our approach are presented.

show abstract

Section: B Tv Stream Macro-segmentation Improvement Using Credits Dementioning

confidence: 99%

Section: B Tv Stream Macro-segmentation Improvement Using Credits Dementioning

confidence: 99%

Section: B Tv Stream Macro-segmentation Improvement Using Credits Dementioning

confidence: 99%

Section: B Tv Stream Macro-segmentation Improvement Using Credits Dementioning

confidence: 99%

Section: Analysis On the Amount Of Accumulated Tv Streammentioning

confidence: 99%

See 3 more Smart Citations

Unsupervised Credit Detection in TV Broadcast Streams

Benezeth

Berrani

2010

2010 IEEE International Symposium on Multimedia

Self Cite

View full text Add to dashboard Cite

show abstract

Fast and accurate audio repetition detection in broadcast audio/video towards applications of content-based intelligent radio/TV services

Wang

Gao

et al. 2011

2011 6th International Conference on Pervasive Computing and Applications

View full text Add to dashboard Cite

Audio repetition detection has played a very important role in applications of content-based intelligent radio/TV services. In this paper, a method for fast and accurate audio repetition detection in broadcast audio/video is proposed based on the audio feature EEUPC (Energy Envelope Unit Position and Confidence). Audio repetition is first detected quickly using a fast algorithm based on EEUPC, and then refined on the basis of distance matrix to achieve higher accuracy. Experimental results on TV broadcasting audio of 40 hours show that the approach achieves performance of precision over 98% and recall over 97% with processing speed of 0.04x real-time for 20-hour data.

show abstract

Exploiting Speech for Automatic TV Delinearization: From Streams to Cross-Media Semantic Navigation

Gravier¹,

Guinaudeau²,

Lecorvé³

et al. 2011

EURASIP Journal on Image and Video Processing

View full text Add to dashboard Cite

The gradual migration of television from broadcast diffusion to Internet diffusion offers countless possibilities for the generation of rich navigable contents. However, it also raises numerous scientific issues regarding delinearization of TV streams and content enrichment. In this paper, we study how speech can be used at different levels of the delinearization process, using automatic speech transcription and natural language processing (NLP) for the segmentation and characterization of TV programs and for the generation of semantic hyperlinks in videos. Transcript-based video delinearization requires natural language processing techniques robust to transcription peculiarities, such as transcription errors, and to domain and genre differences. We therefore propose to modify classical NLP techniques, initially designed for regular texts, to improve their robustness in the context of TV delinearization. We demonstrate that the modified NLP techniques can efficiently handle various types of TV material and be exploited for program description, for topic segmentation, and for the generation of semantic hyperlinks between multimedia contents. We illustrate the concept of cross-media semantic navigation with a description of our news navigation demonstrator presented during the NEM Summit 2009.

show abstract

Content-Based TV Stream Analysis Techniques toward Building a Catch-Up TV Service

Cited by 3 publications

References 12 publications

Unsupervised Credit Detection in TV Broadcast Streams

Unsupervised Credit Detection in TV Broadcast Streams

Fast and accurate audio repetition detection in broadcast audio/video towards applications of content-based intelligent radio/TV services

Exploiting Speech for Automatic TV Delinearization: From Streams to Cross-Media Semantic Navigation

Contact Info

Product

Resources

About