Intelligent delivery of personalised video programmes from a video database

Faudemay, Pascal; Seyrat, Claude

doi:10.1109/dexa.1997.617264

Cited by 8 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jaimes et al (2002) present a new framework for generating personalized video digests using a supervised learning algorithm which takes from specific users examples of important/ unimportant events as input from detailed event metadata where high level semantic features (e.g., number of offensive events) are extracted from an existing metadata signal at fixed time intervals. Faudemay and Seyrat (1997) present a system developed within the French Transdoc project for intelligent access to videos, enabling the application of content-based and cooperative queries to the video database and retrieval of sets of sequences and personalized videos. Hauptmann and Lin ( 2001) discuss a wearable, personalized Informedia system, which listens to and transcribes the wearer's part of a conversation, recognizes the face of the current dialog partner…”

Section: Research In Content Personalizationmentioning

confidence: 99%

A selective review of research in content personalization

Jeevan

Padhi²

2006

Library Review

View full text Add to dashboard Cite

Purpose -To provide a selective bibliography in the emerging area of library content personalization for the benefit of library and information professionals. Design/methodology/approach -A range of recently published works (in the period 1993-2004), which aim to provide pragmatic application of content personalization rather than theoretical works, are discussed and sorted into ''classified'' sections to help library professionals understand more about the various options for formulating content as per the specific needs of their clientele. Findings -This paper provides information about each category of tool and technique of personalization, indicating what is achieved and how particular developments can help other libraries or professionals. It recognises that personalization of library resources is a viable way of helping users deal with the information explosion, conserving their time for more productive intellectual tasks. It identifies how computer and information technology has enabled document mapping to be more efficient, especially because of the ease with which a document can be indexed and represented with multiple terms, and confirms that this same functionality can be used to represent a user's interests, facilitating the easy linking of relevant sources to prospective users. Personalization of library resources is an effective way for maximizing user benefit. Research limitations/implications -This is not an exhaustive list of developments in personalization. Rather it identifies a mix of products and solutions that are of immediate use to librarians. Practical implications -A very useful source of pragmatic applications of personalization so far, that can guide a practicing professional interested in creating similar solutions for more productive information support in his/her library. Originality/value -This paper fulfils an identified need for a ''review of technology'' for LIS practitioners and offers practical help to any professional exploring solutions similar to those outlined in this paper.

show abstract

Section: Research In Content Personalizationmentioning

confidence: 99%

A selective review of research in content personalization

Jeevan

Padhi²

2006

Library Review

View full text Add to dashboard Cite

show abstract

“…Views are lists of video segments, or query results. Our language operates on view sources, and returns view targets [15]. We have applied the first step of our query to spatial features, based on image.…”

Section: Example Of Sunset Detection Through Image Channelmentioning

confidence: 99%

<title>Video indexing based on image and sound</title>

1997

View full text Add to dashboard Cite

Video indexing is a major challenge for both scientific and economic reasons. Information extraction can sometimes be easier from sound channel than from image channel.We first present a multi-channel and multi-modal query interface, to query sound, image and script through "pull" and "push" queries. We then summarize the segmentation phase, which needs information from the image channel. Detection of critical segments is proposed. It should speed-up both automatic and manual indexing. We then present an overview of the information extraction phase. Information can be extracted from the sound channel, through speaker recognition, vocal dictation with unconstrained vocabularies, and script alignment with speech (or "script warping"). We present experiment results for these various techniques. Speaker recognition methods were tested on the TIMIT and NTIMIT database. Vocal dictation was experimented on newspaper sentences spoken by several speakers. Script alignment was tested on part of a cartoon movie, "Ivanhoe".For good quality sound segments, error rates are low enough for use in indexing applications. Major issues are the processing of sound segments with noise or music, and performance improvement through the use of appropriate, low-cost parallel architectures or networks of workstations.

show abstract

Content and Presentation Adaptation in Hypermedia Systems

Burnik

Pogačnik

Intelligent Integrated Media Communication Techniques

View full text Add to dashboard Cite

Intelligent delivery of personalised video programmes from a video database

Cited by 8 publications

References 11 publications

A selective review of research in content personalization

A selective review of research in content personalization

<title>Video indexing based on image and sound</title>

Content and Presentation Adaptation in Hypermedia Systems

Contact Info

Product

Resources

About