The Open Video Digital Library

Marchionini, Gary; Geisler, Gary

doi:10.1045/december2002-marchionini

Cited by 86 publications

(45 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Open Video Project (www.open-video.org) currently has more than 1800 video segments with a variety of automatically and manually generated metadata elements. The repository is used as a testbed for creating and testing highly interactive user interfaces for digital video (See [1] for an overview of the project and [2] for details regarding one of the previous user studies). These interfaces are crucially dependent on surrogates (metadata that 'stands for' the full object) that provide context and clarity during the retrieval process.…”

Section: Introductionmentioning

confidence: 99%

Text or Pictures? An Eyetracking Study of How People View Digital Video Surrogates

Hughés

Wilkens

Wildemuth

et al. 2003

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

One important user-oriented facet of digital video retrieval research involves how to abstract and display digital video surrogates. This study reports on an investigation of digital video results pages that use textual and visual surrogates. Twelve subjects selected relevant video records from results lists containing titles, descriptions, and three keyframes for ten different search tasks. All subjects were eye-tracked to determine where, when, and how long they looked at text and image surrogates. Participants looked at and fixated on titles and descriptions statistically reliably more than on the images. Most people used the text as an anchor from which to make judgments about the search results and the images as confirmatory evidence for their selections. No differences were found whether the layout presented text or images in left to right order.

show abstract

Section: Introductionmentioning

confidence: 99%

Text or Pictures? An Eyetracking Study of How People View Digital Video Surrogates

Hughés

Wilkens

Wildemuth

et al. 2003

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to evaluate the performance of the proposed scheme, 5 videos form Open Video Project [13] are used. Table I lists some of the properties of these videos.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Video Summarization by Employing Visual Saliency in a Sufficient Content Change Method

Ejaz¹,

Mehmood²,

Sajjad³

et al. 2014

IJCTE

View full text Add to dashboard Cite

Abstract-The growing number of videos on the internet requires effective management strategies. Video summarization is a method for managing video data which provides succinct versions of the videos for efficient browsing and retrieval. The inter-frame disparity based key frame extraction is a popular scheme for summarizing videos. However, the performance of such schemes is limited by the fact that most of these techniques select the first frame in a shot as key frame which may not be representative of the shot. In this paper, we propose a saliency inspired inter-frame difference based summarization scheme which selects the most important frame of the shot based on color contrast saliency. The preliminary experimental results prove the efficacy of the proposed method.Index Terms-Video summarization, key frame extraction, image saliency, visual attention model, frame difference measure.

show abstract

“…The interview questions focused on defining the interviewees' search behaviour, including (i) a general overview of the interviewee's work -as advocated by Marchionini et al [7], Amato et al [1] and Larson et al [6], (ii) the researchers' selection of resources, i.e. reference to web-based search engines and other web sites, (iii) concrete examples of various current and past search processes, the importance of which is discussed in Smeulders et al [12].…”

Section: Case Study: Bandg User Requirementsmentioning

confidence: 99%

“…6 The ASR transcripts were generated by the Dutch language version of Nuance Dragon Naturally Speaking 9 SDK Server Edition used "out of the box" 7 . The emphasis in the prototype was placed on shot-level access and not on optimization of absolute speech transcript quality since it was determined that the recognition rate achieved by the ASR application without any form of speaker or language model adaptation was sufficient for the purposes of evaluating the prototype system.…”

Section: Content-based Audio-visual Indexing In Miasmentioning

confidence: 99%

Multimodal indexing of digital audio-visual documents: A case study for cultural heritage data

Carmichael

Larson

Marlow

et al. 2008

2008 International Workshop on Content-Based Multimedia Indexing

View full text Add to dashboard Cite

This paper describes a multimedia multimodal information access sub-system (MIAS) for digital audio-visual documents, typically presented in streaming media format. The system is designed to provide both professional and general users with entry points into video documents that are relevant to their information needs. In this work, we focus on the information needs of multimedia specialists at a Dutch cultural heritage institution with a large multimedia archive. A quantitative and qualitative assessment is made of the efficiency of search operations using our multimodal system and it is demonstrated that MIAS significantly facilitates information retrieval operations when searching within a video document.

show abstract

The Open Video Digital Library

Cited by 86 publications

References 12 publications

Text or Pictures? An Eyetracking Study of How People View Digital Video Surrogates

Text or Pictures? An Eyetracking Study of How People View Digital Video Surrogates

Video Summarization by Employing Visual Saliency in a Sufficient Content Change Method

Multimodal indexing of digital audio-visual documents: A case study for cultural heritage data

Contact Info

Product

Resources

About