Video browsing interfaces for the open video project

Geisler, Gary; Marchionini, Gary; Wildemuth, Barbara M.; Hughés, A.E.; Meng, Yonggang; Wilkens, Todd; Spinks, Richard

doi:10.1145/506444.506456

Cited by 8 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[27] Our experiments have been performed on 50 videos selected from the Open Video Project. [43] Those videos are the same ones used by Avila et al [27] to evaluate their methodology for estimating static video summaries, named VSUMM, whose results are considered in this work as a baseline for comparison purposes. All videos are in MPEG-1 format (30 fps, 352 × 240 pixels) with a duration varying from 1 to 4 minutes.…”

Section: Video Summarizationmentioning

confidence: 99%

A unified approach to content-based indexing and retrieval of digital videos from television archives

Souza¹,

Pádua

Nunes³

et al. 2014

AIR

View full text Add to dashboard Cite

This work addresses the development of a unified approach to content-based indexing and retrieval of digital videos from television archives. The proposed approach has been designed to deal with arbitrary television genres, making it suitable for various applications. To achieve this goal, the main steps of a content-based video retrieval system are addressed in this work, namely: video segmentation, key-frame extraction, content-based video indexing and the video retrieval operation itself. Video segmentation is addressed as a typical TV broadcast structuring problem, which consists in automatically determining the boundaries of each broadcasted program (like movies, news, among others) and inter-program (for instance, commercials). Specifically, to segment the videos, Electronic Program Guide (EPG) metadata is combined with the detection of two special cues, namely, audio cuts (silence) and dark monochrome frames. On the other hand, a color histogram-based approach performs key-frame extraction. Video indexing and retrieval are accomplished by using hashing and k-d tree methods, while visual signatures containing color, shape and texture information are estimated for the key-frames, by using image and frequency domain techniques. Experimental results with the dataset of a multimedia information system especially developed for managing television broadcast archives demonstrate that our approach works efficiently, retrieving videos in 0.16 seconds on average and achieving recall, precision and F1 measure values, as high as 0.76, 0.97 and 0.86 respectively.

show abstract

Section: Video Summarizationmentioning

confidence: 99%

A unified approach to content-based indexing and retrieval of digital videos from television archives

Souza¹,

Pádua

Nunes³

et al. 2014

AIR

View full text Add to dashboard Cite

show abstract

“…Video abstracts, analogous to text abstracts and created using a series of selected clips, may support many functions, including providing an overview or summary of the video (Wildemuth et al, 2002).…”

Section: Browsing and Searching In Digital Video And Audiomentioning

confidence: 99%

“…At the time of the study, the only metadata available were the titles of the webcasts, which were perceived as useful for selecting relevant webcasts. Because of the nature of the video track (a "talking head"), the creation of a video abstract by selecting a series of clips (e.g., keyframes) as a means of providing an overview (Lee et al, 2000;Wildemuth et al, 2002) will not be an effective solution. As suggested by some participants, a searchable text abstract (Smeaton & Browne, 2006) or an audio abstract (Marchionini et al, 2009;Song & Marchionini, 2007) would be more useful approaches when the technology matures.…”

Section: Selecting a Webcastmentioning

confidence: 99%

“…Some improvements to the webcasting system suggested by the participants were to satisfy the need for additional help: an annotation tool to take notes while doing the task as well as access to a dictionary or glossary. Similar to Task A, an abstract whether in text or audio (Lee et al, 2000;Marchionini et al, 2009;Song & Marchionini, 2007;Wildemuth et al, 2002) would likely be highly beneficial for this task.…”

Section: Writing a Gist: Help For Abstraction (Task C)mentioning

confidence: 99%

See 1 more Smart Citation

Understanding how webcasts are used as sources of information

Dufour

Bartlett

Toms

2010

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

Webcasting systems were developed to provide remote access in real-time to live events. Today, these systems have an additional requirement: to accommodate the "second life" of webcasts as archival information objects. Research to date has focused on facilitating the production and storage of webcasts as well as the development of more interactive and collaborative multimedia tools to support the event, but research has not examined how people interact with a webcasting system to access and use the contents of those archived events. Using an experimental design, this study examined how 16 typical users interact with a webcasting system to respond to a set of information tasks: selecting a webcast, searching for specific information, and making a gist of a webcast. Using several data sources that included user actions, user perceptions, and user explanations of their actions and decisions, the study also examined the strategies employed to complete the tasks.The results revealed distinctive system-use patterns for each task and provided insights into the types of tools needed to make webcasting systems better suited for also using the webcasts as information objects.

show abstract

“…A virtual repository is a key element in a Collaboratory as it provides a research community with a touchstone corpus of empirical materials and analyses to which members may have access (Berman et al, 2003). There currently exists no such virtual repository for video data in the human sciences, although the Open Video Project has developed a large testbed resource for digital video research work on such problems as automatic segmentation, summarization, creation of content surrogates, and developing face recognition algorithms (Geisler et al, 2002). The closest analog is TalkBank, which provides a few heavily used and oftcited data corpora (particularly audio data) in a number of language-related sub-disciplines.…”

Section: Virtual Repository For Video Data and Analysesmentioning

confidence: 99%

Video-as-Data and Digital Video Manipulation Techniques for Transforming Learning Sciences Research, Education, and Other Cultural Practices

Pea

The International Handbook of Virtual Learning Environments

View full text Add to dashboard Cite

Video browsing interfaces for the open video project

Cited by 8 publications

References 0 publications

A unified approach to content-based indexing and retrieval of digital videos from television archives

A unified approach to content-based indexing and retrieval of digital videos from television archives

Understanding how webcasts are used as sources of information

Video-as-Data and Digital Video Manipulation Techniques for Transforming Learning Sciences Research, Education, and Other Cultural Practices

Contact Info

Product

Resources

About