A video database system for Digital Libraries

Zhang, Hong-Jiang; Smoliar, Stephen W.; Wu, Jian; Low, Chien Yong; Kankanhalli, Atreyi

doi:10.1007/bfb0026860

Cited by 8 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The library used in the experiment reported here contained all documentaries. The results should be verified across other classes of video, such as news footage which is often the focus of other research groups (Brown, 1995;Zhang, 1995;Hauptmann, 1997).…”

Section: Future Workmentioning

confidence: 93%

“…• Filmstrip: a set of images extracted from a video clip and displayed in chronological order, as shown in Figure 3. Such filmstrips have been used since the advent of digital video (Mills, 1992) and remain popular today (Taniguchi, 1995;Zhang, 1995). • Skim: a compact representation that summarizes the original clip by concatenating its significant subsets of video and audio data.…”

Section: Video Abstractionmentioning

confidence: 99%

“…Each library clip can be decomposed into camera shots, which are sets of "contiguous frames representing a continuous action in time or space" (Zhang, 1995). Informedia researchers have developed an algorithm that identifies, for each camera shot, a shot frame, the individual frame that best represents the whole shot .…”

Section: Construction Of Poster Framesmentioning

confidence: 99%

See 2 more Smart Citations

Improving Access to a Digital Video Library

Christel

Winkler

Taylor

1997

Human-Computer Interaction INTERACT ’97

View full text Add to dashboard Cite

Quick access to short, relevant video segments enables efficient use of a digital video library. This study evaluated an interface designed for such access, an interface that allows the user to browse a set of segments generated by a search query. Subjects' performance and attitudes were measured while they performed a fact-finding task to determine the relative effectiveness of three presentations: a text list, naively chosen visual imagery, and querybased visual imagery. Results show little difference in performance and subjective satisfaction between text lists and naively chosen imagery, but significant improvements when the images that represent video segments are based on the query that returned the segments (query-based poster frames). This result applies to the organization and representation of information in digital video libraries.

show abstract

Section: Future Workmentioning

confidence: 93%

Section: Video Abstractionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Access to a Digital Video Library

Christel

Winkler

Taylor

1997

Human-Computer Interaction INTERACT ’97

View full text Add to dashboard Cite

show abstract

“…Deconstructed into segments and shots, with each story segment consisting of a continuous range of video and/or audio deemed conceptually similar, and a shot being "contiguous frames representing a continuous action in time or space" [5]; Analyzed to derive additional descriptors, i.e., metadata, for creating alternate representations of the video; Augmented with indices of the metadata associated with segments to allow for the fast searching and retrieval of segments and shots.…”

Section: Introduction To the Informedia Projectmentioning

confidence: 99%

Automated Metadata in Multimedia Information Systems: Creation, Refinement, Use in Surrogates, and Evaluation

Christel

2009

Synthesis Lectures on Information Concepts, Retrieval, and Serv

View full text Add to dashboard Cite

Improvements in network bandwidth along with dramatic drops in digital storage and processing costs have resulted in the explosive growth of multimedia (combinations of text, image, audio, and video) resources on the Internet and in digital repositories. A suite of computer technologies delivering speech, image, and natural language understanding can automatically derive descriptive metadata for such resources. Difficulties for end users ensue, however, with the tremendous volume and varying quality of automated metadata for multimedia information systems. This lecture surveys automatic metadata creation methods for dealing with multimedia information resources, using broadcast news, documentaries, and oral histories as examples. Strategies for improving the utility of such metadata are discussed, including computationally intensive approaches, leveraging multimodal redundancy, folding in context, and leaving precision-recall tradeoffs under user control. Interfaces building from automatically generated metadata are presented, illustrating the use of video surrogates in multimedia information systems. Traditional information retrieval evaluation is discussed through the annual National Institute of Standards and Technology TRECVID forum, with experiments on exploratory search extending the discussion beyond fact-finding to broader, longer term search activities of learning, analysis, synthesis, and discovery.

show abstract

“…Digital video is becoming an increasingly common data type in the new generation of multimedia databases [1][2][3][4][5][6][7][8][9][10][11][12][13][14]. Many broadcasters are switching to digital formats for broadcasting, and some of them already have a significant amount of video material available in digital format for previewing.…”

Section: Introductionmentioning

confidence: 99%