Automated Video Indexing of Very Large Video Libraries

Metadata

Publisher: SMPTE — White Plains, NY, USA
Doc Type: Journal Article
Content Type: Original Research
Abbreviated Title: SMPTE J
Volume: 106, No. 8, pp. 524–529
Abstract: The Informedia Digital Video Library project is implementing full content search and retrieval from digital video, audio, and text libraries through the utilization of integrated speech, image, and language understanding technologies for automated creation and exploration. Image processing analyzes scenes, speech processing transcribes the audio signal, and natural language processing determines word relevance. Together, these generate a meaningful index into the video content. Segment breaks produced by image processing are examined, along with the boundaries identified by the natural language processing of the transcript to partition the video library into sets of segments, or “video paragraphs.” Automating these techniques into a unified collaborative system uniquely enables us to include and search through vast amounts of video data in the library with little to no human intervention.
Publication Date: 1997-08-01
DOI: 10.5594/J04554
ISSN: Print: 0036-1682
Link: https://doi.org/10.5594/J04554
Author(s): H. D. WactlarCarnegie Mellon University, Pittsburgh, PA 15213
bio
Howard D. Wactlar is the viceprovost for research computing and associate dean of the School of Computer Science at Carnegie Mellon University. He was a founder of the Software Engineering Institute and director of the Information Technology Center, a research department focused on large-scale deployment and technology transfer. He was the primary architect and is currently the project director of the Informedia Digital Video Library. His research interests are multimedia, distributed systems, networking, and performance measurement.
A. G. HauptmannCarnegie Mellon University, Pittsburgh, PA 15213
bio
Alex Hauptmann is a systems scientist in the Computer Science Dept. at Carnegie Mellon University. He received his B.A. and M.A. degrees in psychology from Johns Hopkins University, studied computer science at Technische Universitaet Berlin from 1982 to 1984, and received his Ph.D. in computer science from Carnegie Mellon in 1991. His research interests have led him to pursue and combine several different areas: man-machine communication, natural language processing, speech understanding, and synthesis. He worked on speech and machine translation at CMU from 1984 to 1997, when he joined the Informedia project where he is researching a news-on-demand application.
M. A. SmithCarnegie Mellon University, Pittsburgh, PA 15213
bio
Michael Smith is a doctoral candidate in the Electrical and Computer Engineering Dept. at Carnegie Mellon University. He received his B.S. in electrical engineering from North Carolina A&T State University in 1991 and his M.S.E.E. from Stanford University in 1992. His a member of IEEE as well as Eta Kappa Nu, Tau Beta Pi, and Pi Mu Epsilon. — Smith has published papers on the subjects of pattern recognition, biomedical imaging, video characterization, and interactive computer systems. His current interests are image classification and recognition and content-based image understanding. His research is an active component of the Informedia Digital Video Library project at Carnegie.
K. V. PendyalaCarnegie Mellon University, Pittsburgh, PA 15213
bio
Krishna Pendyala is an information designer with extensive experience in the development of informational and learning applications. He serves as the assistant director of the NSF-sponsored Informedia Digital Video Library project at CMU's School of Computer Science. His research focus is on tools and methodologies for digital, nonlinear networked learning environments. — Pendyala is also the founder of Visual Symphony, Inc., a multimedia software developer that specializes in interactive networked applications to enhance human performance. He serves as a Unesco consultant to India on multimedia infrastructure and development. He is the vice-president of the International Interactive Communications Society (IICS) and the founder of the Pittsburgh Chapter, and a member of the board of directors of the Multimedia Foundry of Pittsburgh, established to promote that city as a center for new media. — Pendyala holds a Master's degree in educational media from Indiana State University and a Bachelor's degree in engineering from the Indian Institute of Technology, Madras, India.
D. GarlingtonISLIP Media Network, Inc., Pittsburgh, PA 15213.
bio
Dennis Garlington is a founder and principal in the firm of Dalby Emprise, a consultancy which investigates, reports, and advises on the technologies and business motivations creating the convergence of telephones, computers, and video displays. Garlington is a 25-year veteran of the telecommunications and interactive technology industries; he has held executive positions with GTE Interactive Media, Prodigy Services, Times Mirror, Cox Communications, and Memorex Corp.
Copyright: © 1997 Society of Motion Picture and Television Engineers, Inc.

Bibliographic Reference(s)

1. Christel M. Stevens S. Wactlar H. , “Informedia Digital Video Library,” Proc. of Second ACM International Conf. on Multimedia, Video Program, New York : ACM , pp. 480 – 481 , Oct. 1994 . EXTERNAL
2. Stevens S. Christel M. Wactlar H. , “Informedia: Improving Access to Digital Video,” Interactions 1 , pp. 67 – 71 , Oct. 1994 . EXTERNAL
3. Christel M. Kanade T. Mauldin M. ., “Informedia Digital Video Library,” Comnum. of the ACM , 38 : 51 – 58 , Apr. 1994 . EXTERNAL
4. Wactlar H. D. Kanade T. Smith M. A. Stevens S. M. , “Intelligent Access to Digital Video: Informedia Project,” IEEE Computer , 29 : 46 – 52 , May 1996 . EXTERNAL
5. Hauptmann A. G. Smith M. , “Text, Speech, and Vision for Video Segmentation: The Informedia Project,” AAAI Fall 1995 Symposium on Computational Models for Integrating Language and Vision, pp. 90 – 95 , MIT , Cambridge, Mass. , Nov. 1995 . EXTERNAL
6. Mauldin M. , “Information Retrieval by Text Skimming,” Ph.D. Thesis, Carnegie Mellon University , Aug. 1989 . Rev. edition published as Conceptual Information Retrieval: A Case Study in Adaptive Partial Parsing, Kluwer Press, Sept. 1991. EXTERNAL
7. Salton G. McGill M. J. , Introduction to Modern Information Retrieval , McGraw-Hill , New York , 1983 . EXTERNAL
8. Zhang H. Low C. Smoliar S. , “Video Parsing and Indexing of Compressed Data,” Multimedia Tools and Applications , 1 : 89 – 111 , Mar. 1995 . EXTERNAL
9. Hwang M. Rosenfeld R. Thayer E. ., “Improving Speech Recognition Performance via Phone-Dependent VQ Code-books and Adaptive Language Models in SPHINX-II,” ICASSP-94 , vol. I , pp. 549 – 552 . EXTERNAL
10. Rudnicky A. , “Language Modeling with Limited Domain Data,” Proc. of the 1995 ARPA Workshop on Spoken Language Technology , in press. EXTERNAL
11. Smith M. Kanade T. , “Video Skimming for Quick Browsing Based on Audio and Image Characterization,” Carnegie Mellon University technical report CMU-CS-95–186, July 1995 . EXTERNAL

Source Data (JSON)

Full registry record with provenance metadata. Open directly: /api/doc/10.5594-J04554.json

Reference Tree

Explore all references and references to this document, as a navigable tree.

Open Reference Tree

Reference this Doc

Plain text (ISO 690 compliant)

Preview:

H. D. Wactlar, A. G. Hauptmann, M. A. Smith, K. V. Pendyala, and D. Garlington; Automated Video Indexing of Very Large Video Libraries, SMPTE Journal ( Volume: 106, Issue: 8, August 1997); SMPTE, 1997. Available at https://doi.org/10.5594/J04554

Snippet:

H. D. Wactlar, A. G. Hauptmann, M. A. Smith, K. V. Pendyala, and D. Garlington; Automated Video Indexing of Very Large Video Libraries, SMPTE Journal ( Volume: 106, Issue: 8, August 1997); SMPTE, 1997. Available at https://doi.org/10.5594/J04554

HTML (ISO 690 compliant)

Preview:

Snippet:

<span class="citation">H. D. Wactlar, A. G. Hauptmann, M. A. Smith, K. V. Pendyala, and D. Garlington; <cite>Automated Video Indexing of Very Large Video Libraries</cite>, SMPTE Journal ( Volume: 106, Issue: 8, August 1997); SMPTE, 1997. Available at <a href="https://doi.org/10.5594/J04554" target="_blank" rel="noopener">https://doi.org/10.5594/J04554</a></span>

SMPTE's HTML Pub

Preview:

Snippet:

<li>
H. D. Wactlar, A. G. Hauptmann, M. A. Smith, K. V. Pendyala, and D. Garlington; <cite id="bib-10-5594-j04554">Automated Video Indexing of Very Large Video Libraries</cite>, SMPTE Journal ( Volume: 106, Issue: 8, August 1997); SMPTE, 1997
<span class="doi">10.5594/J04554</span>
</li>