Collective media annotation using undirected random field...

Details Collective media annotation using undirected random field... Collective media annotation using undirected random field...

2011-07-26

2011-07-26

Ahmed, Samir (Department: 2624)

Image analysis

Pattern recognition

Classification

C382S173000

Reexamination Certificate

active

07986842

ABSTRACT:
In an embodiment, the present invention relates to a method for semantic analysis of digital multimedia. In an embodiment of the invention, low level features are extracted representative of one or more concepts. A discriminative classifier is trained using these low level features. A collective annotation model is built based on the discriminative classifiers. In various embodiments of the invention, the frame work is totally generic and can be applied with any number of low-level features or discriminative classifiers. Further, the analysis makes no domain specific assumptions, and can be applied to activity analysis or other scenarios without modification. The framework admits the inclusion of a broad class of potential functions, hence enabling multi-modal analysis and the fusion of heterogeneous information sources.

REFERENCES:
patent: 6516090 (2003-02-01), Lennon et al.
Kumar et al: “Discriminative random fielsd: a discriminative framework for contextual interaction in classification”, IEEE, ICCV, 2003.
Tekinalp: “Detecting and recognizing text from video frames”, Middle East Technical University, the thesis for master degree, 2002.
Berry et al., “Using Linear Algebra for Intelligent Information Retrieval,” SIAM Review, pp. 1-24 (Dec. 1994).
Ghamrawi and McCallum, “Collective Multi-Label Classification,” Proc. of the 14thACM International Conference on Information and Knowledge Management, CIKM '05, ACM Press, 7 pages (2005).
Hauptmann, “Towards a Large Scale Concept Ontology for Broadcast Video,” In Proc. of the 3rdInt'l Conf. On Image and Video Retrieval, CIVR 2004. LNCS 3115. Springer-Verlag, Berlin, pp. 674-675 (2004).
Hollink et al., “Building a Visual Ontology for Video Retrieval,” In Multimedia '05: Proceedings of the 13th Annual ACM International Conference on Multimedia, ACM Press, 4 pages (2005).
Jeon et al., “Automatic Image Annotation and Retrieval Using Cross-Media Relevance Models,” . Proceedings of the 26th Annual international ACM SIGIR Conference on Research and Development in Information Retrieval, ACM Press, 8 pages (2003).
Kumar et al., “Discriminative Fields for Modeling Spatial Dependencies in Natural Images,” Advances in Neural Information Processing Systems, NIPS, 8 pages (2004).
Lafferty et al., “Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data,” Proc. of the 18thInternational Conference on Machine Learning, p. 262-289 (2001).
Malouf “A Comparison of Algorithms for Maximum Entropy Parameter Estimation,” Proc. of the 6thConference on Natural Language Learning—vol. 20 International Conference on Computational Linguistics, Association for Computational Linguistics, 7 pages (2002).
Over et al., “TRECVID 2005—An Overview,” Proc. TRECVID 2005, http://www-nlpir.nist.gov/projects/tvpubs/tv5.papers/tv5overview.pdf, 27 pages (Mar. 27, 2006).
Platt, “Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods,” Advances in Large Margin Classifiers, Smola, ed., MIT Press, 14 pages, (Mar. 26, 1999).
Snoek et al., “Early Versus Late Fusion in Semantic Video Analysis,” Proc. of the 13th Annual ACM International Conference on Multimedia, ACM Press, Singapore, 4 pages (Nov. 6-11, 2005).
Snoek et al., “The Challenge Problem for Automated Detection of 101 Semantic Concepts in Multimedia,” Proc. of ACM Multimedia, Santa Barbara, CA, 10 pages (Oct. 23-27, 2006).
van Gemert et al.,“Robust Scene Categorization by Learning Image Statistics in Context,” Proc. of IEEE CVPR, pp. 1-8 (2006).
Yan et al., “Mining Relationships Between Concepts Using Probabalistic Graphical Models.” Proc. IEEE ICME, Toronto, Canada, 4 pages. (Jul. 9-12, 2006).
Kumar, “Models for Learning Spatial Interactions in Natural Images for Context-Based Classification,” Ph.D. Thesis, The Robotics Institute, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, 191 pages, (2005).

Affiliated with

Also associated with

Rating

Collective media annotation using undirected random field... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Collective media annotation using undirected random field..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Collective media annotation using undirected random field... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2679476