skip to main content
10.1145/1459359.1459398acmconferencesArticle/Chapter ViewAbstractPublication PagesmmConference Proceedingsconference-collections
research-article

Configuring topologies of distributed semantic concept classifiers for continuous multimedia stream processing

Published: 26 October 2008 Publication History

Abstract

Real-time multimedia semantic concept detection requires instant identification of a set of concepts in streaming video or images. However, the potentially high data volumes of multimedia content, and high complexity associated with individual concept detectors, have hindered its practical deployment. In this paper, we present a new online concept detection system deployed on top of a distributed stream mining system. It uses a tree-topology of classifiers that are constructed on a semantic hierarchy of concepts of interest. We introduce a novel methodology for configuring such cascaded classifier topologies under constraints on the available resources. In our approach, we configure individual classifiers with optimized operating points after jointly and explicitly considering the misclassification cost of each end-to-end class of interest in the tree, the system imposed resource constraints, and the confidence level of each object that is classified. We describe the implemented application, system, and optimization algorithms, and verify that significant improvement in terms of accuracy of classification can be achieved through our approach.

References

[1]
LIBSVM. http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/.
[2]
A. J. A. Vailaya, M. Figueiredo and H. Zhang, A bayesian framework for semantic classification of outdoor vacation images, in SPIE Conference on Electronic Imaging, San Jose, California, 1999.
[3]
L. Amini, H. Andrade, F. Eskesen, R. King, Y. Park, P. Selo, and C. Venkatramani, The stream processing core, Tech. Report RSC 23798, IBM T.J. Watson Research Center, November 2005.
[4]
B. Babcock, S. Babu, M. Datar, and R. Motwani, Chain: Operator scheduling for memory minimization in data stream systems, in SIGMOD, 2003.
[5]
B. Babcock, S. Babu, M. Datar, R. Motwani, and D. Thomas, Operator scheduling in data stream systems, The VLDB Journal (2004).
[6]
M. Balazinska, H. Balakrishnan, S. Madden, and M. Stonebraker, Fault tolerance in the borealis distributed stream processing system, in SIGMOD, June 2005, pp. 13--24.
[7]
P. Boggs and J. Tolle, Sequential quadratic programming, Acta Numerica, 1995.
[8]
D. Carney and et al, Monitoring streams-a new class of data management applications, in VLDB, 2002.
[9]
M. Cherniack, H. Balakrishnan, M. Balazinska, D. Carney, U. Çetintemel, Y. Xing, and S. B. Zdonik, Scalable distributed stream processing, in CIDR, January 2003.
[10]
Y. Chi, P. S. Yu, H. Wang, and R. R. Muntz, Loadstar: A load shedding scheme for classifying data streams, in SDM, 2005.
[11]
M. Ciraco, M. Rogalewski, and G. Weiss, Improving classifier utility by altering the misclassification cost ratio, in Proc. 1st Intnl. Workshop on Utility-based Data Mining, 2005.
[12]
V. Eide, F. Eliassen, O. Granmo, and O. Lysne, Supporting timeliness and accuracy in distributed real-time content-based video analysis, in ACM International Conference on Multimedia, 2003.
[13]
F. Fu, D. Turaga, O. Verscheure, M. van der Schaar, and L. Amini, Configuring competing classifier chains in distributed stream mining systems, IEEE Journal on Selected Topics in Signal Processing (2007).
[14]
M. Gaber, A. Zaslavsky, and S. Krishnaswamy, Resource-aware knowledge discovery in data streams, in International Workshop on Knowledge Discovery in Data Streams, 2004.
[15]
B. Gedik, H. Andrade, K.-L. Wu, P. S. Yu, and M. Doo, SPADE: The System S Declarative Stream Processing Engine, in SIGMOD, 2008.
[16]
R. Lienhart, L. Liang, and A. Kuranov, A detector tree for boosted classifiers for real-time object detection and tracking, in ICME, 2003.
[17]
Y. Mao, X. Zhou, D. Pi, Y. Sun, and S. T. C. Wong, Multiclass cancer classification by using fuzzy support vector machine and binary decision tree with gene selection., Journal of Biomedical Biotechnology 2005, no. 2 (2005), pp. 160--71.
[18]
R. Motwani and et al, Query processing, approximation, and resource management in a data stream management system, in CIDR, 2003.
[19]
M. Naphade, J. R. Smith, J. Tesic, S.-F. Chang, W. Hsu, L. Kennedy, A. Hauptmann, and J. Curtis, Large-scale concept ontology for multimedia, IEEE MultiMedia 13, no. 3 (2006), pp. 86--91.
[20]
M. R. Naphade and J. R. Smith, On the detection of semantic concepts at trecvid, in Proceedings of the 12th annual ACM international conference on Multimedia, New York, NY, USA, 2004, pp. 660--667.
[21]
A. Ntoulas, M. Najork, M. Manasse, and D. Fetterly, Detecting spam web pages through content analysis, in WWW, May 2006, pp. 83--92.
[22]
C. Olston, J. Jiang, and J. Widom, Adaptive filters for continuous queries over distributed data streams, in SIGMOD, June 2003, pp. 563--574.
[23]
J. C. Platt, Fast training of support vector machines using sequential minimal optimization (1999), pp. 185--208.
[24]
M. Powell, A fast algorithm for nonlinearly con-strained optimization calculations, in Numerical Analysis, L. N. i. M. G.A. Watson ed., ed., Springer Verlag, 1978.
[25]
M. A. Shah, J. M. Hellerstein, S. Chandrasekaran, and M. J. Franklin, Flux: An adaptive partitioning operator for continuous query systems, in ICDE, March 2003, pp. 25--36.
[26]
J. R. Smith, IBM multimedia analysis and retrieval system (MARVEL). http://mp7.watson.ibm.com/marvel/.
[27]
C. Snoek and M. Worring, Multimodal video indexing: A review of the state-of-the-art, Multimedia Tools Application 25, no. 1 (2005), pp. 5--35.
[28]
N. Tatbul, U. Çetintemel, and S. B. Zdonik, Staying fit: Efficient load shedding techniques for distributed stream processing, in Proceedings of the 33rd International Conference on Very Large Databases (VLDB), 2007.
[29]
W. Teng, M. Chen, and P. Yu, Resource-aware mining with variable granularities in data streams, in ICDM 2004, 2004.
[30]
S. Viglas and J. Naughton, Rate-based query optimization for streaming information sources, in SIGMOD, 2002.
[31]
Y. Wu, B. L. Tseng, and J. R. Smith, Ontology-based multi-classification learning for video concept detection, in IEEE International Conference on Multimedia and Expo (ICME), Taipei, Taiwan, 2004.
[32]
Y. Xing, S. B. Zdonik, and J.-H. Hwang, Dynamic load distribution in the borealis stream processor, in ICDE, 2005, pp. 791--802.
[33]
R. Yan and A. G. Hauptmann, A review of text and image retrieval approaches for broadcast news video, Inf. Retr. 10, no. 4-5 (2007), pp. 445--484.
[34]
R. Yan, J. Tesic, and J. R. Smith, Model-shared subspace boosting for multi-label classification, in KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining, New York, NY, USA, 2007, ACM, pp. 834--843.

Cited By

View all
  • (2020)Pulse of the City: Spatio-Temporal Twitter Content Analysis2020 IEEE 36th International Conference on Data Engineering Workshops (ICDEW)10.1109/ICDEW49219.2020.00-10(33-39)Online publication date: Apr-2020
  • (2011)Configuring Trees of Classifiers in Distributed Multimedia Stream Mining SystemsIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2010.205701221:3(245-258)Online publication date: 1-Mar-2011
  • (2011)Towards large scale land-cover recognition of satellite images2011 8th International Conference on Information, Communications & Signal Processing10.1109/ICICS.2011.6174291(1-5)Online publication date: Dec-2011
  • Show More Cited By

Index Terms

  1. Configuring topologies of distributed semantic concept classifiers for continuous multimedia stream processing

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    MM '08: Proceedings of the 16th ACM international conference on Multimedia
    October 2008
    1206 pages
    ISBN:9781605583037
    DOI:10.1145/1459359
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 26 October 2008

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. multimedia stream mining
    2. resource constrained mining
    3. semantic concept detection

    Qualifiers

    • Research-article

    Conference

    MM08
    Sponsor:
    MM08: ACM Multimedia Conference 2008
    October 26 - 31, 2008
    British Columbia, Vancouver, Canada

    Acceptance Rates

    Overall Acceptance Rate 2,145 of 8,556 submissions, 25%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)1
    • Downloads (Last 6 weeks)1
    Reflects downloads up to 16 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2020)Pulse of the City: Spatio-Temporal Twitter Content Analysis2020 IEEE 36th International Conference on Data Engineering Workshops (ICDEW)10.1109/ICDEW49219.2020.00-10(33-39)Online publication date: Apr-2020
    • (2011)Configuring Trees of Classifiers in Distributed Multimedia Stream Mining SystemsIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2010.205701221:3(245-258)Online publication date: 1-Mar-2011
    • (2011)Towards large scale land-cover recognition of satellite images2011 8th International Conference on Information, Communications & Signal Processing10.1109/ICICS.2011.6174291(1-5)Online publication date: Dec-2011
    • (2011)Foresighted tree configuration games in resource constrained distributed stream mining sensorsAd Hoc Networks10.1016/j.adhoc.2010.08.0079:4(497-513)Online publication date: 1-Jun-2011
    • (2010)Design principles for developing stream processing applicationsSoftware—Practice & Experience10.5555/1890754.189076140:12(1073-1104)Online publication date: 1-Nov-2010
    • (2010)Exploiting multi-level parallelism for low-latency activity recognition in streaming videoProceedings of the first annual ACM SIGMM conference on Multimedia systems10.1145/1730836.1730838(1-12)Online publication date: 22-Feb-2010
    • (2010)Design principles for developing stream processing applicationsSoftware: Practice and Experience10.1002/spe.99340:12(1073-1104)Online publication date: 24-Aug-2010
    • (2009)Resource-adaptive multimedia analysis on stream mining systemsProceedings of the 2009 IEEE international conference on Multimedia and Expo10.5555/1698924.1699322(1584-1585)Online publication date: 28-Jun-2009
    • (2009)Resource-adaptive semantic concept detection using ensemble classifiersProceedings of the 2009 IEEE international conference on Multimedia and Expo10.5555/1698924.1699025(410-413)Online publication date: 28-Jun-2009
    • (2009)Resource-adaptive multimedia analysis on stream mining systems2009 IEEE International Conference on Multimedia and Expo10.1109/ICME.2009.5202818(1584-1585)Online publication date: Jun-2009
    • Show More Cited By

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media