Abstract
Video is a kind of structured data with multi-layer (ML) information, e.g., a shot is consisted of three layers including shot, key-frame, and region. Moreover, multi-instance (MI) relation is embedded along the consecutive layers. Both the ML structure and MI relation are essential for video concept detection. The previous work [5] dealt with ML structure and MI relation by constructing a MLMI kernel in which each layer is assumed to have equal contribution. However, such equal weighting technique cannot well model MI relation or handle ambiguity propagation problem, i.e., the propagation of uncertainty of sub-layer label through multiple layers, as it has been proved that different layers have different contributions to the kernel. In this paper, we propose a novel algorithm named MILC2 (Multi-Layer Multi-Instance Learning with Inter-layer Consistency Constraint.) to tackle the ambiguity propagation problem, in which an inter-layer consistency constraint is explicitly introduced to measure the disagreement of inter-layers, and thus the MI relation is better modeled. This learning task is formulated in a regularization framework with three components including hyper-bag prediction error, inter-layer inconsistency measure, and classifier complexity. We apply the proposed MILC2 to video concept detection over TRECVID 2005 development corpus, and report better performance than both standard Support Vector Machine based and MLMI kernel methods.
This work was performed when the first author visited Microsoft Research Asia as an intern.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
TRECVID: TREC Video Retrieval Evaluation. http://www-nlpir.nist.gov/projects/TRECVID
Chen, Y., Bi, J., Wang, J.Z.: MILES: Multiple-instance learning via embedded instance selection. IEEE Trans. on Pattern Analysis and Machine Intelligence 28(12), 1931–1947 (2006)
Cheung, P.-M., Kwok, J.T.: A regularization framework for multiple-instance learning. In: Proceedings of International Conference on Machine Learning, pp. 193–200. ACM Press, New York (2006)
Deng, Y., Manjunath, B.S.: Unsupervised segmentation of color-texture regions in images and video. IEEE Trans. on Pattern Analysis and Machine Intelligence 23(8), 800–810 (2001)
Gu, Z., Mei, T., Hua, X.-S., Tang, J., Wu, X.: Multi-layer multi-instance kernel for video concept detection. In: Proceedings of ACM Multimedia, Augsburg, Germany (September 2007)
Kwok, J., Cheung, P.-M.: Marginalized multi-instance kernels. In: Proceedings of International Joint Conference on Artificial Intelligence, Hyderabad, India, pp. 901–906 (January 2007)
Maron, O., Ratan, A.L.: Multiple-instance learning for natural scene classification. In: Proceedings of International Conference on Machine Learning, pp. 341–349. Morgan Kaufmann, San Francisco (1998)
Naphade, M., Smith, J.R., Tesic, J., Chang, S.-F., Hsu, W., Kennedy, L., Hauptmann, A., Curtis, J.: Large-scale concept ontology for multimedia. IEEE MultiMedia 13(3), 86–91 (2006)
Qi, G.-J., Hua, X.-S., Rui, Y., Tang, J., Mei, T., Zhang, H.-J.: Correlative multi-label video annotation. In: Proceedings of ACM Multimedia, Augsburg, Germany (September 2007)
Smola, A., Vishwanathan, S., Hofmann, T.: Kernel methods for missing variables. In: Proceedings of International Workshop on Artificial Intelligence and Statistics, Barbados (2005)
Gartner, T., Flach, P.A., Kowalczyk, A., Smola, A.J.: Multi-instance kernels. In: Proceedings of International Conference on Machine Learning, pp. 179–186. Morgan Kaufmann, San Francisco (2002)
Yan, R., Naphade, M.: Semi-supervised cross feature learning for semantic concept detection in video. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2005)
Smeaton, A.F., Over, P., Kraaij, W.: Evaluation Campaigns and TRECVID. In: Proceedings of ACM SIGMM International Workshop on Multimedia Information Retrieval (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gu, Z., Mei, T., Tang, J., Wu, X., Hua, XS. (2008). MILC2: A Multi-Layer Multi-Instance Learning Approach to Video Concept Detection. In: Satoh, S., Nack, F., Etoh, M. (eds) Advances in Multimedia Modeling. MMM 2008. Lecture Notes in Computer Science, vol 4903. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-77409-9_3
Download citation
DOI: https://doi.org/10.1007/978-3-540-77409-9_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-77407-5
Online ISBN: 978-3-540-77409-9
eBook Packages: Computer ScienceComputer Science (R0)