Abstract
Horror scene detection is a research problem that has much practical use. The supervised method requires the training data to be labeled manually, which can be tedious and onerous. In this paper, a more challenging setting of the problems without complete information on data labels is investigated. In particular, as the horror scene is characterized by multiple features, this problem is formulated as a special multiple instance learning (MIL) problem – Multiple Grouped Instance Learning (MGIL), which requires partial labeled training. To solve the MGIL problem, a learning method is proposed – Multiple Distance- Expectation Maximization Diversity Density (MD-EMDD).Additionally, a survey is conducted to collect people’s opinions based on the definition of horror scenes. Combined with the survey results, Labeled with Ranking – MD – EMDD is proposed and demonstrated better results when compared to the traditional MIL algorithm and close to performance achieved by supervised method.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Gillespie, W.J., Nguyen, D.T.: Video Classification Using aTree-Based RBF Network. In: IEEE International Conference onImage Processing, vol. 3, pp. 465–468 (2005)
Hana, R.O.A., Freitas, C.O.A., Oliveira, L.S., Bortolozzi, F.: Crime scene classification. In: Proceedings of the ACM Symposium on Applied Computing, pp. 419–423 (2008)
Moncriefi, S., Venkatesh, S.: Horror Film Genre Typing And Scene Labeling Via Audio Analysis. In: ICME 2003, pp. 193–197 (2003)
Jiang, X., Sun, T., Chen, B.: Automatic Video Pattern RecognitionBased on Combination of MPEG-7 Descriptors andSecond-Prediction Strategy. In: Second International Symposium on Electronic Commerce and Security, pp. 199–202 (2009)
Gu, Z., Mei, T., Hua, X.-S.: Multi-Layer Multi-Instance Learning for Video Concept Detection. IEEE Transactions on Multimdeia 10(8), 1605–1616 (2008)
Dietterich, T.G., Lathrop, R.H., Lozano-Perez, T.: Solving The Multiple Instance Problem With Axis-parallel Rectangles. Artificial Intelligence 89(1-2), 31–71 (1997)
Rahmani, R., Goldman, S.A., Zhang, H., Cholleti, S.R., Fritts, J.E.: Localized Content Based Image Retrieval. IEEE Transactions On Pattern Analysis And Machine Intelligence, Special Issue, 1–10 (November 2008)
Zhang, Q., Goldman, S.A.: EM-DD: An Improved Multiple-instance Learning Technique. In: NIPS, vol. 14, pp. 1073–1080 (2002)
Maron, O., Lozano-Pérez, T.: A Framework for Multiple-instance Learning. In: Advances in Neural Information Processing Systems, vol. 10, pp. 570–576. MIT Press, Cambridge (1998)
Top Rated “Horror” Titles (2010), http://www.imdb.com/chart/horror
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wu, B. et al. (2011). A Novel Horror Scene Detection Scheme on Revised Multiple Instance Learning Model. In: Lee, KT., Tsai, WH., Liao, HY.M., Chen, T., Hsieh, JW., Tseng, CC. (eds) Advances in Multimedia Modeling. MMM 2011. Lecture Notes in Computer Science, vol 6524. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17829-0_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-17829-0_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17828-3
Online ISBN: 978-3-642-17829-0
eBook Packages: Computer ScienceComputer Science (R0)