A novel horror scene detection scheme on revised multiple instance learning model

Authors:
Bin Wu;Xinghao Jiang;Tanfeng Sun;Shanfeng Zhang;Xiqing Chu;Chuxiong Shen;Jingwen Fan
Affiliations:
School of Information Security Engineering, Shanghai Jiao Tong University;School of Information Security Engineering, Shanghai Jiao Tong University and Shanghai Information Security Management and Technology Research Key Lab;School of Information Security Engineering, Shanghai Jiao Tong University and Shanghai Information Security Management and Technology Research Key Lab;School of Information Security Engineering, Shanghai Jiao Tong University;School of Information Security Engineering, Shanghai Jiao Tong University;School of Information Security Engineering, Shanghai Jiao Tong University;School of Information Security Engineering, Shanghai Jiao Tong University
Venue:
MMM'11 Proceedings of the 17th international conference on Advances in multimedia modeling - Volume Part II
Year:
2011

Citing 7
Cited 2

Solving the multiple instance problem with axis-parallel rectangles

Artificial Intelligence
A framework for multiple-instance learning

NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
Horror film genre typing and scene labeling via audio analysis

ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 1
Crime scene classification

Proceedings of the 2008 ACM symposium on Applied computing
Localized Content-Based Image Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic Video Pattern Recognition Based on Combination of MPEG-7 Descriptors and Second-Prediction Strategy

ISECS '09 Proceedings of the 2009 Second International Symposium on Electronic Commerce and Security - Volume 01
Multi-Layer Multi-Instance Learning for Video Concept Detection

IEEE Transactions on Multimedia

Horror video scene recognition based on multi-view multi-instance learning

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Video scene segmentation by improved visual shot coherence

Proceedings of the 19th Brazilian symposium on Multimedia and the web

Quantified Score

Hi-index	0.00

Visualization

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.