Communications of the ACM
Content-Based Image Retrieval at the End of the Early Years
IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to Algorithms
RIDE '98 Proceedings of the Workshop on Research Issues in Database Engineering
Associating characters with events in films
Proceedings of the 6th ACM international conference on Image and video retrieval
RoleNet: treat a movie as a small society
Proceedings of the international workshop on Workshop on multimedia information retrieval
Automated summarization of narrative video on a semantic level
ICSC '07 Proceedings of the International Conference on Semantic Computing
Representing and playing user selected video narrative domains
SRMC '08 Proceedings of the 2nd ACM international workshop on Story representation, mechanism and context
Video summarization and scene detection by graph modeling
IEEE Transactions on Circuits and Systems for Video Technology
ICEC'07 Proceedings of the 6th international conference on Entertainment Computing
Hi-index | 0.00 |
Complex movies with different parallel lines of action, only intersecting in a small number of scenes, can be difficult to analyze. The present study sets out to provide the viewer with assisted automatic procedures designed to decompose and analyze the narrative from different possible perspectives. We propose a model for narrative decomposition, based on the interaction of characters. The production of a time-stamped screenplay is used to achieve movie annotation based on the screenplay's contents, providing information about scene boundaries and the action semantics therein. The analysis of the graph of main character relations enables the extraction of coherent sub-stories from the main narrative.