Click Here For Video
Email: fn@comp.lancs.ac.uk
Position: Research Associate
The research dealt with AUTEUR (Artificial Utilities for Thematic Film Editing using Context Understanding and Editing Rules), an experimental system that embodies mechanisms to interpret, manipulate and generate video. Within this system I explored the use of cognitive aspects of video editing and their use in the automated creation of film.
I assume a story as a psychological entity that refers to mental or conceptual objects such as themes, goals, events or actions. I believe that the strategies underlying stories for film, books, plays or pantomime are essentially the same. However, there are deep differences between the perceptual aspects of different communicational systems, and thus it is not possible to directly apply the well-known mechanisms of natural language to the understanding of film.
The aim of AUTEUR is to create video scenes that realise an overall thematic specification. The design of AUTEUR reflects aspects of visual humour, my approach of scene and meaning creation, and an editing model based on a knowledge elicitation exercise which involved studying and interviewing editors in their own environment.
The input for AUTEUR is a theme and a startshot around which the scene should be built. The process of scene construction is based on structural aspects of the given scene, with respect to the story to be created and the available arbitrary video material.
Within the VirtuOsi Project I seek to investigate the use of narrational techniques for two domains: animated co-operative virtual worlds (AVW) and business process applications (BPA). For the latter I focus in particularly on workflow management software. AVW and BPA are domains in which causal and temporal relationships between events, people and objects play an important role in the representation of the flow of, and the presentation of, information. Thus, it is reasonable to investigate how narrative knowledge and inference strategies might support the understanding, deduction, information retrieval and planning processes in AVW and BPA.
Nack, F. and Parkes, A. (early 1997) The Application of video Semantics and Theme Representation in Automated Video Editing. To Appear In... Special Issue on Representation and Retrieval of visual Media in multimedia Systems of Multimedia Tools and Applications [Ed: Zhang, H.]
Nack, F. AUTEUR: The Application of video Semantics and Theme Representation for Automated Film Editing (August 1996). Ph.D. Thesis, Lancaster University
Nack, F. and Parkes, A. (1995). AUTEUR: The Creation of Humorous Scenes Using Automated Video Editing. IJCAI-95 Workshop on AI Entertainment and AI/Alife, Montreal, Canada, August 19, 1995.
Nack, F. and Parkes, A. (1995). Automated Film Editing for Educational Applications? Don't make me laugh! Proceedings of ED-Media 95 - World Conference on Educational Multimedia and Hypermedia, Graz, Austria, June 17 - 21, 1995, 482 - 487.
Parkes, A. , Nack, F. and Butler, S. (1994) Artificial intelligence techniques and film structure knowledge for the representation and manipulation of video. Proceedings of RIAO '94, Intelligent Multimedia Information Retrieval Systems and Management. Vol. 2. Rockefeller University, New York, October 11-13, 1994