Abstract—Video images are capable of expressing various kinds of information; however special knowledge and techniques are required for authoring quality video content. In order to represent impressions, proper camerawork is required for delivering understandable content. However, amateur users often have difficulties in shooting images which appropriately reflect their expressive intentions. In this paper, we propose an incremental interaction model which supports the user’s shooting activity and aims to take shots that fit the expressive intention. The model helps to build interaction incrementally between the user and the system. Experiments were carried out to see how amateur users express emotive information using video cameras without any prior information. Results showed that the users with more experience could recognize if they have shot footage in an appropriate way; however they could not always shoot appropriately. It was also indicated that their self-evaluation of the shots does not always reflect the actual suitability of the shots.
Index Terms—Emotive, video production, film grammar
The authors are with School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa 923-1292 Japan (e-mail: hmitarai@jaist.ac.jp, ayoshi@jaist.ac.jp).
Cite: Hiroko Mitarai and Atsuo Yoshitaka, "Interaction Model for Emotive Video Production," International Journal of Information and Electronics Engineering vol. 2, no. 5, pp. 661-666, 2012.