What happens in films?

This paper aims to contribute to the analysis and description of semantic video content by investigating what actions are important in films. We apply a corpus analysis method to identify frequently occurring phrases in texts that describe films-screenplays and audio description. Frequent words and statistically significant collocations of these words are identified in screenplays of 75 films and in audio description of 45 films. Phrases such as 'looks at', 'turns to', 'smiles at' and various collocations of 'door' were found to be common. We argue that these phrases occur frequently because they describe actions that are important story-telling elements for filmed narrative. We discuss how this knowledge helps the development of systems to structure semantic video content.

[1]  Mike Graham,et al.  Extracting information about emotions in films , 2003, ACM Multimedia.

[2]  Volker Roth.  Content-based retrieval from digital video , 1999, Image Vis. Comput..

[3]  David Herman,et al.  Story Logic: Problems and Possibilities of Narrative , 2002 .

[4]  Avideh Zakhor,et al.  Applications of Video-Content Analysis and Retrieval , 2002, IEEE Multim..

[5]  Mike Graham,et al.  Linking Video and Text via Representations of Narrative , 2003 .

[6]  Svetha Venkatesh,et al.  Toward automatic extraction of expressive elements from motion pictures: tempo , 2002, IEEE Trans. Multim..

[7]  Kimiaki Shirahama,et al.  Video data mining: rhythms in a movie , 2004, 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763).

[8]  Svetha Venkatesh,et al.  Towards automatic extraction of expressive elements from motion pictures: tempo , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

[9]  Shih-Fu Chang,et al.  Color-mood analysis of films based on syntactic and psychological models , 2004, 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763).

[10]  Alberto Del Bimbo,et al.  Multi-Perspective Navigation of Movies , 1996, J. Vis. Lang. Comput..

[11]  SmadjaFrank.  Retrieving collocations from text , 1993 .

[12]  Shih-Fu Chang,et al.  Computable scenes and structures in films , 2002, IEEE Trans. Multim..

[13]  Robert B. Allen,et al.  Browsing the structure of multimedia stories , 2000, DL '00.

[14]  Nevenka Dimitrova,et al.  Screenplay alignment for closed-system speaker identification and analysis of feature films , 2004, 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763).

[15]  Hang-Bong Kang,et al.  Affective content detection using HMMs , 2003, ACM Multimedia.

[16]  Sue Ellen Wright,et al.  Handbook of terminology management. , 2001 .