2005 · 14 citations · 14 references
HumanitiesComputer ScienceFilm StudiesCorpus LinguisticsNarratologyNatural Language ProcessingFilm AudiencesFilm GenresFilm ReceptionMultimodal CorporaNarrative StyleCinematic LanguageFilm-text RelationsNarrative Structure In FilmSemantic ContentSemantic Content ModelingSemantic StructureVideo Corpus Linguistics
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.
14
Story logic: problems and possibilities of narrative
Choice Reviews Online · 2002 · 1K citations
Arts, Design, Narrative Studies +16
Applications of video-content analysis and retrieval
Nevenka Dimitrova, Behzad Shahraray, Ibrahim Sezan et al. · IEEE Multimedia · 2002 · 275 citations
Retrieving collocations from text
SmadjaFrank · Computational Linguistics · 1993 · 212 citations
Affective content detection using HMMs
Hang-Bong Kang · 2003 · 145 citations