University of Cambridge > Talks.cam > NLIP Seminar Series > Analyzing and Summarizing Movies using Turning Points

Analyzing and Summarizing Movies using Turning Points

Add to your list(s) Download to your calendar using vCal

  • UserFrank Keller (University of Edinburgh)
  • ClockFriday 19 November 2021, 12:00-13:00
  • HouseVirtual (Zoom).

If you have a question about this talk, please contact Huiyuan Xie.

Join Zoom Meeting https://cl-cam-ac-uk.zoom.us/j/98526954309?pwd=UVl2TkJxN3hyMUtLTzlZQVhuOVFxdz09

Meeting ID: 985 2695 4309 Passcode: 870201

According to screenwriting theory, turning points (e.g., change of plans, major setback, climax) are crucial narrative moments in a movie: They define the plot structure, determine its progression and segment the movie into thematic units. We propose the task of turning point identification a means of analyzing the narrative structure of a movie; turning points and the segmentation they provide facilitate the processing long, complex narratives. We introduce a dataset of movie synopses annotated with turning points, and show how neural networks can be trained to identify turning points automatically. We then use this the basis for graph-based neural models which perform movie summarization and trailer generation automatically.

This talk is part of the NLIP Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2021 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity