Abstract
We present a novel approach to the automatic generation of lmic variants within an implemented Video-Based Storytelling (VBS) system that successfully integrates video segmentation with stochastically controlled re-ordering techniques
and narrative generation via AI planning. We have introduced exibility into the video recombination process by sequencing video shots in a way that maintains local video consistency and this is combined with exploitation of shot polysemy to enable shot reuse in a range of valid semantic contexts. Results of evaluations on output narratives using a shared set of video data show consistency in terms of local video sequences and global causality with no loss of generative power.
and narrative generation via AI planning. We have introduced exibility into the video recombination process by sequencing video shots in a way that maintains local video consistency and this is combined with exploitation of shot polysemy to enable shot reuse in a range of valid semantic contexts. Results of evaluations on output narratives using a shared set of video data show consistency in terms of local video sequences and global causality with no loss of generative power.
Original language | English |
---|---|
Title of host publication | MM '11: Proceedings of the 19th ACM international conference on Multimedia |
Publisher | ACM |
Pages | 223-232 |
ISBN (Print) | 9781450306164 |
DOIs | |
Publication status | Published - 28 Nov 2011 |
Event | 19th ACM International Conference - Scottsdale, Arizona, United States Duration: 28 Nov 2011 → 1 Dec 2011 Conference number: 19 |
Conference
Conference | 19th ACM International Conference |
---|---|
Country/Territory | United States |
City | Arizona |
Period | 28/11/11 → 1/12/11 |