Towards auto-documentary: Tracking the evolution of news stories
dc.citation.epage | 827 | en_US |
dc.citation.spage | 820 | en_US |
dc.contributor.author | Duygulu, Pınar | en_US |
dc.contributor.author | Pan J.-Y. | en_US |
dc.contributor.author | Forsyth, D.A. | en_US |
dc.coverage.spatial | New York, NY, USA | en_US |
dc.date.accessioned | 2016-02-08T11:53:00Z | |
dc.date.available | 2016-02-08T11:53:00Z | |
dc.date.issued | 2004 | en_US |
dc.department | Department of Computer Engineering | en_US |
dc.description | Date of Conference: October 10 - 16, 2004 | en_US |
dc.description.abstract | News videos constitute an important source of information for tracking and documenting important events. In these videos, news stories are often accompanied by short video shots that tend to be repeated during the course of the event. Automatic detection of such repetitions is essential for creating auto-documentaries, for alleviating the limitation of traditional textual topic detection methods. In this paper, we propose novel methods for detecting and tracking the evolution of news over time. The proposed method exploits both visual cues and textual information to summarize evolving news stories. Experiments are carried on the TREC-VID data set consisting of 120 hours of news videos from two different channels. | en_US |
dc.description.provenance | Made available in DSpace on 2016-02-08T11:53:00Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2004 | en |
dc.identifier.doi | 10.1145/1027527.1027719 | en_US |
dc.identifier.uri | http://hdl.handle.net/11693/27423 | en_US |
dc.language.iso | English | en_US |
dc.publisher | ACM | en_US |
dc.relation.isversionof | https://doi.org/10.1145/1027527.1027719 | en_US |
dc.source.title | MULTIMEDIA '04 Proceedings of the 12th annual ACM international conference on Multimedia | en_US |
dc.subject | Auto-documentary | en_US |
dc.subject | Duplicate sequences | en_US |
dc.subject | Graph-based multi-modal topic discovery | en_US |
dc.subject | Matching logos | en_US |
dc.subject | News video analysis | en_US |
dc.subject | Algorithms | en_US |
dc.subject | Computer vision | en_US |
dc.subject | Database systems | en_US |
dc.subject | Graphic methods | en_US |
dc.subject | Information analysis | en_US |
dc.subject | Mathematical models | en_US |
dc.subject | Multimedia systems | en_US |
dc.subject | Information retrieval systems | en_US |
dc.title | Towards auto-documentary: Tracking the evolution of news stories | en_US |
dc.type | Conference Paper | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Towards auto-documentary Tracking the evolution of news stories.pdf
- Size:
- 965.23 KB
- Format:
- Adobe Portable Document Format
- Description:
- Full printable version