Beyond Shot Retrieval: Searching for Broadcast News Items Using Language Models of Concepts


Share/Save/Bookmark

Aly, Robin and Doherty, Aiden and Hiemstra, Djoerd and Smeaton, Alan (2010) Beyond Shot Retrieval: Searching for Broadcast News Items Using Language Models of Concepts. In: 32nd European Conference on IR Research, ECIR 2010, 28-31 March 2010, Milton Keynes, UK (pp. pp. 241-252).

open access
[img]
Preview
PDF
173kB
Abstract:Current video search systems commonly return video shots as results. We believe that users may better relate to longer, semantic video units and propose a retrieval framework for news story items, which consist of multiple shots. The framework is divided into two parts: (1) A concept based language model which ranks news items with known occurrences of semantic concepts by the probability that an important concept is produced from the concept distribution of the news item and (2) a probabilistic model of the uncertain presence, or risk, of these concepts. In this paper we use a method to evaluate the performance of story retrieval, based on the TRECVID shot-based retrieval groundtruth. Our experiments on the TRECVID 2005 collection show a significant performance improvement against four standard methods.
Item Type:Conference or Workshop Item
Copyright:© 2010 Springer
Faculty:
Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:
Link to this item:http://purl.utwente.nl/publications/71235
Official URL:http://dx.doi.org/10.1007/978-3-642-12275-0_23
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page