Query-independent learning for video search
Yuan Liu
Tao Mei
Guojun Qi
Xiuqing Wu
Xian-Sheng Hua
Univ. of Sci. & Technol. of China, Hefei;
This paper appears in: Multimedia and Expo, 2008 IEEE International Conference on
Publication Date: June 23 2008-April 26 2008
On page(s): 1249-1252
Location: Hannover,
ISBN: 978-1-4244-2570-9
INSPEC Accession Number: 10178946
Digital Object Identifier: 10.1109/ICME.2008.4607668
Current Version Published: 2008-08-26
Abstract
Most of existing learning-based methods for query-by-example take the query examples as ldquopositiverdquo and build a model for each query. These methods, referred to as query-dependent, only achieved limited success as they can hardly be applied to real-world applications, in which an arbitrary query is usually given. To address this problem, we propose to learn a query-independent model by exploiting the relevance information which exists in the pair of query-document. The proposed approach takes a query-document pair as a sample and extracts a set of query-independent textual and visual features from each pair. It is general and suitable for a real-world video search system since the learned relevance relation is independent on any query. We conducted extensive experiments over TRECVID 2005-2007 corpus and shown superior performance (+37% in Mean Average Precision) to the query-dependent learning approaches.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
