The Community for Technology Leaders
2007 IEEE 23rd International Conference on Data Engineering (2007)
Istanbul, Turkey
Apr. 15, 2007 to Apr. 20, 2007
ISBN: 1-4244-0802-4
pp: 1395-1399
Jie Shao , School of Information Technology and Electrical Engineering, The University of Queensland, Australia, jshao@itee.uq.edu.au
Zi Huang , School of Information Technology and Electrical Engineering, The University of Queensland, Australia, huang@itee.uq.edu.au
Heng Tao Shen , School of Information Technology and Electrical Engineering, The University of Queensland, Australia, shenht@itee.uq.edu.au
Xiaofang Zhou , School of Information Technology and Electrical Engineering, The University of Queensland, Australia, zxf@itee.uq.edu.au
Yijun Li , Nielsen Media Research, Australia, yijun.li@acnielsen.com.au
ABSTRACT
To retrieve similar database videos to a query clip, each video is typically represented by a sequence of high-dimensional feature vectors. Given a query video containing m feature vectors, an independent Nearest Neighbor (NN) search for each feature vector is often first performed. Completing all the NN searches, an overall similarity is then computed, i.e., a single video retrieval usually involves the searches for m times. Since normally nearby feature vectors in a video are similar, a large number of expensive random disk accesses are expected to repeatedly occur, which crucially affects the overall query performance. Batch Nearest Neighbor (BNN) search is stated as a single operation that performs a batch of individual NN searches. This paper presents a novel approach to efficient high-dimensional BNN search called Dynamic Query Ordering (DQO) for advanced optimizations in both I/O and CPU cost. Observing the overlapped candidates (or search space) of a pervious query may help to further reduce the candidate sets of succeeding queries, DQO aims to progressively find a query order such that the common candidates among queries are fully utilized to maximally reduce the total number of candidates. Modelling the candidate set relationship by a Candidate Overlapping Graph (COG), DQO iteratively selects the next query to be executed based on its estimated pruning power to the rest of queries with the dynamically updated COG. The extensive experiments show its significance.
INDEX TERMS
null
CITATION

J. Shao, X. Zhou, Z. Huang, H. T. Shen and Y. Li, "Dynamic Batch Nearest Neighbor Search in Video Retrieval," 2007 IEEE 23rd International Conference on Data Engineering(ICDE), Istanbul, Turkey, 2007, pp. 1395-1399.
doi:10.1109/ICDE.2007.369020
101 ms
(Ver 3.3 (11022016))