TY - GEN
T1 - An adaptive search path traverse for large-scale video frame retrieval
AU - Nguyen, Diep Thi Ngoc
AU - Kiyoki, Yasushi
PY - 2014/1/1
Y1 - 2014/1/1
N2 - Multimedia retrieval task is faced with increasingly large datasets and variously changing preferences of users in every query. We realize that the high dimensional representation of physical data which previously challenges search algorithms now brings chances to cope with dynamic contexts. In this paper, we introduce a method of building a large-scale video frame retrieval environment with a fast search algorithm that handles user's dynamic contexts of querying by imagination and controlling response time. The search algorithm quickly finds an initial candidate, which has highest-match possibility, and then iteratively traverses along feature indexes to find other neighbor candidates until the input time bound is elapsed. The experimental studies based on the video frame retrieval system show the feasibility and effectiveness of our proposed search algorithm that can return results in a fraction of a second with a high success rate and small deviation to the expected ones. Moreover, its potential is clear that it can scale to large dataset while preserving its search performance.
AB - Multimedia retrieval task is faced with increasingly large datasets and variously changing preferences of users in every query. We realize that the high dimensional representation of physical data which previously challenges search algorithms now brings chances to cope with dynamic contexts. In this paper, we introduce a method of building a large-scale video frame retrieval environment with a fast search algorithm that handles user's dynamic contexts of querying by imagination and controlling response time. The search algorithm quickly finds an initial candidate, which has highest-match possibility, and then iteratively traverses along feature indexes to find other neighbor candidates until the input time bound is elapsed. The experimental studies based on the video frame retrieval system show the feasibility and effectiveness of our proposed search algorithm that can return results in a fraction of a second with a high success rate and small deviation to the expected ones. Moreover, its potential is clear that it can scale to large dataset while preserving its search performance.
KW - Adaptive response time
KW - Inverted index
KW - Large-scale multimedia retrieval
KW - Local search
KW - Video navigation
UR - http://www.scopus.com/inward/record.url?scp=84922548729&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84922548729&partnerID=8YFLogxK
U2 - 10.3233/978-1-61499-472-5-324
DO - 10.3233/978-1-61499-472-5-324
M3 - Conference contribution
AN - SCOPUS:84922548729
T3 - Frontiers in Artificial Intelligence and Applications
SP - 324
EP - 342
BT - Information Modelling and Knowledge Bases XXVI
A2 - Thalheim, Bernhard
A2 - Jaakkola, Hannu
A2 - Yoshida, Naofumi
A2 - Kiyoki, Yasushi
PB - IOS Press
T2 - 24th International Conference on Information Modelling and Knowledge Bases, EJC 2014
Y2 - 3 June 2014 through 6 June 2014
ER -