TY - JOUR
T1 - Efficient Search and Localization of Human Actions in Video Databases
AU - Shao, Ling
AU - Jones, Simon
AU - Li, Xuelong
PY - 2014/3
Y1 - 2014/3
N2 - As digital video databases grow, so grows the problem of effectively navigating through them. In this paper we propose a novel content-based video retrieval approach to searching such video databases, specifically those involving human actions, incorporating spatio-temporal localization. We outline a novel, highly efficient localization model that first performs temporal localization based on histograms of evenly spaced time-slices, then spatial localization based on histograms of a 2-D spatial grid. We further argue that our retrieval model, based on the aforementioned localization, followed by relevance ranking, results in a highly discriminative system, while remaining an order of magnitude faster than the current stateof-the-art method. We also show how relevance feedback can be applied to our localization and ranking algorithms. As a result, the presented system is more directly applicable to real world problems than any prior content-based video retrieval system.
AB - As digital video databases grow, so grows the problem of effectively navigating through them. In this paper we propose a novel content-based video retrieval approach to searching such video databases, specifically those involving human actions, incorporating spatio-temporal localization. We outline a novel, highly efficient localization model that first performs temporal localization based on histograms of evenly spaced time-slices, then spatial localization based on histograms of a 2-D spatial grid. We further argue that our retrieval model, based on the aforementioned localization, followed by relevance ranking, results in a highly discriminative system, while remaining an order of magnitude faster than the current stateof-the-art method. We also show how relevance feedback can be applied to our localization and ranking algorithms. As a result, the presented system is more directly applicable to real world problems than any prior content-based video retrieval system.
KW - Human actions
KW - relevance feedback
KW - spatiotemporal localization
KW - video retrieval
UR - http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6575133
U2 - 10.1109/TCSVT.2013.2276700
DO - 10.1109/TCSVT.2013.2276700
M3 - Article
SN - 1051-8215
VL - 24
SP - 504
EP - 512
JO - IEEE Transactions on Circuits and Systems for Video Technology
JF - IEEE Transactions on Circuits and Systems for Video Technology
IS - 3
ER -