TY - GEN
T1 - Global image representation using Locality-constrained Linear Coding for large-scale image retrieval
AU - Wu, Yu Hsing
AU - Ku, Wei Lin
AU - Peng, Wen-Hsiao
AU - Chou, Hung Chun
PY - 2014/1/1
Y1 - 2014/1/1
N2 - This paper proposes a global image representation based on Locality-constrained Linear Coding (LLC), with an aim to simplify the encoding process of local descriptors so as to facilitate large-scale image retrieval. Starting from the state-of-the-art Fisher Vector (FV) representation, we replace the computation of sophisticated posterior probabilities with simpler LLC. We then conduct several empirical studies to investigate the effects and benefits of this change and to adapt the other terms in FV for a better trade-off between performance and complexity. The result is a simpler global descriptor that combines the merits of both FV and LLC. Experimental results show that when compared with other similar works, our scheme not only brings performance benefits in mean Average Precision, but also offer complexity advantages.
AB - This paper proposes a global image representation based on Locality-constrained Linear Coding (LLC), with an aim to simplify the encoding process of local descriptors so as to facilitate large-scale image retrieval. Starting from the state-of-the-art Fisher Vector (FV) representation, we replace the computation of sophisticated posterior probabilities with simpler LLC. We then conduct several empirical studies to investigate the effects and benefits of this change and to adapt the other terms in FV for a better trade-off between performance and complexity. The result is a simpler global descriptor that combines the merits of both FV and LLC. Experimental results show that when compared with other similar works, our scheme not only brings performance benefits in mean Average Precision, but also offer complexity advantages.
UR - http://www.scopus.com/inward/record.url?scp=84907394984&partnerID=8YFLogxK
U2 - 10.1109/ISCAS.2014.6865248
DO - 10.1109/ISCAS.2014.6865248
M3 - Conference contribution
AN - SCOPUS:84907394984
SN - 9781479934324
T3 - Proceedings - IEEE International Symposium on Circuits and Systems
SP - 766
EP - 769
BT - 2014 IEEE International Symposium on Circuits and Systems, ISCAS 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 IEEE International Symposium on Circuits and Systems, ISCAS 2014
Y2 - 1 June 2014 through 5 June 2014
ER -