• No results found

Cover Page The handle http://hdl.handle.net/1887/45135 holds various files of this Leiden University dissertation. Author: Wu, S. Title: Large scale visual search Issue Date: 2016-12-22

N/A
N/A
Protected

Academic year: 2021

Share "Cover Page The handle http://hdl.handle.net/1887/45135 holds various files of this Leiden University dissertation. Author: Wu, S. Title: Large scale visual search Issue Date: 2016-12-22"

Copied!
4
0
0

Bezig met laden.... (Bekijk nu de volledige tekst)

Hele tekst

(1)

Cover Page

The handle http://hdl.handle.net/1887/45135 holds various files of this Leiden University dissertation.

Author: Wu, S.

Title: Large scale visual search Issue Date: 2016-12-22

(2)

Acknowledgements

First of all, I would like to thank the collaborations with Dr. Erwin M. Bakker, Dr. Bart Thomée, and Dr. Ard Oerlemans for some publications. Thank you very much for teaching me the art of scientific writing. I want to thank Dr. Fons Verbeek and Dr. Erwin M. Bakker for the post-doc position recommendation.

I also want to thank my master supervisor Prof. Guoqiang Xiao (Southwest University, China) for the help of my research and career planning.

Second, I would like to thank my colleagues in the media lab, LIACS, Yanming Guo and Yu Liu, thank you for organizing the research seminar every week and introducing me to the background of deep learning. I also want to thank Prof.

Feng Yao (National University of Defense Technology, China) for good suggestions about my research.

I am deeply grateful for my dear parents, you raised me, taught me how to be good, have always been supportive and meticulous caring. I wish we can spend more time together and travel a lot in the near future. I also want to thank my girlfriend Cailing Tang. Even as we face difficulties due to our long distance relationship, we always trust the happy future.

Many thanks to my friends in the Netherlands: Zhan Xiong, Junlin He, Boyang Liu, Qinyin Hu, Shengfa Miao, Di liu, Fuyu Cai, Yuanhao Guo, Xiaoqing Tang, Enrique Larios Vargas, Zhiwei Yang, Kaifeng Yang, Channa Li, Hao Wang, Long- mei Li, Koen van der Blom, Minghao Li, Peng Wang, Hongchang Shan, Jian Yang, Jinxian Wang, Yuchuan Qiao, Meng Sun, Min He, Guangchao Chen, Yinlong Xiao, Zhenyu Xiao, Yaojin Pen, Wenbo Ma, Rui Zhang, and Feng Zhang.

137

(3)

ACKNOWLEDGEMENTS

Many thanks to my friends in China: Han Jiang, Wei Xiong, Heng Yang, Fei Yuan, Zhen Tan, Chong Chen, Yu Guan, Kaifeng Deng, Fan Jiang, Feiwu Yuan, and Xiao Lin.

138

(4)

Curriculum Vitae

Song Wu was born in Mianyang, Sichuan, China on September 13, 1985. He received the B.S. degree and the M.S degree (under the supervision of Prof. Guo- qiang Xiao) of computer science from Southwest University, Chongqing, China, in 2009 and 2012, respectively.

In September 2012, he obtained a PhD position at the Leiden Institute of Ad- vanced Computer Science (LIACS), Leiden University, the Netherlands, under the supervision of Prof. Dr. J.N. Kok and Dr. M.S. Lew. His research mainly focuses on image pattern recognition, feature descriptors and detectors, large scale image search and classification, machine learning and deep learning. He is a reviewer of of the International Journal of Multimedia Information Retrieval (2012-now) and the International Conference of British Machine Vision Conference (BMVC 2014-now).

139

Referenties

GERELATEERDE DOCUMENTEN

Convolutional neural networks based deep hash learning: In order to achieve efficient large scale image search, the high performance of the supervised deep hashing model appears to

In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern

The evaluation results showed that the binary string descriptor based BoW model has low memory requirements for vocabulary storage and competi- tive performance compared with

De evaluatie-resultaten laten zien dat deze aanpak weinig geheugen gebruikt voor vocabulaire opslag en com- petetief presteert vergeleken met BoW afbeeldingsrepresentaties gebaseerd

This thesis aims to acquire knowledge on the epidemiology, treatment and outcomes of specialized burn care in the Netherlands and is based on data from the Rotterdam Burn

Financial support to the costs associated with the publication of this thesis from Tricolast nv (Belgie), Stichting Brandwonden Research Instituut/Humeca, Centrum Orthopedie

This thesis aims to acquire knowledge on the epidemiology, treatment and outcomes of specialized burn care in the Netherlands and is based on data from the Rotterdam Burn

Data on 9031 patients show a shift in burn centre utilization, with increasing incidence rates of burn-related burn centre admissions, a decreasing incidence rate of burn