Multimodal learning for quality of experience in video-to-retail applications: algorithms and deployment

Abstract

First, I sincerely thank my supervisor, Lau Chiew Tong (Nanyang Technological University, NTU), for accepting me as his student and helping me prepare this thesis. Second, I am thankful to Yonggang Wen for teaching me to organize research projects. I am also very grateful to my two external mentors, Kyle Guan (Bell Lab, USA) and Nguyen Binh Duong Ta (Singapore Management University), both of whom have guided me in my research and in revising my draft word by word.In addition, I would like to express my thanks to Jianfei Cai, Yong Luo, Han Hu, and Xinwen Zhang, for their tremendous help in many of the projects that I worked on during my PhD study. They provided detailed comments and motivated me to delve deeply into the issues encountered. Moreover, their guidance, from different perspectives and disciplines, enabled me to consider and explore more varied and comprehensive solutions rather than being constrained by a limited research field.