Dr. Junhong (Jennifer) Zhao obtained her doctoral degree in 2015 from the Institute of Electronics at the Chinese Academy of Sciences (CAS). Her academic journey began at the Human-Computer Speech Interaction Lab of Tsinghua University, where she participated in a collaborative program between CAS and Tsinghua. During this period from 2011 to 2015, her research centered around machine learning, particularly in speech-driven facial animation, speech recognition, and speaker verification. She then moved to the Institution of Information Engineering (IIE) of CAS and worked as an assistant researcher, where her research focused on deep learning and its applications on image understanding and audio signal processing (2015-2017). In 2018, she joined the Computational Media Innovation Center (CMIC) at Victoria University of Wellington (VUW) as a postdoctoral. There she contributed her background in deep learning in Computer Graphics (CG) and Virtual Reality (VR). Her research interests include deep learning methods for image-based lighting, portrait image relighting/delighting, and speech-driven facial animation. Since 2023, she transitioned to the Centre for Data Science and Artificial Intelligence (CDSAI) of VUW as a research fellow, contributing her expertise to artificial intelligence research and its practical applications, such as the innovative domain of intelligent aquaculture. In 2024, she joined the Victoria AI group as a lecturer.