Dr. Yongtao Hu
I'm now a Research Scientist at Guangdong Virtual Reality Technology Co., Ltd. (aka. Ximmerse), leading the research lab (aka. X-Lab) including algorithm, interaction design and patent teams. At Ximmerse, we dedicate ourselves in mobile VR/AR/MR input solutions and mobile visual computing technologies.
Previously, I was a Staff Researcher at Image & Visual Computing Lab (IVCL) of Lenovo (Hong Kong). Earlier, I also took internships at IVCL and Internet Graphics Group of Microsoft Research Asia (MSRA).
I received my Ph.D. degree of Computer Science from The University of Hong Kong in 2014, under the supervision of Prof. Wenping Wang. Before that, I received the B.S. degree of Computer Science from Shandong University in 2010.
My research interests include (but not limited to): Computer Vision & Learning (e.g., Image/Video Processing, Object Detection and Tracking, Deep Learning, etc.), Virtual/Augmented Reality (e.g., mobile VR/AR/MR input solutions, Environmental Understanding, etc.), Multimedia (e.g., Speaker Detection and Identification, Multimodal Analysis, TV/Movie Viewing Enhancement, etc.).
Job / Internship opening!
We are recruiting self-motivated interns / full-time researchers and developers to work at X-Lab in computer vision and interaction techniques, etc, to enhance VR/AR/MR. If interested, please drop me an email with your CV.
04/2020: Our paper on TopoTag: A Robust and Scalable Topological Fiducial Marker System is accepted to IEEE TVCG 2020. Software and dataset are also available.
03/2017: Our paper on Close to the Action: Eye-Tracking Evaluation of Speaker-Following Subtitles is accepted to CHI 2017.
02/17/2016: Code and dataset of our AAAI'16 paper Look, Listen and Learn - A Multimodal LSTM for Speaker Identiﬁcation have been made publicly online.
11/13/2015: Our paper on Look, Listen and Learn - A Multimodal LSTM for Speaker Identiﬁcation is accepted to AAAI 2016.