Shih-Yao (Mike) Lin is an Applied Scientist at Amazon Prime Video working on Video Generation. Prior to joining Prime Video, he also worked with Amazon Aelxa AI, and focus on the project of large scale Vision-Language Model Pre-training and Zero-shot Prediction. From October 2021 to July 2022, he worked at Sony as a Senior Research Scientist, within the R&D Center US Lab, focusing on 3D Character Motion Generation for Games. From April 2018 to August 2021, he worked at Tencent America as a Senior Researcher, specializing in Human Pose Estimation and Motion Analysis. he also served as a Postdoctoral Researcher at Bosch from May 2017 to March 2018, contributing to projects involving Sensor-based Hand Gesture Detection.
His research interests revolve around the intersection of Computer Vision and Deep Multimodal Learning. Lately, he have worked on advancing large-scale Visual-Language models, with a special emphasis on pre-training and zero-shot prediction
2023-06-02: One paper was accepted by IJCAI'23 Workshop on Spatio-Temporal Reasoning and Learning (STRL)
2022-08-08: Join Amazon as an Applied Scientist
2022-04-22: One paper was accepted by IJCAI'22
2021-10-15: One paper was accepted by BMVC'21
2021-09: Join Sony as a Sr. Research Scientist
2020-11-02: Two papers were accepted by WACV'21
2020-07-25: One paper was accepted by ACM Multimedia'20
2019-12-08: Our Artificial intelligence apps for Parkinson's patient evaluation was reported by BBC.
2019-09-16: One paper was accepted by WACV'20 (First Round Early Accepted)
2019-07-01: One paper was accepted by BMVC'19
2019-05-09: We launched our Parkinson’s AI clinical trial in London, UK, and it was reported by Parkinson’s Life
2019-01-21: Our work entitled "A Pilot Study to Evaluate the Severity of Motor Dysfunction in Parkinson's Disease Based on AI Video Analysis" has been registered in US NIH-registered Clinical Trial
2018-09-03: One paper was accepted by BMVC'18