Mike Zheng SHOU

Dr. Mike Zheng Shou is a leading researcher in multimodal artificial intelligence, with a strong focus on video understanding and video generation. He is currently a tenure-track Assistant Professor in the Department of Electrical and Computer Engineering at the National University of Singapore (NUS), where he has been serving since May 2021. He also leads the Show Lab, a research group at NUS dedicated to advancing intelligent video systems. His work combines computer vision and deep learning to develop systems that allow machines to understand actions, events, and complex visual information in videos.

Dr. Shou received his Doctor of Philosophy degree in Electrical and Electronics Engineering from Columbia University in 2019, where he was advised by Professor Shih-Fu Chang. He completed his research with a perfect academic record. During his doctoral studies, he was awarded the Wei Family Private Foundation Fellowship from 2014 to 2017 in recognition of his research contributions. Before joining NUS, Dr. Shou worked as a Research Scientist at Facebook AI in the San Francisco Bay Area from 2019 to 2021. He also held research internship positions at Facebook in 2018 and at Microsoft in 2017.

In 2021, Dr. Shou was awarded the Singapore National Research Foundation (NRF) Fellowship, one of the country’s highest honours for early-career researchers. His fellowship project, titled “Towards Next-generation Video Intelligence: Training Machines to Understand Actions and Complex Events”, supports independent research in Singapore. His research has applications across self-driving vehicles, care robots for elderly support, smart surveillance systems, social media recommendation systems, and intelligent video creation tools for journalism and filmmaking.

Dr. Shou has made major research contributions in video-language models and video diffusion systems. His publication “Tune-A-Video” (ICCV 2023) introduced the first open-source video diffusion model and has received wide adoption in the research community. His work “Egocentric Video-Language Pretraining” (NeurIPS 2022) pioneered foundation models for egocentric video. He has also published influential papers at CVPR, ECCV, ICCV, and NeurIPS.

His research team has won first place in several major international challenges, including ActivityNet 2017, EPIC-Kitchens 2022, and Ego4D in 2022 and 2023. He has received Best Student Paper nomination at CVPR 2017 and Best Paper Finalist recognition at CVPR 2022. Dr. Shou regularly serves as Area Chair for top international conferences, including CVPR, ICCV, ECCV, and ACM Multimedia. He is a Fellow of Singapore’s National Research Foundation and was named to the Forbes 30 Under 30 Asia list, reflecting his global impact in artificial intelligence research.

Dr. Mike Zheng Shou is a researcher and academic in the field of artificial intelligence, with a focus on video understanding, video generation, computer vision, and deep learning. He is currently a tenure-track Assistant Professor in the Department of Electrical and Computer Engineering at the National University of Singapore, a role he has held since May 2021. He also leads the Show Lab at NUS, where his research group works on developing intelligent systems that allow machines to understand actions, activities, and complex events from video data and to generate videos using artificial intelligence.

Dr. Shou completed his Doctor of Philosophy in Electrical and Electronics Engineering at Columbia University in New York City in 2019. He was supervised by Professor Shih-Fu Chang and graduated with a perfect academic record. During his doctoral studies, he was awarded the Wei Family Private Foundation Fellowship from 2014 to 2017 for his research work. His doctoral research focused on video analysis and laid the foundation for his later contributions to video intelligence and multimodal learning.

Before joining NUS, Dr. Shou worked in industry research. From June 2019 to May 2021, he was a Research Scientist at Facebook AI in Menlo Park, California, where he contributed to large-scale research projects in computer vision and machine learning. Earlier, he held research internship positions at Facebook in the summer of 2018 and at Microsoft in the summer of 2017, gaining experience in both academic and industrial research environments.

In 2021, Dr. Shou received the Singapore National Research Foundation Fellowship, a highly competitive award that supports early career researchers. His fellowship project, titled “Towards Next-generation Video Intelligence: Training Machines to Understand Actions and Complex Events,” provided funding for him to establish an independent research programme in Singapore. His work aims to enable machines to interpret human actions and complex activities in video data, supporting real-world applications such as self-driving vehicle perception systems, care robots for elderly support, smart surveillance systems, social media content recommendation, and intelligent video creation tools for journalism and film production.

Dr. Shou’s research contributions include major advances in video-language models and video diffusion systems. In 2023, he co-authored “Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation,” presented at ICCV. This work introduced the first open-source video diffusion model and has been widely used in the research community. He also contributed “All in One: Exploring Unified Video-Language Pre-training” at CVPR 2023. In 2022, his paper “Egocentric Video-Language Pretraining” was presented at NeurIPS, where it received Spotlight recognition, placing it among the top papers at the conference. His work “AssistQ” was presented at ECCV 2022 and focused on task completion for egocentric assistants.

His research team has achieved first place in multiple international challenges, including ActivityNet 2017, EPIC-Kitchens 2022, and the Ego4D challenges in 2022 and 2023. He received a Best Student Paper nomination at CVPR 2017 and was named Best Paper Finalist at CVPR 2022. He is a Fellow of Singapore’s National Research Foundation and has been named on the Forbes 30 Under 30 Asia list for his contributions to artificial intelligence research.

Alongside his research and teaching duties, Dr. Shou serves regularly as Area Chair for major international conferences, including CVPR, ICCV, ECCV, and the ACM International Conference on Multimedia. Through his academic work, industry experience, and leadership in the research community, Dr. Mike Zheng Shou continues to shape the development of video intelligence systems that support a wide range of practical applications in technology and society.

Dr. Mike Zheng Shou’s vision is to build artificial intelligence systems that can understand, interpret, and generate video in ways that are useful, reliable, and practical for real-world applications. He aims to enable machines to recognise human actions and complex events from visual data so that technology can support areas such as transport, healthcare, safety, communication, and media creation. His long-term goal is to develop intelligent video systems that can work alongside people, improving decision making and automation while remaining accessible and responsible. Through research, education, and collaboration, he seeks to advance video intelligence so it can benefit both industry and society in meaningful and sustainable ways.

Dr. Mike Zheng Shou has received several major awards for his contributions to artificial intelligence research. In 2021, he was awarded the Singapore National Research Foundation Fellowship, one of the highest research honours for early career scientists in Singapore. He was named to the Forbes 30 Under 30 Asia list for his work in artificial intelligence. During his doctoral studies, he received the Wei Family Private Foundation Fellowship from 2014 to 2017. His research achievements include Best Student Paper nomination at CVPR 2017 and Best Paper Finalist at CVPR 2022. His teams have won first place in major international challenges including ActivityNet 2017, EPIC-Kitchens 2022, and Ego4D 2022 and 2023.