Yi-Hsuan Tsai
Email: wasidennis [at] gmail [dot] com
I am the AI/ML Tech Lead Manager at Google, working on edge AI for perception and scene understanding. Please contact me if you are interested in our full-time or research internship positions.
Biography
I was the Director of AI at Phiar (acquired by Google), where I lead the AI team to improve real-world AR navigation in vehicles. Before this, I was a senior researcher at NEC Laboratories America, working with Prof. Manmohan Chandraker on fundamental computer vision/deep learning research.
I received my Ph.D in the Department of Electrical Engineering and Computer Science at University of California, Merced in 2017 advised by Prof. Ming-Hsuan Yang in the Vision and Learning Lab. Before coming to UC Merced in 2012, I received my M.S. degree in the Department of Electrical Engineering and Computer Science from University of Michigan, Ann Arbor in 2012, and my B.S. degree in the Department of Electronics Engineering from National Chiao-Tung University, Hsinchu, Taiwan in 2009.
Google Scholar | Github | LinkedIn
CV & Research Statement (upon request)
Research Interest
Multimodal Learning, Scene Understanding, Video Analysis, Representation Learning
Professional Activity
Area Chair/Senior Program Committee: CVPR (2023, 2024), NeurIPS (2023, 2024), ICLR 2024, ICCV 2023, WACV (2020, 2023), AAAI (2021-2024), BMVC 2021, IJCAI 2021
Reviewer Award: ICLR'23, CVPR'21, ECCV'20, ICCV'19, BMVC'19, CVPR'18, ICCV'17, ECCV'16
News & Events
07/2024: Three ECCV'24 papers are accepted on "3D Object Detection", "3D Scene Editing", "Room Layout Estimation". Stay tuned!
06/2024: We host a Atomic Activity Recognition Challenge in the Road++ Workshop at ECCV'24. Join us if you are interested!
05/2024: I will serve as Area Chair for NeurIPS'24.
04/2024: Check our new approach on 3D Open-world Segmentation via Gaussian Splatting [Project Page].Â
02/2024: Three CVPR'24 papers are accepted on " Temporal 3D Object Detection", "Text-driven Image Editing", "Activity Recognition in Traffic Scenes".
12/2023: Check our new works on 3D object detection via weakly-supervised learning and temporal reasoning.
12/2023: Check our new methods on text-driven editing for 2D images and 3D scenes.
12/2023: Check our new benchmark dataset and framework for "Atomic Activity Recognition in Traffic Scenes".
10/2023: I will serve as Area Chair for ICLR'24 and CVPR'24.
09/2023: One NeurIPS'23 paper on "diffusion model for semi-supervised 3D object detection" is accepted [Project Page] [Paper].
08/2023: Give a talk at "AI Engineering Job Fair" for learning "Skill set and Mindset of an AI Scientist and Engineer".
08/2023: I will serve as Senior Program Committee for AAAI'24.
07/2023: One ICCV'23 paper on "monocular 3D object tracking" is accepted [Project Page] [Paper].