About me

I am a PhD in Electrical and Computer Engineering from the University of Washington - Seattle, where my dissertation focused on “Building Multimodal AI Systems for Perceiving and Reasoning in 3D Space”. I also hold a Master of Science degree in Electrical and Computer Engineering from the University of Washington, and a Bachelor degree from the National Chiao Tung University in Taiwan.

I will be joining Amazon as an Applied Scientist in June.

News

• [May. 2026] Successfully defended my PhD dissertation "Building Multimodal AI Systems for Perceiving and Reasoning in 3D Space"!
• [Feb. 2026] One main paper and one finding paper accepted by CVPR.
• [Dec. 2025] SAMURAI is accepted by IEEE Transactions on Image Processing!
• [Oct. 2025] Invited talk at National Yang Ming Chiao Tung University (NYCU), College of Artificial Intelligence with topic "Spatial Intelligence and 3D Scene Understanding".
• [Jun. 2025] My first author paper "Warehouse Spatial Question Answering with LLM Agent" is accepted by ICCV AI City Challenge Workshop.
• [Jun. 2025] Our team won the 1st place of 2025 ICCV AI City Challenge Track 3: Warehouse Spatial Question Answering!
• [Jun. 2025] My first author paper "ToSA: Token Merging with Spatial Awareness" is accepted by IROS 2025.
• [Jun. 2025] One paper accepted by ICCV.
• [Jun. 2025] Started my internship at Amazon CoRo Visual Perception Team.
• [Jun. 2025] Passed the general exam!
• [May. 2025] Two first author papers accepted by CVPR 2025 3D LLM/VLA Workshop.
• [Feb. 2025] My first author paper "Zero-shot 3D Question Answering via Voxel-based Dynamic Token Compression" is accepted by CVPR 2025.
• [Dec. 2024] Our team won the 2nd place of 2025 SkiTB Visual Tracking Challenge, in conjunction with WACV 2025.
• [Dec. 2024] My first author paper "MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking" is accepted by ICASSP 2025.
• [Nov. 2024] We release SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory, project page is available at here.
• [Oct. 2024] Our team won the 1st place of 2024 MMVPR Tracking Challenge in Multi-modal Visual Object Tracking.
• [Aug. 2024] My first author paper "ToddlerAct: A Toddler Action Recognition Dataset for Gross Motor Development Assessment" is accepted by 2024 ECCV Workshop.
• [Jul. 2024] Our paper "RT-Pose: A 4D Radar-Tensor based 3D Human Pose Estimation and Localization Benchmark." is accepted by ECCV 2024.
• [Jun. 2024] Started my internship at Amazon CoRo Visual Perception Team.
• [Apr. 2024] My co-first author paper "An Online Approach and Evaluation Method for Tracking People Across Cameras in Extremely Long Video Sequence" is accepted by 2024 CVPR AI City Challenge Workshop.
• [Apr. 2024] Our paper "Boosting Online 3D Multi-Object Tracking through Camera-Radar Cross Check" is accepted by 2024 IEEE Intelligent Vehicles Symposium.
• [Apr. 2024] Invited talk at National Chiayi University (NCYU) with topic "Deep Learning in Video Understanding: Applications, Challenges and Trend".
• [Jan. 2024] Our paper "A Density-Guided Temporal Attention Transformer for Indiscernible Object Counting in Underwater Videos" is accepted by IEEE ICASSP 2024.
• [Nov. 2023] Passed the qualifying exam. One down, two to go!
• [Nov. 2023] Our paper "Sea You Later: Metadata-Guided Long-Term Re-Identification for UAV-Based Multi-Object Tracking" is accepted by the 2024 WACV 2nd Workshop on Maritime Computer Vision. It achieves State-Of-The-Art performance on the SeaDroneSee UAV Multi-Object Tracking dataset!
• [Nov. 2023] Our team won the 1st place of 2024 MaCVi Challenge UAV Multi-Object Tracking and USV Multi-Object Tracking tracks!
• [Nov. 2023] My first author paper "Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in Sports" is accepted by the 2024 WACV Real-World Surveillance: Applications and Challenges Workshop. It achieves State-Of-The-Art performance on the SportsMOT dataset!
• [Jun. 2023] My co-first author paper "Enhancing Multi-Camera People Tracking with Anchor-Guided Clustering and Spatio-Temporal Consistency ID Re-Assignment" is accepted by the 2023 CVPR AI City Challenge Workshop!
• [Mar. 2023] Our team won the 1st place of 2023 AI City Challenge Track 1 in Multi-Camera People Tracking!
• [Mar. 2023] Started my graduate study at University of Washington as a PhD student working at the Information Processing Lab advised by prof. Jenq-Neng Hwang.
• [Feb. 2023] Started my intership at Chimei Motor Electronics Research and Development department.
• [Jan. 2023] Gave an oral presenation at the 2023 WACV CV4WS Workshop for our paper "Observation Centric and Central Distance Recovery for Athlete Tracking".
• [Dec. 2022] Successfully defended my master thesis "Observation Centric and Central Distance Recovery for Tracking of Sports Athletes"!
• [Dec. 2022] My first-author paper "Observation Centric and Central Distance Recovery for Athlete Tracking" is accepted by the 2023 WACV CV4WS Workshop!
• [Aug. 2022] Our team won the 3rd place of 2022 ECCV SportsMOT Challenge on Multi-actor Tracking!
• [Sep. 2021] Started my graduate study at University of Washington as a master student.