2024: Google Academic Research Awards (South Asia & Southeast Asia)
2024: CelebA is awarded PAMI Mark Everingham Prize
2024: Asian Young Scientist Fellowship
2024: Wildlife Identification is selected as WAIC 2024 Young Researcher Outstanding Paper Award
2024: DGCNN is selected as Second Most Cited Paper in TOG History
2024: Winner of the Waymo Open Dataset Challenge
2023: MIT Technology Review Innovators under 35 Asia Pacific
2023: LaserMix is selected as PREMIA Best Student Paper Award
2023: DGCNN is selected as ICBS 2023 Frontiers of Science Award
2023: OmniObject3D is selected as CVPR 2023 Best Paper Award Candidate
2023: Robo3D is selected as ICLR 2023 SR4AD Workshop Best Paper Award
2022: CoCoOp is selected as Top-100 Most Cited AI Paper in 2022
2022: World’s Top 2% Scientists
2022: Winner of the Computer Vision in the Wild Challenge
2022: WAIC Yunfan Award
2022: Baidu AI Young Scholars in Computer Vision
2021: DGCNN is selected as Most Cited Paper within 5 Years in TOG
2021: DeepFashion is selected as Top-100 Most Cited Paper within 5 Years in CVPR
2021: AI 2000 Most Influential Scholars in Computer Vision
2020: Nanyang Assistant Professorship
2020: CelebA is selected as Top-10 Most Cited Paper Within 5 Years in ICCV
2020: Winner of the Video Virtual Try-on Challenge
2019: OLTR is selected as HKSTP Best Paper Award
2019: Winner of the FAIR Self-Supervision Challenge
2018: Winner of the COCO Detection Challenge
2017: Winner of the DAVIS Video Segmentation Challenge
2017: ICCV Young Researcher Award
2024 @ NeurIPS: From High-fidelity 3D Generative Models to Dynamic Embodied Learning
2024 @ ACM MM: Multi-Modal Generative AI with Foundation Models
2024 @ ECCV: From High-fidelity 3D Generative Models to Dynamic Embodied Learning
2024 @ CVPR: Multi-Modal Generative AI with Foundation Models
2024 @ CVPR: Vchitect: Efficient and Scalable Video Generation
2024 @ CVPR: 3DTopia: Foundation Ecosystem for 3D Generative Models
2024 @ CVPR: Building Open-World Multi-Modal AI Assistant
2024 @ CVPR: LMMs-Lab: Building Multimodal Intelligence
2024 @ WWW: Building Open-World Multi-Modal AI Assistant
2024 @ VALSE: Vchitect: Building Open Source Foundation System for Video Generation
2024 @ WACV: Multi-Modal Generative AI with Foundation Models
2023 @ ACM MM: Multi-Modal Generative AI with Foundation Models
2023 @ IJCAI: Towards Building Practical AI Assistant
2023 @ USTC: Multi-Modal Generative AI with Foundation Models
2023 @ CVPR: Prompting in Visual Generation
2023 @ CVPR: Towards Building Practical AI Assistant
2023 @ China3DV: Visual AIGC with Foundation Models
2023 @ SCA: AI-Driven Visual Content Generation
2022 @ PRCV: Robust and Data-Efficient 3D Perception
2022 @ ACCV: Human-Centric Visual Generation and Editing
2022 @ ICLR: Rethinking Generalization in Vision Models: Architectures, Modalities, and Beyond
2021 @ M2VIP: 3D Perception from Partial Observations
2021 @ AI Technology Summer School: AI-Synthesized Media and How to Detect Them
2020 @ ACM MM: Sensing, Understanding and Synthesizing Humans in an Open World
2019 @ ICCV: Learning Diverse Human Representation in the Wild
2019 @ VALSE: The Glimpse of Detectron: Dynamic Forwarding and Routing in Modern Detectors
2018 @ Berkeley: Learning Video Parsing, Tracking and Synthesis in the Wild
2017 @ VALSE: Deep Learning Human-centric Representation in the Wild
2016 @ Google: Deep Fashion Understanding
2015 @ CUHK: Formulating Structure for Vision Problems
2014 @ SIGGRAPH Asia: Fast Burst Images Denoising
2013 @ HUST: Pathological Microscopic Image Segmentation (in Chinese)