Image and Pixel-level Scene Understanding

2024年5月27日（周一）10:00 - 11:00

信息管理与工程学院308室

Shuting He（何淑婷） is currently a research fellow at Nanyang Technological University, Singapore. She received a B.Eng degree from Xiamen University, China in 2018, and a Ph.D. degree from Zhejiang University, China in 2023. She focuses on scene understanding (e.g. image/video identification, segmentation), multi-modal learning (e.g., vision-language), and low-shot learning. Her works are published in top-tier conferences and journals like CVPR, ICCV, TIP, etc.

Image and Pixel-level Scene Understanding

In the realm of computer vision, achieving a comprehensive understanding of complex visual scenes remains an ongoing challenge. This talk provides a holistic overview of the state-of-the-art techniques, their applications, and the potential impact of image and pixel-level scene understanding on various domains. This seminar will delve into foundational concepts of image and pixel-level scene understanding, encompassing a wide range of cutting-edge topics, such as fully supervised scene re-identification, few-shot and zero-shot scene segmentation, as well as language-guided scene segmentation. These research areas hold great promise for advancing autonomous driving, robotics, virtual reality, and embodied AI development.