【海韵讲座】2024年第14期- Label-efficient Learning and Fine-grained Understanding for Large-scale Scenes
报告题目：Label-efficient Learning and Fine-grained Understanding for Large-scale Scenes
主讲人：马月昕 上海科技大学助理教授
报告时间：2024年04月11日（星期四）09:30-10:30
报告地点：翔安校区bwin必赢1号楼108会议室
报告摘要：
Recent advancements in NLP and 2D vision foundation models have spurred AI development to new heights. However, constructing 3D vision foundation models is challenging due to the high cost of acquiring and annotating 3D data. To tackle this, we've approached the problem from two angles. First, we've developed label-efficient learning algorithms tailored for 3D scenes. These algorithms excel in unsupervised learning, domain adaptation, label-free learning, and open vocabulary learning tasks. Second, we've focused on fine-grained understanding for human-centric scenes. We proposed several large-scale datasets and benchmarks for understanding dense crowds, human-object interactions, human motions. These efforts are significant for building 3D vision foundation models and are crucial for applications like autonomous driving, service robots, and human-robot collaboration.
报告人简介： 
Yuexin Ma is an Assistant Professor in SIST, ShanghaiTech University. She received the PhD degree from the University of Hong Kong. Her research interests include computer vision and artificial intelligence. Particularly, her current research focuses on 3D scene understanding, multi-modal learning, autonomous driving, human-robot cooperation, etc. She has published more than 60 papers on top journals and conferences, including Science Robotics, TPAMI, CVPR, ICCV, ECCV, AAAI, IJCAI, TOG, SIGGRAPH, etc., which have obtained more than 2500 citations. Her first-author paper had been awarded as one of the most influential AAAI-19 papers.
邀请人：人工智能系 温程璐教授