
李寅霖 女 中国科学院自动化研究所
电子邮件: yinlin.li@ia.ac.cn
通信地址: 北京市海淀区中关村东路95号自动化大厦
邮政编码:100190
研究领域
个人简介
李寅霖,中国科学院自动化研究所多模态人工智能系统全国重点实验室副研究员,主要从事计算机视觉、机器人视觉、机器人操作学习研究及应用工作。累计发表学术论文 25 篇 (SCI 13,EI 11),授权发明专利 2 项,其中,类脑视觉相关工作被IEEE前主席Toshio Fukuda教授,欧盟脑计划“神经机器人”负责人Alois C. Knoll教授分别引用并给出积极评价。作为项目负责人承担国家基金委青年基金项目等国家和应用领域基金/课题 3 项,主持海洋、交通、电网等领域的国家重大工程项目及应用开发项目,研发的视觉识别算法、软件系统、机器人平台在智慧苗圃、开放/复杂环境异常检测、工业目标检测识别等场景中应用,部分形成了产品级服务,获得中国自动化学会技术发明一等奖(4/8,所内第二完成人)。
招收全日制、非全日制硕士生
招收自动化、人工智能、计算机等相关专业本科高年级和研究生实习生
欢迎与我邮件联系交流
招生信息
招生专业
招生方向
教育背景
工作经历
工作简历
社会兼职
2017-08-20-今,CASE2017, Session Chair
2017-08-08-今,ICMA2017, Session Chair
2017-04-18-2017-04-19,“类脑智能机器人的未来”第592次香山科学会议, 会议秘书
专利与奖励
奖励信息
专利成果
(1) 基于人-物体交互弱监督标签的物体检测方法, 专利授权, 2021, 第 1 作者, 专利号: CN111931703B
(2)形状层级描述、平均形状和动态形状计算及形状匹配方法, 发明专利, 2015, 第 5 作者, 专利号: CN104794473A
出版信息
部分代表论文
(1)Enhancing Prompt Tuning with Multitask Embedding Reparameterization, ICONIP, 2024, 第 4 作者 通讯作者
(2)Enhancing Text Generation from Knowledge Graphs with Cross-Structure Attention Distillation, Engineering Applications of Artificial Intelligence, 2024, 第4作者
(3) Unsupervised offensive speech detection for multimedia based on multilingual BERT, International Journal Of Sensor Networks, 2024, 第 4 作者
(4) Enhancing Translation Ability of Large Language Models by Leveraging Task-Related Layers. Joint International Conference on Computational Linguistics, 2024, 第 3 作者
(5) Learning Pre-Grasp Sliding Manipulation of Flat Objects in Cluttered Environments, ICRA, 2023, 通信作者
(6) Sub-Instruction and Local Map Relationship Enhanced Model for Vision and Language Navigation, ICONIP, 2023, 通信作者
(7) Deep Learning based Moving Objects Segmentation: Recent Progress and Research Prospects, Machine Intelligence Research, 2023, 第 4 作者
(8) Learning Pre-grasp Pushing Manipulation of Wide and Flat Objects Using Binary Masks, ICONIP, 2022, 通信作者
(9) A Survey of Multifingered Robotic Manipulation: Biological Results, Structural Evolvements, and Learning Methods, FRONTIERS IN NEUROROBOTICS, 2022, 第 1 作者
(10) Activity and Relationship Modeling Driven Weakly Supervised Object Detection, ICPR, 2021, 第 1 作者
(11) A two-step method for 4-pin form-closure gripper with grasping force optimization, ASIAN JOURNAL OF CONTROL, 2021, 第 2 作者
(12) Event-triggered guaranteed cost control of time-varying delayed fuzzy systems with limited communication, MEASUREMENT & CONTROL, 2020, 第 1 作者
(13) Mode-dependent event-triggered tracking control for uncertain semi-Markov systems with application to vertical take-off and landing helicopter, MEASUREMENT & CONTROL, 2020, 第 2 作者
(14) 基于局部-全局一致性学习的弱监督人手分割, WEAKLY SUPERVISED HAND SEGMENTATION BASED ON LOCAL AND GLOBAL CONSISTENCY LEARNING, 计算机应用与软件, 2019, 第 2 作者
(15) Un-supervised and semi-supervised hand segmentation in egocentric images with noisy label learning, NEUROCOMPUTING, 2019, 第 1 作者
(16) Distributed mode-dependent state estimation for semi-markovian jumping neural networks via sampled data, INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE, 2019, 第 3 作者
(17) A Novel Biologically Inspired Visual Cognition Model: Automatic Extraction of Semantics, Formation of Integrated Concepts, and Reselection Features for Ambiguity, IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, 2018, 第 5 作者
(18) A Hierarchical Graph Matching Based Key Point Correspondence Method for Large Distance Rover Localization, 2017 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION (ICMA), 2017, 第 1 作者
(19) A biologically inspired model mimicking the memory and two distinct pathways of face perception, NEUROCOMPUTING, 2016, 第 4 作者
(20) Biologically Inspired Model for Visual Cognition Achieving Unsupervised Episodic and Semantic Feature Learning., IEEE TRANSACTIONS ON CYBERNETICS, 2016, 第 2 作者
(21) Grasp type understanding - classification, localization and clustering, PROCEEDINGS OF THE 2016 12TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA), 2016, 第 1 作者
(22) Enhanced HMAX model with feedforward feature learning for multiclass categorization., FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2015, 第 1 作者
(23) Biologically Inspired Visual Model With Preliminary Cognition and Active Attention Adjustment, IEEE TRANSACTIONS ON CYBERNETICS, 2015, 第 3 作者
(24) Introducing memory and association mechanism into a biologically inspired visual model., IEEE TRANSACTIONS ON CYBERNETICS, 2014, 第 2 作者