危辉 - 复旦大学 - 计算机科学技术学院

个人简介

危辉，复旦大学计算机科学技术学院教授，博士生导师。1998年7月毕业于北京航空航天大学计算机科学系，先后师从导师怀进鹏院士和何新贵院士，获计算机科学理论与软件专业工学博士学位。同年9月进入浙江大学计算机科学系人工智能研究所，师从我国著名人工智能专家潘云鹤院士进行为期两年的博士后研究工作。2000年11月期满出站后进入复旦大学计算机科学技术系从事教学与科研工作。2000年10月在浙江大学晋升为副教授，2005年4月在复旦大学晋升为教授。自1993年起从事非单调逻辑与不确定性推理研究，1995年后受认知心理学启发从事人工智能与认知科学或说基于认知科学背景的人工智能研究，致力于基于神经生物学和认知心理学机制的神经视觉算法模型和神经编码机制研究，以及基于认知机制约束的人工智能基础范型研究，是国内最早独立开展且持续不间断开展类脑计算研究的小组之一，包括视觉神经计算模型和脉冲神经元回路结构与编码机制研究。主持或作为主要成员参与的研究课题有973计划课题、973前期专项、国防973课题专题、国家自然科学基金、国家自然科学基金重点、国家自然科学基金重大研究计划课题、国防预研课题、上海市科委重大专项、上海市青年科技启明星计划课题等。作为第一作者或通信作者在IEEE Transactions系列、Elsevier系列、Springer系列等国际学术期刊上发表完全由国内独立完成的计算机科学领域SCI论文60余篇，出版学术专著《人工智能形式概念系统》和《认知相关性与智能模型构造的系统观点》。自2001年起承担复旦大学本科和研究生的教学工作，到目前为止按时间顺序独立讲授离散数学2学期、高等数理逻辑4学期、人工智能与认知科学5学期、人工智能或高级人工智能55学期/次、从计算到智能20学期、认知科学导论10学期。

研究领域

认知科学与人工智能人工智能基础类脑计算神经视觉计算模型神经回路与编码模型智能机器人

近期论文

查看导师新发文章（温馨提示：请注意重名现象，建议点开原文通过作者单位确认）

Deep subspace image clustering network with self-expression and self-supervision .Applied Intelligence .2023 ,53 (4) :4859-4873 A global generalized maximum coverage-based solution to the non-model-based view planning problem for object reconstruction .Computer Vision and Image Understanding .2023 ,226 An accurate stereo matching method based on color segments and edges .Pattern Recognition .2023 ,133 Curved Alleyway Understanding Based on Monocular Vision in Street Scenes .IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS .2022 ,23 (7) :8544-8563 An Integration Model Based on Non-classical Receptive Fields .SIXTH INTERNATIONAL SYMPOSIUM ON NEURAL NETWORKS (ISNN 2009) .2009 ,56 :451-459 Neural encoding based on frequency states using multi-spike train data Creating Efficient Visual Codebook Ensembles for Object Categorization Periodic Motion Detection with ROI-based Similarity Measure and Extrema-based Reference Selection Detection of community structure in networks based on community coefficients A GMRES Method for Solving Fuzzy Linear Equations 基于轮廓线统计量的前景分割Markov随机场模型 Enhance knowledge acquisition with theory architecture 基于数学形态学的聚类集成算法 Analyzing topological characteristics of neuronal functional networks in the rat brain Multiscale Triangular Centroid Distance for Shape-Based Plant Leaf Recognition Computational Model for Global Contour Precedence Based on Primary Visual Cortex Mechanisms Indoor scene understanding based on manhattan and non-manhattan projection of spatial right-angles The Evolving of Concept System based on Representation Redescription 一种基于MAS和GIS平台的城市人口变迁模拟仿真方法 A Computational Retina Model and Its Self-adjustment Property An UML-based Describing and Organizing Approach for Complex Domain Knowledge and its Usage in Composite Materials Manufacture Multilayer and Multipathway Simulation on Retina 基于人造物体直线段结构特征的不变性识别 Main retina information processing pathways modeling A model of image representation based on non-classical receptive field Multi-scale Image Analysis Based on Non-Classical Receptive Field Mechanism A Neural Circuit Model for nCRF's Dynamic Adjustment and its Application on Image Representation A Neural Computation Model Based on nCRF and Reverse Control Mechanism A New Model to Simulate the Formation of Orientation Columns Map in Visual Cortex A bio-inspired model for image representation and image analysis A neurual dynamic model based on activation diffusion and a micro-explanation for cognitive operations Soaking with uncertainty for problem solving A MATHEMATICAL MODEL OF A RETINA GANGLION CELL' RESPONSE TO CONTRAST EDGES Main retina information processing pathways modeling A Scale-Changeable Image Analysis Method A Group-decision Making Model of Orientation Detection An Image Representation Method Based on Retina Mechanism for the Promotion of SIFT and Segmentation An Orientation Detection Model Based on Fitting from Multiple Local Hypotheses Compact Image Representation Model Based on Both nCRF and Reverse Control Mechanisms A neural dynamic model based on activation diffusion and a micro-explanation for cognitive operations A Retina-Inspired Neurocomputing Circuit for Image Representation A General Image Representation Scheme and Its Improvement for Image Analysis A Neurocomputing Model for Ganglion Cell's Color Opponency Mechanism and Its Application in Image Analysis A shape recognition method based on graph- and line-contexts A line-context based object recognition method A ga-based solution for the combination optimization in the contour formation Learning and Representing Object Shape Through an Array of Orientation Columns A Model of V4 Neurons Based on Sparse Coding A Line-Context Based Object Recognition Method Shape Description and Recognition Method Inspired by the Primary Visual Cortex A SHAPE-BASED OBJECT CLASS DETECTION MODEL USING LOCAL SCALE-INVARIANT FRAGMENT FEATURE V4 Neural Network Model for Visual Saliency and Discriminative Local Representation of Shapes Local Image Descriptor Inspired by Visual Cortex A Bio-inspired Early-Level Image Representation and Its Contribution to Object Recognition A Genetic-Algorithm-Based Explicit Description of Object Contour and its Ability to Facilitate Recognition V4 Neural Network Model for Shape-Based Feature Extraction and Object Discrimination A Bio-Inspired Method for Object Representation 如何看待人工智能类脑计算 Contour Representation and Shape Matching Based on Mechanism of Visual Cortex A ganglion-cell-based primary image representation method and its contribution to object recognition A BIO-INSPIRED INTEGRATION METHOD FOR OBJECT SEMANTIC REPRESENTATION 人工智能离我们很近了吗? Contour segment grouping for object detection Training a Two-choice Decision-making Model with Environment Feedback 拱序列的曲线描述与匹配 Visual Navigation Using Projection of Spatial Right-Angle In Indoor Environment A Visual Cortex-Inspired Imaging-Sensor Architecture and Its Application in Real-Time Processing A Temporal Signal-Processing Circuit Based on Spiking Neuron and Synaptic Learning 人工智能盛宴下的隐忧 Binocular Matching Model Based on Hierarchical V1 and V2 Receptive Fields With Color, Orientation, and Region Feature Information Vision-guided fine-operation of robot and its application in eight-puzzle game