副教授 硕士生导师
电子邮箱:
学历:博士研究生毕业
在职信息:在职
主要研究方向包括计算机视觉、人工智能算法等;
人工智能算法研究:深度学习算法、多模态大模型、小样本学习;侧重处理和理解图像、文本、音频、视频等多种模态的信息,实现跨模态的交互与推理,并力图在某些垂直领域设计理想通用的多模态模型。
计算机视觉:语义分割,3D语义分割,小样本图像语义分割,情感识别;研究侧重对自然场景的理解,以便应用于具身智能领域。
无线电信号识别:通信信号的识别分类;侧重将辐射源信号(如雷达或通信设备)进行检测并且实现个体识别和解析。
[1] Hai Min, Wei Jia, Yang Zhao, Wangmeng Zuo, Haibin Ling, Yuetong Luo: LATE: A Level Set Method Based on Local Approximation of Taylor Expansion for Segmenting Intensity Inhomogeneous Images. IEEE Transaction on Image Processing, 27(10):5016-5031,2018
[2] Hai Min, Li Xia, Junwei Han, Xiaofeng Wang, Qianqian Pan, Hao Fu, Hongzhi Wang, Stephen T.C. Wang, Hai Li: A multi-scale level set method based on local features for segmentation of images with intensity inhomogeneity, Pattern Recognition, 91:69-85, 2019,
[3] Hai Min, Jingting Lu, Wei Jia, Yang Zhao, Yuetong Luo: An Effective Local Regional Model Based on Salient Fitting for Image Segmentation. Neurocomputing 311:245-259,2018
[4] Hai Min, Wei Jia*, Xiao-Feng Wang, Yang Zhao, Jing-Ting Lu, Yue-Tong Luo: A Polynomial Piecewise Constant Approximation Method Based on Dual Constraint Relaxation for Segmenting Images with Intensity Inhomogeneity. Pattern Recognition, 73(1):15-32(2018)
[5] Hai Min, Xiao-Feng Wang*, De-Shuang Huang, Wei Jia, “A novel dual minimization based level set method for image segmentation” Neurocomputing 2016
[6] Hai Min, Wei Jia*, Xiao-Feng Wang, Yang Zhao, Rong-Xiang Hu, Yue-Tong Luo, Feng Xue, Jing-Ting Lu: An Intensity-Texture model based level set method for image segmentation. Pattern Recognition 48(4): 1547-1562 (2015)