刘迪超

研究领域

所属学科1：人工智能

学科方向1：人工智能理论基础

研究方向：计算机视觉、交通系统中的智能视觉感知、医学图像处理

教育背景

工作经历

教育教学情况

1、承担课程情况

2、出版教材情况

3、承担教改项目情况

4、发表教改论文情况

科学研究情况

1、承担项目情况

2、发表学术论文情况

[1] Dichao Liu; Compact and Structurally Transparent Cervical Cytology with Geometry-Driven Features and Closed-Form Attention, European Conference on Computer Vision (ECCV), 2026: 624–641. CAAI-A. CCF-B. 计算机视觉三大顶会之一.

[2] Dichao Liu; Longjiao Zhao; Mingkai Gu; HaoJiang Chen; Ying Ji; Train Once, Apply Broadly: Low-Frequency Generative Augmentation for Driver Distraction Recognition under Photometric Shifts, IEEE International Conference on Robotics and Automation (ICRA), 2026. CAAI-A. CCF-B. 机器人领域顶级会议.

[3] Dichao Liu; Masatoshi Hori; Keitaro Sofue; Takamichi Murakami; Kenji Suzuki; Transparent AI for Liver Cancer Diagnosis in MRI with Explanations in LI-RADS Language, Radiological Society of North America Annual Meeting (RSNA), 2025, Chicago, USA. 放射学领域顶级学术年会（口头报告 Oral）.

[4] Dichao Liu*; Progressive Multi-Task Anti-Noise Learning and Distilling Frameworks for Fine-Grained Vehicle Recognition, IEEE Transactions on Intelligent Transportation Systems (TITS), 2024, 25(9): 10667–10678. 中科院一区(Top). JCR-Q1.

[5] Dichao Liu*; Yu Wang; Kenji Mase; Jien Kato; MT-ASM: a Multi-Task Attention Strengthening Model for Fine-Grained Object Recognition, Multimedia Systems (Multimed. Syst.), 2024, 30: 297.JCR-Q2.

[6] Pengyu Dai; Yafei Ou; Yuqiao Yang; Dichao Liu; Masahiro Hashimoto; Masahiro Jinzaki; Mototaka Miyake; Kenji Suzuki; SaSaMIM: Synthetic Anatomical Semantics-Aware Masked Image Modeling for Colon Tumor Segmentation in Non-contrast Abdominal Computed Tomography, Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024: 567–578.

[7] Dichao Liu*; Toshihiko Yamasaki; Yu Wang; Kenji Mase; Jien Kato; Toward Extremely Lightweight Distracted Driver Recognition with Distillation-Based Neural Architecture Search and Knowledge Transfer, IEEE Transactions on Intelligent Transportation Systems (TITS), 2023, 24(1): 764–777. 中科院一区(Top). JCR-Q1.

[8]Dichao Liu*; Longjiao Zhao; Yu Wang; Jien Kato; Learn from Each Other to Classify Better: Cross-layer Mutual Attention Learning for Fine-Grained Visual Classification, Pattern Recognition, 2023, 140: 109550. 中科院一区(Top). JCR-Q1.

[9] Dichao Liu*; Yu Wang; Kenji Mase; Jien Kato; Recursive Multi-Scale Channel-Spatial Attention for Fine-Grained Image Classification, IEICE Transactions on Information and Systems, 2022, E105.D(3): 713–726.ß

[10] Dichao Liu; Yu Wang; Kenji Mase; Jien Kato; Attention-Based Multi-Task Learning for Fine-Grained Image Classification, IEEE International Conference on Image Processing (ICIP), 2021.

[11]  Dichao Liu; Yu Wang; Jien Kato; Kenji Mase; Contrastively-Reinforced Attention Convolutional Neural Network for Fine-Grained Image Recognition, British Machine Vision Conference (BMVC), 2020.

3、获得授权专利情况

4、出版学术专著情况

社会兼职和服务情况

1、承担社会兼职情况

担任 The British Machine Vision Conference (BMVC)、International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 等国际会议审稿人，以及《Scientific Reports》《IET Intelligent Transport Systems》《IEICE TRANSACTIONS on Information and Systems》等 SCI 期刊审稿人。

2、社会服务情况

荣誉获奖情况

1、获得荣誉情况

2、获奖情况

IEEE Nagoya Section Student Paper Award, 2018

指导研究生情况

1、指导硕士研究生情况

2、指导博士研究生情况

3、指导留学生研究生情况

研究生招生情况

1、研究生招生学科、招生方向和名额

2、研究生招生要求

欢迎对计算机视觉、交通系统中的智能视觉感知以及医学图像处理等方向有兴趣的同学联系我，我会尽我所能提供良好的科研条件和耐心的指导，尊重并支持每一位学生的成长规划。

希望你有积极的人生态度，具备一定的动手能力和执行力，以及基本的编程和英文文献阅读能力，愿意踏实做事，在科研中不断打磨自己。

此外，我与东京大学、东京科学大学（原东京工业大学）、大连理工大学以及本田研究所等机构的科研工作者保持长期合作，希望未来有交流或深造机会的同学也欢迎与我联系。