基本信息:
姓名:王菡苑
职称:讲师
系所:人工智能系
研究领域:人工智能、计算机视觉、智慧医疗
电子邮箱:hanyuanwang5@outlook.com
王菡苑,计算机科学博士。2016年毕业于必赢565net官网获得通信工程学士学位,2019年毕业于电子科技大学获得通信与信息系统硕士学位,2024年毕业于英国布里斯托大学获得计算机科学博士学位。主要研究方向是人工智能、计算机视觉、智慧医疗等。共计发表8篇国际期刊、会议论文,申请发明专利4项,受邀参与TPAMI、TIP、BMVC等国际期刊会议的审稿工作。
教育经历:
1)2019-10至2024-01,英国布里斯托大学(University of Bristol),计算机科学,博士(研究方向:计算机视觉,导师:Professor Majid Mirmehdi, Professor Dima Damen)
2)2016-09至2019-06,电子科技大学, 通信与信息系统,硕士(研究方向:计算机视觉,导师:徐杰教授,博导)
3)2012-09至2016-06,必赢565net官网,通信工程,学士
科研与学术工作经历:
2024.08 — 至今,必赢565net官网,必赢565net官网,讲师
代表论文:
[1] Hanyuan Wang, Jie Xu, Linke Li, et al. Multi-scale fusion with context-aware network for object detection. In 24th International Conference on Pattern Recognition (ICPR). 2018.
[2] Xu Jie, Wei Wang, Hanyuan Wang, et al. Multi-model ensemble with rich spatial information for object detection. In Pattern recognition. 2020.
[3] Yu Chen, Jian Ma, Hanyuan Wang, et al. Discriminative representation loss for continual learning. In the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Continual Learning Challenges. 2020.
[4] Xu Jie, Hanyuan Wang, Mingzhu Xu et al. Feature-Enhanced Occlusion Perception Object Detection for Smart Cities. In Wireless Communications and Mobile Computing, 2021.
[5] Hanyuan Wang, Majid Mirmehdi, Dima Damen, et al. Refining action boundaries for one-stage detection. In 18th IEEE International Conference on Advanced Video and Signal based Surveillance, 2022.
[6] Hanyuan Wang, Dima Damen, Majid Mirmehdi, et al. TVNet: Temporal voting network for action localization. In 17th International Conference on Computer Vision Theory and Applications. 2022.
[7] Hanyuan Wang, Dima Damen, Majid Mirmehdi, et al. Gaussian boundary mechanism for ego-centric action detection. In the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Epic-kitchens-100 Challenges. 2022.
[8] Hanyuan Wang, Majid Mirmehdi, Dima Damen, et al.. Centre Stage: Centricity-based Audio-Visual Temporal Action Detection. In The 1st Workshop in Video Understanding and its Applications at the 34th British Machine Vision Conference (BMVC). 2023.
授权发明专利:
[1] 一种基于弱监督学习与遮挡感知的目标检测方法, 201910567434.2.
[2] 一种具有丰富空间信息的多模型集成目标检测方法, 201910567433.8.
[3] 一种基于GAN网络的视频描述及描述一致性判别方法, 201810987113.3.
[4] 一种基于时空及通道的多注意力机制视频描述方法, 201810988895.2.
科研项目:
[1] 基于对抗样本的弱监督目标检测技术研究,四川省高校支撑项目,主要参与人,已结项,2018 - 2019
[2] 智慧藤椒病虫害预警与指导服务系统,四川省绵阳市科技局项目,主要参与人,已结项,2017 - 2018
其他学术活动:
受邀担任审稿人:
IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI)
IEEE Transactions on Image Processing(TIP)
The British Machine Vision Conference(BMVC)
IEEE Access