Jiafan Zhuang               庄嘉帆

  Jiafan Zhuang               庄嘉帆

Shantou University

🤵🏻 About me

I received the B.Eng. degree and PhD degree from University of Science and Technology of China (USTC) advised by Prof. Zilei Wang (王子磊).

I joined Shantou University as a lecturer in Sept. 2022, leading a computer vision research group. If you are seeking any form of academic cooperation, please feel free to email me at jfzhuang@stu.edu.cn.

My research interests include:

  • Video Analysis
  • Unsupervised/Semi-supervised/Weakly-supervised Learning
  • Domain Adaptation/Generalization
  • UAV/Medical/Industrial Vision Applications

🔥 News

  • 2024.12:  🎉🎉 1 paper has been accepted by AAMAS
  • 2024.02:  🎉🎉 1 paper has been accepted by CVPR
  • 2024.09:  🎉🎉 1 paper has been accepted by BigDIA as the Best Student Paper
  • 2024.10:  🎉🎉 1 paper has been accepted by CCIR for an Oral Presentation

📝 Publications

Conference Paper

  • Robust Policy Learning for Multi-UAV Collision Avoidance with Causal Feature Selection. Jiafan Zhuang, Gaofei Han, Zihao Xia, Che Lin, Boxi Wang, Wenji Li, Dongliang Wang, Zhifeng Hao, Ruichu Cai, Zhun Fan*. AAMAS, 2024. PDF
  • Attention-Driven Mixing Perception based on Object Detection for UAV Distance Estimation. Duan Yuan, Yicheng Luo, Rihong Yan, Jiafan Zhuang*, Zhun Fan*. CCIR, 2024. PDF
  • Deep Reinforcement Learning based Multi-UAV Collision Avoidance with Causal Representation Learning. Gaofei Han, Qingling Wu, Boxi Wang, Che Lin, Jiafan Zhuang*, Wenji Li*, Zhifeng Hao, Zhun Fan*. BigDIA, 2024. PDF
  • Infer from What You Have Seen Before: Temporally-dependent Classifier for Semi-supervised Video Semantic Segmentation. Jiafan Zhuang, Zilei Wang*, Yixin Zhang, Zhun Fan. CVPR, 2024. PDF
  • A Multi-Agent Control Model Based on Gene Regulatory Network. Wenji Li, Pengxiang Ren, Zhaojun Wang, Dongliang Wang, Biao Xu, Chaotao Guan, Chuangbin Chen, Jiafan Zhuang and Zhun Fan*. BigDIA, 2023. PDF
  • A Constrained Multi-objective Evolutionary Algorithm Based on Early Convergence Followed by Diversity. Wenji Li, Yifeng Qiu, Zhaojun Wang, Qinchang Zhang, Ruitao Mai, Biao Xu, Yue Zhang, Jiafan Zhuang, Zhun Fan*. DOCS, 2023. PDF
  • Exploit Domain-robust Optical Flow in Domain Adaptive Video Semantic Segmentation. Yuan Gao, Zilei Wang*, Jiafan Zhuang, Yixin Zhang, Junjie Li. AAAI, 2023. PDF
  • Towards Effective Instance Discrimination Contrastive Loss for Unsupervised Domain Adaptation. Yixin Zhang, Zilei Wang*, Junjie Li, Jiafan Zhuang, Zihan Lin. ICCV, 2023. PDF
  • Semi-Supervised Video Semantic Segmentation with Inter-Frame Feature Reconstruction. Jiafan Zhuang, Zilei Wang*, Yuan Gao. CVPR, 2022. PDF
  • 5th Place Solution for VSPW 2021 Challenge. Jiafan Zhuang, Yixin Zhang, Xinyu Hu, Junjie Li, Zilei Wang*. ICCVW, 2021. PDF
  • Efficient License Plate Recognition via Holistic Position Attention. Yesheng Zhang, Zilei Wang*, Jiafan Zhuang. AAAI, 2021. PDF
  • Towards Human-Level License Plate Recognition. Jiafan Zhuang, Saihui Hou, Zilei Wang*, Zheng-Jun Zha. ECCV, 2018. PDF

Journal Paper

  • Paying more attention on backgrounds: Background-centric attention for UAV detection. Xiuxiu Lin, Yusu Niu, Xinran Yu, Zhun Fan, Jiafan Zhuang, An-Min Zhou*. Neural Networks, 2025. PDF
  • UAV Collision Avoidance in Unknown Scenarios with Causal Representation Disentanglement. Zhun Fan, Zihao Xia, Che Lin, Wenji Li, Dongliang Wang, Yindong Chen, Zhifeng Hao, Ruichu Cai, Jiafan Zhuang*. Drones, 2024. PDF
  • Frequency and content dual stream network for image dehazing. Meihua Wang, Lei Liao, De Huang, Zhun Fan*, Jiafan Zhuang, Wensheng Zhang. Image and Vision Computing, 2023. PDF
  • Efficient Focus Autoencoders for Fast Autonomous Flight in Intricate Wild Scenarios. Kaiyu Hu, Huanli Li, Jiafan Zhuang, Zhifeng Hao, Zhun Fan*. Drones, 2023. PDF
  • Modular design automation of the morphologies, controllers, and vision systems for intelligent robots: a survey. Wenji Li, Zhaojun Wang, Ruitao Mai, Pengxiang Ren, Qinchang Zhang, Yutao Zhou, Ning Xu, Jiafan Zhuang, Bin Xin, Liang Gao, Zhifeng Hao and Zhun Fan*. Visual Intelligence, 2023. PDF
  • Video Semantic Segmentation with Distortion-Aware Feature Correction. Jiafan Zhuang, Zilei Wang*, Bingke Wang. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021. PDF

📝 Patents

  • 范衠、魏沛蔚、郑家雯、钟礼壕、庄嘉帆、亢晓丽、王亚夫、郑策，基于因果特征选择的图神经网络精细化斜视诊断方法、系统、设备及介质，申请号：CN202411944815.5，申请日：2024.12.27，法律状态：已受理
  • 李文姬; 张顺杰; 王诏君; 关朝滔; 王栋梁; 庄嘉帆; 郝志峰; 范衠，一种机器人及其运动控制方法、装置，申请号：CN202411527520.8，申请日：2024.10.30，法律状态：实审中
  • 李文姬; 王博禧; 庄嘉帆; 王诏君; 王栋梁; 郝志峰; 范衠，基于因果表征学习的无人机集群围捕控制方法及系统，申请号：CN202411456225.8，申请日：2024.10.18，法律状态：实审中
  • 庄嘉帆; 伍庆玲; 严日鸿; 朱贵杰; 李文姬; 范衠，基于因果解耦的道路裂缝检测方法、电子设备及存储介质，申请号：CN202411368410.1，申请日：2024.09.29，法律状态：实审中

  • 王子磊、庄嘉帆，轻量级视频语义分割方法、系统、设备及存储介质，申请号：CN202210068739.0，申请日：2022.01.20，法律状态：实审中

  • 王诏君; 丁辰汶; 李文姬; 姚俊杰; 庄嘉帆; 范衠，一种地层形态建模方法、系统、电子设备及存储介质，专利号：CN119068132B，授权日：2025.04.11，法律状态：已授权
  • 王诏君; 丁辰汶; 李文姬; 姚俊杰; 庄嘉帆; 范衠，井眼轨道设计参数确定方法、系统、电子设备及存储介质，专利号：CN119066812B，授权日：2025.04.11，法律状态：已授权
  • 庄嘉帆; 郑家雯; 范衠，一种视频语义分割网络的半监督训练方法、设备及介质，专利号：CN118537556B，授权日：2025.01.14，法律状态：已授权
  • 庄嘉帆; 陈创彬; 李文姬; 任鹏翔; 王诏君; 关朝滔; 王栋梁; 范衠，一种集群围捕控制方法、电子设备及存储介质，专利号：CN118938657A，授权日：2024.11.12，法律状态：已授权
  • 范衠; 向纯斌; 李原; 周于涛; 甘飘; 黄书山; 易贤; 杨永泽; 陶通涓; 曹宇轩; 罗贤; 庄嘉帆; 赵雷; 刘进超; 王栋梁; 黄伟鑫; 张承钿; 朱贵杰; 李文姬; 郝志峰; 曹作林，基于多特征融合的工件焊缝位置检测方法、系统及设备，专利号：CN118710885A，授权日：2024.09.27，法律状态：已授权
  • 范衠; 向纯斌; 李原; 甘飘; 周于涛; 黄书山; 杨永泽; 陶通涓; 曹宇轩; 韦选豪; 庄嘉帆; 赵雷; 刘进超; 王栋梁; 黄伟鑫; 张承钿; 朱贵杰; 李文姬; 郝志峰; 曹作林，基于多特征融合的工件焊缝识别方法、系统、设备及介质，专利号：CN118691799A，授权日：2024.09.24，法律状态：已授权
  • 庄嘉帆; 韩高飞; 夏子皓; 林澈; 李文姬; 范衠; 郝志峰，基于CFS的多无人机避障方法、系统、装置及介质，专利号：CN118311976B，授权日：2024.09.27，法律状态：已授权
  • 王子磊、庄嘉帆，视频语义分割网络的训练方法、系统、设备及存储介质，专利号：CN114494973B，授权日：2024.03.29，法律状态：已授权
  • 王子磊、庄嘉帆，高效准确的车牌识别方法，专利号：CN107239778B，授权日：2020.01.03，法律状态：已授权

📝 Projects

  • 广东省自然科学基金-面上项目（No.2025A1515010800），“知识与数据联合驱动的斜视自动诊断系统研究”，主持，2025.01-2027.12
  • 国家自然科学基金青年项目 (NSFC, No.62406186)，“结构与运动知识引导的视频语义分割方法研究”，主持，2025.01-2027.12
  • 国家自然科学基金面上项目 (NSFC, No.62476163)，“因果图结构熵优化的自动机器学习方法研究”，参与，2025.01-2028.12
  • 汕头大学科研启动项目 (NTF22030)，“精确高效的视频语义分析模型及学习方法研究”，主持，2022.09-2025.8
  • 国家自然科学基金面上项目 (NSFC, No.62176246)，“时空结构知识引导的视频语义分析模型及学习方法”，参与，2022.01-2025.12

📖 Educations

  • 2017.09 - 2022.06, PhD, University of Science and Technology of China.
  • 2013.09 - 2017.06, B.Eng, University of Science and Technology of China.