Xie Xiaohua

Professor

Email: xiexiaoh6@mail.sysu.edu.cn

Address: A611

教师简介: 

谢晓华（Xiaohua Xie），教授（Professor）、博士生导师、广东省信息安全技术重点实验室副主任、广东省科技青年拔尖人才。

主持5项国家级科研项目（含重点项目1项）、3项省级项目（含重点项目1项）及多项省市重大任务；以骨干成员参与国家重大/重点项目5项。在包括IEEE TPAMI、IJCV、ACM Computing Surveys、IEEE TIP、IEEE TIFS、IEEE TVCG、IEEE TCSVT、IEEE TKDE、PR、ICML、NeurIPS、ICCV、CVPR、AAAI、IJCAI在内的国际著名刊物和会议发表论文150篇（其中CCF-A/中科院一区论文85篇），单篇论文最高引用超过1800次，拥有国家授权发明专利40件。核心技术支撑研发的嵌入式行人分析智能摄像机在十多个国家获得应用。获广东省自然科学一等奖、教育部自然科学二等奖、广东省自然科学二等奖、中国电子学会及中山大学优秀硕士学位论文指导老师奖、腾讯犀牛鸟杰出导师奖。

指导学生(部分与赖剑煌教授共同指导)获奖情况：

——2024年董钧昊《基于对抗样本的人脸图像防篡改与识别系统防御》获评中国电子学会优秀硕士学位论文（激励计划）

——2024年国际模式识别会议(ICPR)最佳学生论文奖（陈泓栩）

——2024年全国生物特征识别大会(CCBR)最佳学生论文奖（陈贤彪）

——2023年度腾讯犀牛鸟精英人才计划杰出奖（张鹏泽）

——2023年董钧昊《基于对抗样本的人脸图像防篡改与识别系统防御》获评中山大学优秀硕士学位论文

——2023年博士研究生国家奖学金（张鹏泽）

——2023年广东省研究生学术论坛人工智能技术及应用论坛一等奖（郑有为，广东省学位委员办公室主办）

——2023年广东省研究生学术论坛人工智能技术及应用论坛二等奖（陈韵，广东省学位委员办公室主办）

——2023年郑有为《基于扩散模型的人像语义编辑》获评中山大学优秀本科毕业论文

——2019年张鹏泽《基于生成对抗网络的视频动作迁移》获评中山大学优秀本科毕业论文

——2018年陈海城《基于字典学习的三角网格优化》获评中山大学优秀本科毕业论文

——2017年罗川璞《非参数化形状初始化的本征图像估计方法》获评中山大学优秀本科毕业论文

——2019年全国生物特征识别大会(CCBR)最佳学生论文奖（郭彤彤）

——2017年全国计算机视觉大会(CCCV)最佳学生论文奖（卓嘉璇）

——2015年中国智能物联系统会议优秀学生论文奖（刘晓）

——2021年“羊城工匠杯”人工智能训练师大赛二等奖（张权、周华君、胡仕腾）

——2020年中国图像图形学会（CSIG）首届图像图形技术挑战赛“遮挡目标检测”赛道第一名（张鹏泽、钱锦浩、张鑫）

—— 2020年中国图像图形学会（CSIG）首届图像图形技术挑战赛“群目标检测”赛道第一名（张鹏泽、钱锦浩、张鑫）

——2019年中国研究生智慧城市技术大赛赛道第二名（梁文琦为队长的“唱跳rap打码队”）

——2019年国际图像图形学学术会议(ICIG)“小目标检测”竞赛一等奖（陈家鑫、许伟鸿、郭彤彤）

——2019年中国模式识别与计算机视觉会议(PRCV)"短视频内容智能制作技术"挑战赛“人体生成”一等奖（张鹏泽、赖贤城）

——2019年中国模式识别与计算机视觉会议(PRCV)"短视频内容智能制作技术"挑战赛“人脸生成”二等奖（张鹏泽、赖贤城）

——2016年中国研究生智慧城市技术大赛“跨摄像机行人识别”赛道二等奖（陆瑞智、何炜雄、卓嘉璇、郭春梅）

——2016年中国研究生智慧城市技术大赛“人脸检测与识别”赛道二等奖（冯展祥、王晓、黄锐、王广聪）

——2016年中国研究生智慧城市技术大赛“异常行为识别”赛道二等奖（刘晓、谷扬、李传俊、朱允全）


博士/硕士招生方向：计算机视觉与模式识别、机器学习

要求：真心喜欢科研，具有不错的编程基础，能吃苦耐劳，懂得尊重团队其他成员

长期欢迎申请博士后、本科生实习

研究领域: 

计算机视觉、图像处理、模式识别、机器学习

目前专注于：视频图像处理、生成、识别；AI安全（AI模型对抗攻防）；嵌入式视觉智能终端；跨相机分析；无人航拍监控；类脑视觉

工作经历: 

  • 2015.07-至今, 中山大学，特聘研究员、副教授、教授
  • 2011.02-2015.07, 中国科学院深圳先进技术研究院，助理研究员、副研究员

海外经历: 

2009.09-2010.09, 国家公派留学，加拿大Concordia大学计算机科学系

 

获奖及荣誉: 

  • 2017年广东省重大人才工程青年项目
  • 2018年度广东省科学技术奖（自然科学奖）一等奖
  • 2018年度教育部高等学校科学研究优秀成果奖（自然科学）二等奖
  • 2020年度广东省科学技术奖（自然科学奖）二等奖
  • 2022年度广东省电子信息行业科技进步二等奖
  • 2022年度广东省公共安全技术防范协会安防技术发明二等奖
  • 2023年中山大学优秀硕士学位论文指导老师奖
  • 2024年中国电子学会优秀硕士学位论文（激励计划）指导老师奖
  • 2024年腾讯犀牛鸟杰出导师奖

科研项目: 

  1. 视觉 xxx模型, 国家重点项目（主持）
  2. 图像生成驱动的物理场景内在属性感知及在视觉识别上的应用，国家自然科学基金面上项目（主持）
  3. 基于场景本征属性感知的图像重渲染研究，国家自然科学基金面上项目（主持）
  4. 基于 xxx 多机协同跟踪，国家平台子课题（主持）
  5. 基于上下文感知的部件组装三维建模，国家自然科学基金青年项目（主持）
  6. 基于颜色与深度感知的场景本征属性重建研究，广东省自然科学基金重点项目（主持）
  7. 广东省重大人才工程青年项目（主持）
  8. 基于总变分模型的图像光照归一化研究，广东省自然科学基金博士启动项目 （主持）
  9. 基于深度表征学习的图像重渲染，中央高校基本科研业务费专项（主持）
  10. 可敏捷定制的智能视觉处理器及系统应用，广东省重点研发项目（中大方主持人）
  11. 跨域智慧警务装备与监测平台研究及应用，广州市重点研发项目（中大方主持人）
  12. 基于智能摄像头阵列协同的博物馆展馆管理应用示范，广东省区域创新能力与支撑保障体系建设项目（中大方主持人）
  13. 面向多警种协同的综合实战应用系统，广州市对外重大合作项目（中大方主持人）
  14. 面向智慧城市的人脸识别身份认证互联网+云平台系统建设及示范应用，智慧广州专项资金项目（中大方主持人）
  15. 基于海量人脸图像深度学习的身份核验系列产品研发应用，广州市科技计划重点项目（中大方主持人）
  16. 多任务迁移学习及其在小样本图像理解中的应用，广东省粤港澳大湾区国际科技创新中心建设项目（中大方主持人）

主要学术兼职: 

  • 广东省信息安全技术重点实验室副主任
  • 中国图象图形学学会（CSIG）广州中心秘书长
  • 中国图象图形学学会（CSIG）竞赛与培训工作委员会副主任
  • 广东省图象图形学会（GDSIG）副秘书长、理事
  • 广东省图象图形学会（GDSIG）-计算机视觉专委会副主任（2018-2024）
  • 中国计算机学会计算机视觉专委会执行委员
  • 中国人工智能学会模式识别专委会委员
  • 中国图象图形学会视觉大数据专委员会委员
  • 中国图象图形学学会高级会员
  • 中国计算机学会高级会员

教授课程: 

  • 《人工智能导论》（本科）
  • 《数字图像处理》（本科、研究生）
  • 《人工智能与模式识别》（研究生）
  • 《高等数学》（本科）
  • 《HPC+AI科学计算前沿》（研究生）

代表性论著: 

机器学习基础理论方法（注意力、大模型适配、域适应、蒸馏、多模态分析）：

  • [无参数无需训练的注意力机制] Lingxiao Yang, Ru-Yuan Zhang, Lida Li, Xiaohua Xie. SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks. International Conference on Machine Learning (ICML), 2021. (CCF A类) [报道][Code][获2024世界人工智能大会青年优秀论文提名奖，谷歌引用超过1800次]

  • [多模态基础模型域适配调优] Lingxiao Yang, Ru-Yuan Zhang, Qi Chen, Xiaohua Xie. Learning with Enriched Inductive Biases for Vision-Language Models. International Journal of Computer Vision (IJCV), 2025. (CCF-A) [Code]

  • [多模态基础模型域适配调优] Lingxiao Yang, Ru-Yuan Zhang, Yanchen Wang, Xiaohua Xie. MMA: Multi-Modal Adapter for Vision-Language Models. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.（CCF A类）[演讲视频]

  • [网络深度自调节的半监督深度学习] Guangcong Wang, Xiaohua Xie, Jianhuang Lai, Jiaxuan Zhuo.  Deep Growing Learning.  International Conference on Computer Vision (ICCV), 2017.（CCF A类）[Code]

  • [跨分辨率蒸馏学习-推理加速] Zhanxiang Feng, Jianhuang Lai, Xiaohua Xie. Resolution-aware Knowledge Distillation for Efficient Inference. IEEE Transactions on Image Processing (TIP), 2021. (中科院1区，CCF A类)

  • [多模态学习-多视图聚类] Jintang Bian, Xiaohua Xie, Jianhuang Lai, Feiping Nie. Multi-view Contrastive Clustering via Integrating Graph Aggregation and Confidence Enhancement. Information Fusion, March 2024. (中科院1区)

  • [多模态学习-多视图聚类] Jintang Bian, Xiaohua Xie, Lingxiao Yang, Jianhuang Lai, Feiping Nie. Angular Reconstructive Discrete Embedding with Fusion Similarity for Multi-view Clustering. IEEE International Conference on Data Engineering (TKDE), 2024. (CCF A类)

  • [多模态学习-多视图聚类] Jintang Bian, Yixiang Lin, Xiaohua Xie, Chang-Dong Wang, Lingxiao Yang, Jianhuang Lai, Feiping Nie. Multi-level Contrastive Multi-view Clustering with Dual Self-supervised Learning. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2025. (中科院一区)

  • [多模态学习-模态缺失下的情感识别] Yuanyue Deng, Jintang Bian, Shisong Wu, Jianhuang Lai, Xiaohua Xie. Multiplex Graph Aggregation and Feature Refinement for Unsupervised Incomplete Multimodal Emotion Recognition. Information Fusion, 2024. (中科院1区) 

  • [视觉识别语义元深度学习] Lingxiao Yang, Xiaohua Xie, Jianhuang Lai. Learning Discriminative Visual Elements using Part-based Convolutional Neural Network. Neurocomputing, 2018.

视频图像处理与生成（扩散模型、神经辐射场、生成对抗网络等）：

  • [文转图像Transformer的一种高效轻量化方法] Youwei Zheng, Yuxi Ren, Xin Xia, Xuefeng Xiao, Xiaohua Xie. Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation. International Conference on Computer Vision (ICCV), 2025.（CCF A类）

  • [基于文本的三维生成] Jiahao Zhu, Zixuan Chen, Guangcong Wang, Xiaohua Xie, Yi Zhou. SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation. International Conference on Computer Vision (ICCV), 2025.（CCF A类）

  • [基于对抗分布匹配的扩散模型高效蒸馏方法] Yanzuo Lu, Yuxi Ren, Xin Xia, Shanchuan Lin, XING WANG, Xuefeng Xiao, Jinhua Ma, Xiaohua Xie, Jianhuang Lai. Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis. International Conference on Computer Vision (ICCV), 2025.（CCF A类）

  • [解决扩散模型的采样时间奇异点问题] Pengze Zhang, Hubery Yin, Chen Li, Xiaohua Xie. Tackling the Singularities at the Endpoints of Time Intervals in Diffusion Models. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.（CCF A类）[Code][演讲视频][报道][入选Highlight]

  • [基于离散概率流的离散扩散模型] Pengze Zhang, Hubery Yin, Chen Li, Xiaohua Xie. Formulating Discrete Probability Flow Through Optimal Transport. The Thirty-Seventh Annual Conference on Neural Information Processing Systems (NeurIPS), 2023.（CCF A类）[Code]

  • [扩散模型应用于人体生成] Yanzuo Lu, Manlin Zhang, Jinhua Ma, Xiaohua Xie, Jianhuang Lai. Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.（CCF A类）[Code][演讲视频][入选Highlight]

  • [任意分辨率神经辐射场] Zixuan Chen, Lingxiao Yang, Jian-Huang Lai, Xiaohua Xie. CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution. International Conference on Computer Vision (ICCV), 2023.（CCF A类）

  • [姿态引导的行人图像生成] Pengze Zhang, Lingxiao Yang, Xiaohua Xie, Jianhuang Lai. Pose Guided Person Image Generation via Dual-task Correlation and Affinity Learning. IEEE Transactions on Visualization and Computer Graphics (TVCG), 2023. (CCF A类) [Code]

  • [姿态引导的行人图像生成] Pengze Zhang, Lingxiao YANG, Xiaohua Xie, Jian-Huang Lai. Exploring Dual-task Correlation for Pose Guided Person Image Generation.  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.（CCF A类）[Code][演讲视频][Presentation]

  • [姿态引导的行人图像生成] Pengze Zhang, Lingxiao Yang, Xiaohua Xie, Jianhuang Lai. Lightweight Texture Correlation Network for Pose Guided Person Image Generation. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022. (中科院1区) [Code]

  • [弱监督图像去阴影] Wenjie Luo, Xiaohua Xie, Kuoyu Deng, Lingxiao Yang, Jianhuang Lai. Learning Shadow Removal from Unpaired Samples via Reciprocal Learning. IEEE Transactions on Image Processing (TIP), 2023. (CCF A类)  

  • [弱监督学习去雨滴] Wenjie Luo, Jianhuang Lai, Xiaohua Xie. Weakly Supervised Learning for Raindrop Removal on a Single Image. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2020.（中科院1区）

  • [人脸光照处理] Xiaohua Xie, Wei-Shi Zheng, Jianhuang Lai, Pong C. Yuan, and Ching Y. Suen. Normalization of Face Illumination Based on Large- and Small- Scale Features. IEEE Transactions on Image Processing (TIP), 2011. (中科院1区，CCF A类)

  • [人脸光照处理] Weihong Xu, Xiaohua Xie, Jianhuang Lai. RelightGAN: Instance-level Generative Adversarial Network for Face Illumination Transfer. IEEE Transactions on Image Processing (TIP), 2021.  (中科院1区，CCF A类)

  • [人脸光照处理] Xiaohua Xie, Wei-Shi Zheng, Jianhuang Lai, and Pong C. Yuan. Face Illumination Normalization on Large and Small Scale Features. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008.（CCF A类）

  • [人脸光照处理] Xiaohua Xie, Jianhuang Lai, and Wei-Shi Zheng. Extraction of Illumination Invariant Facial Features from a Single Image using Nonsubsampled Contourlet Transform. Pattern Recognition, 2010. (中科院1区)

  • [人脸光照处理] Xiaohua Xie, Jianhuang Lai, Ching Y. Suen, and Wei-Shi Zheng. Non-Ideal Class Non-Point Light Source Quotient Image for Face Relighting. Signal Processing, 2011.

  • [人脸光照处理] Xiaohua Xie. Illumination Preprocessing for Face Images based on Empirical Mode Decomposition. Signal Processing, 2014.

  • [超分辨率] Zhanxiang Feng, Jianhuang Lai, Xiaohua Xie, Junyong Zhu. Image super-resolution via a densely connected recursive network. Neurocomputing, 2018.

  • [超分辨率] Yan Liang, Xiaohua Xie, and Jian-Huang Lai. Face hallucination based on morphological component analysis. Signal Processing, 2013.

跨摄像头行人分析（行人/人群重识别、跨摄像头轨迹分析）：

  • [换衣服条件下的小股人群重识别] Quan Zhang, Jianhuang Lai, Xiaohua Xie, Xiaofeng Jin, Sien Huang. Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024.（中科院1区，CCF A类）

  • [小股人群重识别] Quan Zhang, Jianhuang Lai, Zhanxiang Feng, Xiaohua Xie. Uncertainty Modeling for Group Re-Identification, International Journal of Computer Vision (IJCV), 2024. （CCF A类）

  • [时间辅助的跨摄像头行人重识别及轨迹分析] Xin Zhang, Xiaohua Xie, Jianhuang Lai. Cross-Camera Pedestrian Trajectory Retrieval Based on Linear Trajectory Manifolds. IEEE Transactions on Image Processing (TIP), 2025. (中科院1区，CCF A类) [Code and Data]

  • [时空辅助的跨摄像头行人重识别及轨迹分析] Xin Zhang, Xiaohua Xie, Jianhuang Lai, Wei-Shi Zheng. Cross-camera Trajectories Help Person Retrieval in a Camera Network. IEEE Transactions on Image Processing (TIP), 2023. (中科院1区，CCF A类) [Code and Data][CSIG中文推介]

  • [空中视角小股人群重识别] Hongxu Chen, Quan Zhang, Xiaohua Xie, Jianhuang Lai. Unsupervised Group Re-identification from Aerial Perspective via Strategic Member Harmonization. Pattern Recognition, 2025.

  • [基于红外视频的小股人群重识别] Jianghao Xiong, Xiaohua Xie, Jianhuang Lai. Dual-level aggregation network for video-based visible-infrared group re-identification. Pattern Recognition, Vol. 170, February 2026.

  • [时空辅助的跨摄像头行人轨迹分析及人群检测] Xin Zhang, Xiaohua Xie, Li Wen, Jianhuang Lai. People Group Detection with Global Trajectory Extraction in a Disjoint Camera Network. Neurocomputing, 2024. [Code and Data]

  • [融合时空信息的行人再识别] Guangcong Wang, Jian-Huang Lai, Peigen Huang, Xiaohua Xie. Spatial-Temporal Person Re-identification. AAAI 2019. （CCF A类）[Code]

  • [小股人群重识别] Quan Zhang, Jianhuang Lai, Zhanxiang Feng, Xiaohua Xie. Uncertainty Modeling with Second-Order Transformer for Group Re-Identification. AAAI 2022. （CCF A类）

  • [跨天地行人重识别] Quan Zhang, Lei Wang, Vishal M. Patel, Xiaohua Xie, Jianhuang Lai. View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.（CCF A类）[演讲视频]

  • [无监督小股人群重识别] Hongxu Chen, Quan Zhang, Jian-Huang Lai, Xiaohua Xie. Unsupervised Group Re-Identification via Adaptive Clustering-Driven Progressive Learning. AAAI 2024. （CCF A类）

  • [跨模态（文本-图像）行人检索] Qiyang Peng, Lingxiao Yang, Xiaohua Xie, Jianhuang Lai. Learning Weak Semantics by Feature Graph for Attribute-based Person Search. IEEE Transactions on Image Processing (TIP), 2023. (CCF A类)

  • [虚拟场景辅助训练的人群重识别] Quan Zhang, Kaiheng Dang, Jian-Huang Lai, Xiaohua Xie, Zhanxiang Feng. Modeling 3D Layout for Group Re-Identification. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.（CCF A类）

  • [行人重识别] Quan Zhang, Jianhuang Lai, Zhanxiang Feng, Xiaohua Xie. Seeing Like a Human: Asynchronous Learning with Dynamic Progressive Refinement for Person Re-identification. IEEE Transaction on Image Processing (TIP), 2021. (中科院1区，CCF A类)

  • [跨模态（红外-可见光）无监督行人再识别] Wenqi Liang, Guangcong Wang, Jianhuang Lai, Xiaohua Xie. Homogeneous-to-Heterogeneous: Unsupervised Learning for RGB-Infrared Person Re-Identification. IEEE Transactions on Image Processing (TIP), 2021. (中科院1区，CCF A类)

  • [跨模态（红外-可见光）行人再识别] Zhanxiang Feng, Jianhuang Lai, Xiaohua Xie. Learning Modality-specific Representation for Visible-Infrared Person Re-Identification. IEEE Transaction on Image Processing (TIP), 2020. (中科院1区，CCF A类)

  • [跨模态（红外-可见光）行人再识别] Quan Zhang, Jianhuang Lai, Zhanxiang Feng, Xiaohua Xie. Learning Modal-Invariant Angular Metric by Cyclic Projection Network for VIS-NIR Person Re-identification. IEEE Transactions on Image Processing (TIP), 2021. (中科院1区，CCF A类)

  • [视角相关的行人再识别] Zhanxiang Feng, Jianhuang Lai, and Xiaohua Xie. Learning View-Specific Deep Networks for Person Re-Identification. IEEE Transactions on Image Processing (TIP), 2018. (中科院1区，CCF A类)

  • [跨模态（视频-图像）行人再识别] Guangcong Wang, Jianhuang Lai, Xiaohua Xie. P2SNet: Can an Image Match a Video for Person Re-identification in an End-to-end Way? IEEE Trans. on Circuits and Systems for Video Technology (TCSVT), 2018 (中科院1区)

  • [非监督视频行人重识别] Jinhao Qian, Xiaohua Xie. Successive Consensus Clustering for Unsupervised Video-based Person Re-identification. IEEE Signal Processing Letters, 2022.

计算机视觉基础算法（分割、检测、光流）：

  • [工业异常检测] Zixuan Chen, Xiaohua Xie, Lingxiao Yang, Jian-Huang Lai. Hard-Normal Example-Aware Template Mutual Matching for Industrial Anomaly Detection. International Journal of Computer Vision (IJCV), 2024.

  • [定义流数据“视觉指令反馈（Visual Instruction Feedback）”全新任务] Shenghao Fu, Qize Yang, Yuan-Ming Li, Yi-Xing Peng, Kun-Yu Lin, Xihan Wei, Jian-Fang Hu, Xiaohua Xie, Wei-Shi Zheng. ViSpeak: Visual Instruction Feedback in Streaming Videos. International Conference on Computer Vision (ICCV), 2025.（CCF A类）

  • [基于基础大模型的无需训练开放词汇语义分割] Qi Chen, Lingxiao Yang, Yun Chen, Nailong Zhao, Jianhuang Lai, Jie Shao, Xiaohua Xie. Training-Free Class Purification for Open-Vocabulary Semantic Segmentation. International Conference on Computer Vision (ICCV), 2025.（CCF A类）

  • [借助基础大模型加强目标检测模型] Shenghao Fu, Qize Yang, Qijie Mo, Junkai Yan, Xihan Wei, Jingke Meng, Xiaohua Xie, Wei-Shi Zheng. LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. (CCF-A类) [入选Highlight]
  • [借助基础大模型加强目标检测模型] Shenghao Fu, Junkai Yan, Qize Yang, Xihan Wei, Xiaohua Xie, Wei-Shi Zheng. A Hierarchical Semantic Distillation Framework for Open-Vocabulary Object Detection. IEEE Transactions on Multimedia (TMM), 2025.  (CCF-A类)

  • [借助基础大模型加强目标检测模型] Shenghao Fu, Junkai Yan, Qize Yang, Xihan Wei, Xiaohua Xie, Wei-Shi Zheng. Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models. The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024.

  • [单解码层稀疏检测器] Shenghao Fu, Junkai Yan, Yipeng Gao, Xiaohua Xie, Wei-Shi Zheng. ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation. International Conference on Computer Vision (ICCV), 2023.（CCF A类）

  • [显著性目标检测实验性综述] Huajun Zhou, Yang Lin, Lingxiao Yang, Jianhuang Lai, Xiaohua Xie. Benchmarking Deep Models on Salient Object Detection. Pattern Recognition, 2023. (中科院1区) [Code]

  • [无监督显著目标检测] Huajun Zhou, Bo Qiao, Lingxiao Yang, Jianhuang Lai, Xiaohua Xie. Texture-guided Saliency Distilling for Unsupervised Salient Object Detection. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.（CCF A类）[Code]

  • [个性化显著性目标分割] Huajun Zhou , Lingxiao Yang , Xiaohua Xie, Jianhuang Lai. Selective Intra-image Similarity for Personalized Fixation-based Object Segmentation. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022. (中科院1区)

  • [无监督显著性目标检测] Huajun Zhou, Peijia Chen, Lingxiao Yang, Xiaohua Xie, Jianhuang Lai. Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022. (中科院1区) [Code]

  • [弱监督语义分割] Qi Chen, Lingxiao Yang, Jian-Huang Lai, Xiaohua Xie. Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.（CCF A类）[Code]

  • [弱监督语义分割] Qi Chen, Yun Chen, Yuheng Huang, Xiaohua Xie, Lingxiao Yang. Region-based Online Selective Examination for Weakly Supervised Semantic Segmentation. Information Fusion, 2024. (中科院1区)

  • [缺陷视觉检测] Quan Zhang, Jianhuang Lai, Junyong Zhu, Xiaohua Xie. Wavelet-Guided Promotion-Suppression Transformer for Surface-Defect Detection. IEEE Transactions on Image Processing (TIP), 2023. (中科院1区，CCF A类)

  • [缺陷视觉检测] Biaohua Ye, Jianhuang Lai, Xiaohua Xie, Junyong Zhu. Prototype-guided domain adaptive one-stage object detector for defect detection. Advanced Engineering Informatics, 2024. (中科院1区)

  • [视频目标分割] Zixuan Chen, Chunchao Guo, Jianhuang Lai, Xiaohua Xie. Motion-Appearance Interactive Encoding for Object Segmentation in Unconstrained Videos. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2020. (中科院1区)

  • [视觉显著目标分割] Huajun Zhou, Jianhuang Lai, Zixuan Chen, Lingxiao Yang, Xiaohua Xie. Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.（CCF A类）[Code]

  • ​[视觉显著目标分割] Zixuan Chen, Huajun Zhou, Jianhuang Lai, Lingxiao Yang, Xiaohua Xie. Contour-Aware Loss: Boundary-Aware Learning for Salient Object Segmentation. IEEE Transaction on Image Processing (TIP), 2021. (中科院1区，CCF A类)

  • [航拍场景人流密度估计] Jingyu Chen, Shengjie Xiu, Xiang Chen, Hao Guo, Xiaohua Xie. Flounder-Net: An Efficient CNN for Crowd Counting by Aerial Photography. Neurocomputing, 2021. 

  • [光流估计] Jun Chen, Jianhuang Lai, Zemin Cai, Xiaohua Xie, Zhigeng Pan. Optical Flow Estimation Based on the Frequency-Domain Regularization. IEEE Transactions on Circuits and Systems for Video Technology(TCSVT), 2021. (中科院1区) [Code]

  • [光流估计] Jun Chen, Zemin Cai, Jianhuang Lai, Xiaohua Xie. A Filtering Based Framework For Optical Flow Estimation. IEEE Trans. on Circuits and Systems for Video Technology (TCSVT), 2019. (中科院1区)

  • [光流估计] Jun Chen, Jianhuang Lai, Zemin Cai, Xiaohua Xie. Fast Optical Flow Estimation Based on Split Bregman Method. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). 2018. (中科院1区) [Code]

  • [光流估计] Jun Chen, Zemin Cai, Jianhuang Lai, Xiaohua Xie. Efficient Segmentation-Based PatchMatch for Large Displacement Optical Flow Estimation. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). 2018. (中科院1区) [Code]

  • [光流估计] Ling Mei, Jianhuang Lai, Xiaohua Xie, Junyong Zhu, Jun Chen. Illumination-Invariance Optical Flow Estimation Using Weighted Regularization Transform. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2019. (中科院1区)

AI安全与数据隐私：

  • [针对视觉生成大模型的对抗攻击] Junxi Chen, Junhao Dong, Xiaohua Xie. Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.（CCF A类）[入选Highlight]

  • [缓解ℓ∞-范数对抗训练中的不平等现象] Junxi Chen, Junhao Dong, Xiaohua Xie, Jianhuang Lai.  Releasing Inequality Phenomenon in l∞-norm Adversarial Training via Input Gradient Distillation. Transactions on Information Forensics & Security (TIFS), 2025. (CCF-A)

  • [三维媒体水印] Zixuan Chen, Guangcong Wang, Jiahao Zhu, Jianhuang Lai, Xiaohua Xie. GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. （CCF A类）

  • [医学图像分析的对抗攻击综述] Junhao Dong, Junxi Chen, Xiaohua Xie, Jianhuang Lai, Hao Chen. Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challenges. ACM Computing Surveys, 2024. (中科院1区，影响因子23.8)

  • [小样本对抗训练] Junhao Dong, Piotr Koniusz, Junxi Chen, Xiaohua Xie, Yew-Soon Ong. Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.（CCF A类）[演讲视频]

  • [概率对抗训练] Junhao Dong, Lingxiao Yang, Yuan Wang, Xiaohua Xie, Jianhuang Lai. Towards Intrinsic Adversarial Robustness Through Probabilistic Training. IEEE Transactions on Image Processing (TIP), 2023.  (CCF A类)

  • [反向对抗样本训练] Junhao Dong, Junhao_Dong, Seyed-Mohsen Moosavi-Dezfooli, Jianhuang Lai, Xiaohua Xie. The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.（CCF A类）[演讲视频]

  • [对FeepFake的对抗样本黑盒攻击] Junhao Dong, Yuan Wang, Jianhuang Lai, Xiaohua Xie. Restricted Black-box Adversarial Attack Against DeepFake Face Swapping. IEEE Transactions on Information Forensics and Security (TIFS), 2023. (中科院1区，CCF A类)

  • [抵抗对抗样本的小样本图像分类] Junhao Dong, Yuan Wang, Jian-Huang Lai, Xiaohua Xie. Improving Adversarially Robust Few-shot Image Classification with Generalizable Representations. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.（CCF A类）

  • [对FeepFake的对抗样本白盒攻击] Junhao Dong, Xiaohua Xie. Visually Maintained Image Disturbance Against DeepFake Face Swapping. IEEE International Conference on Multimedia and Expo (ICME), 2021. (CCF B类)

类脑视觉（脉冲神经网络、事件相机、视觉推理等）：

  • [类脑神经形态视觉] Jianxiong Tang, Jianhuang Lai, Lingxiao Yang, Xiaohua Xie. Spike-Temporal Latent Representation for Energy-Efficient Event-to-Video Reconstruction. European Conference on Computer Vision (ECCV), 2024.

  • [脉冲神经网络训练方法] Jianxiong Tang, JianHuang Lai, Xiaohua Xie, Lingxiao Yang, Wei-Shi Zheng. AC2AS: Activation Consistency Coupled ANN-SNN framework for fast and memory-efficient SNN training. Pattern Recognition, (中科院1区)

  • [类脑神经形态视觉] Jianxiong Tang, Jian-Huang Lai1, Xiaohua Xie, Lingxiao Yang. Spike Count Maximization for Neuromorphic Vision Recognition. International Joint Conference on Artificial Intelligence (IJCAI), 2023. (CCF A类)

  • [脉冲神经网络SNN训练] Jianxiong Tang, Jianhuang Lai, Wei-Shi Zheng, Lingxiao Yang, Xiaohua Xie. Relaxation RLIF: A Gradient-based Spiking Neuron for Direct Training Spiking Neural Networks. Neurocomputing, 2022.

  • [类脑视觉推理] Lingxiao Yang, Hongzhi You, Zonglei Zhen, Dahui Wang, Xiaohong Wan, Xiaohua Xie, Ru-Yuan Zhang. Neural Prediction Errors Enable Analogical Visual Reasoning in Human Standard Intelligence Tests. International Conference on Machine Learning (ICML), 2023. (CCF A类)

  • [类脑计算]  Yunlong Xu, Lingxiao Yang, Hongzhi You, Zonglei Zhen, Da-Hui Wang, Xiaohong Wan, Xiaohua Xie, Ru-Yuan Zhang. RuleMatch: Matching Abstract Rules for Semi-supervised Learning of Human Standard Intelligence Tests. International Joint Conference on Artificial Intelligence (IJCAI), 2023. (CCF A类)

  • [脑启发小样本检测] Lingxiao Yang, Dapeng Chen, Yifei Chen, Wei Peng, Xiaohua Xie. A Neuroinspired Contrast Mechanism enables Few-Shot Object Detection. Pattern Recognition, 2024. (中科院1区)

其它（语音、三维）：

  • [语音情感转换] Yun Chen, Lingxiao Yang, Qi Chen, Jian-Huang Lai, Xiaohua Xie. Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion. INTERSPEECH 2023. (语音技术国际顶级会议)

  • [多种材料识别] Xiaohua Xie, Lingxiao Yang, Wei-Shi Zheng. Learning Object-Specific DAGs for Multi-Label Material Recognition. Computer Vision and Image Understanding (CVIU), 2016. (CCF B类)

  • [人脸三维重构] Jian-Fang Hu, Wei-Shi Zheng, Xiaohua Xie, and Jianhuang Lai. Sparse Transfer for Facial Shape-from-Shading. Pattern Recognition, vol. 68, August 2017: 272–285. (中科院1区)

  • [手绘三维建模] Xiaohua Xie, Kai Xu, Niloy J. Mitra, Daniel Cohen-Or, Wenyong Gong, Qi Su, Baoquan Chen. Sketch-to-Design: Context-based Part Assembly. Computer Graphics Forum, 2013. (CCF B类)

  • [虚拟数据辅助图像本征属性分解] Guangyun Han, Xiaohua Xie, Jianhuang Lai, Wei-Shi Zheng. Learning an Intrinsic Image Decomposer Using Synthesized RGB-D Dataset. IEEE Signal Processing Letters, 2018.

  • [多种材料识别] Lingxiao Yang, Xiaohua Xie. Exploiting Object Semantic Cues for Multi-label Material Recognition. Neurocomputing, 2016.