1. 人工智能、图像视频大数据(Artificial intelligence, Big data of Image & Video)

2. 医学多模态大数据分析 (Multimodal medical data analysis)

3. 人脸识别、行人重识别 (2D&3D face recognition, Person Re-identification)

4. 基于视频的行为分析 (Hunam behavior analysis and identification based on video)

【B站主页】（主题：“机器学习、计算机视觉技术”分享）：https://space.bilibili.com/202603446

【Gitee源码】：https://gitee.com/swjtugx/classmate

[+] 国家自然科学基金（面上，62376231），内镜超声为中心多模医学影像协同学习在胃肠道间质瘤诊疗中的研究，2024.1-2027.12 ，主持

National Natural Science Foundation of China (62376231), 2024.1-2027.12

Diagnosis and treatment of gastrointestinal stromal based on collaborative learning of EUS-centric multimodal images, 2024.1-2027.12, PI 

[+] 国家自然科学基金（面上，61876158）多模态、多属性甲状腺超声影像大数据自主标注及学习 ，2019.1-2022.12 ，主持

National Natural Science Foundation of China (61876158), Multi-Modal and Multi-Attribute Ultrasound Video and Image Automatic Annotation and Learning for Thyroid Nodule Diagnose, 2019.1-2022.12, PI 

[+] 国家自然科学基金（青年，61202191），面向多场景图像自适应的三维人脸建模研究，2013.1-2015.12，主持

National Natural Science Foundation of China(61202191) Research on Self-adapting 3D Face Modeling from Images of Multiple Scenarios. 2013.1-2015.12, PI 

[+] 四川省重点研发项目（面上），2023.1-2024.12，主持

Natural Science Foundation of Sichuan Province,  2023.1-2024.12, PI

[+] 四川省自然科学基金（面上），2024.1-2025.12，主研

Natural Science Foundation of Sichuan Province, 2024.1-2025.12

[+] 四川省卫生健康委员会科技项目（临床研究专项），2023.08-2025.07，主研

Science and Technology Project of Sichuan Provincial Health Commission， 2023.8-2025.7

[+] 唐山市基础研究科技计划（23130230E），开放环境下全天候复杂场景行为识别关键技术研究，2023.06-2025.12，主持

Tangshan Basic Research Science and Technology Program (23130230E), Research on Key Technology Behavior Recognition in Open Environment, 2023.06-2025.12，PI

[+] 四川省重点研发项目（面上）2019.1-2020.12，主持

Natural Science Foundation of Sichuan Province, 2019.1-2020.12, PI 

[+] 教育部产学合作协同育人项目（创新创业），川西南纸本经图理解及数字化关键技术研究，华为技术有限公司，2022.10-2023.12，主持

[+] Kunlun Wu, Xun Gong*. Asymmetric Information-Regularized Learning for Skeleton-Based Action Recognition. Applied Intelligence. (Accepted)

[+] Zhemin Zhang，Xun Gong^*. Positional Label for Self-Supervised Vision Transformer. The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023). 2023 [paper][code][video][web]

[+] Xun Gong^*, Shuai Yuan, Yang Xiang, Lin Fan, Hong Zhou. Domain Knowledge-Guided Adversarial Adaptive Fusion of Hybrid Breast Ultrasound Data. Computers in Biology and Medicine. 2023.09, Vol(164) [paper][video]

[+] Xun Gong^*, Li Wang, Longlong Miao, Nuo Chen, Jiao Li^*. PIMedSeg: Progressive Interactive Medical Image Segmentation. Computer Methods and Programs in Biomedicine. 25 August 2023, Doi: 10.1016/j.cmpb.2023.107776

[+] Xun Gong^*, Hongling Zhou, Yunhao Gu, Ying Guo. Breast Ultrasound Image Classification with Hard Sample Generation and Semi-supervised Learning. Biomedical Signal Processing and Control. Volume 86, Part B, September 2023 [paper][video]

[+] Daisong Yan, Xun Gong^*, Zhemin Zhang, Rotated and Masked Image Modeling: A Superior Self-Supervised Method for Classification. IEEE Signal Processing Letters. 2023(30): 1477-1481[paper][video][code]

[+] Jinrong Lv, Xun Gong^*. Multi-grained Temporal Segmentation Attention Modeling for Skeleton-based Action Recognition. IEEE Signal Processing Letters. 2023(30): 927-931 [paper][code][video]

[+] Kunlun Wu, Xun Gong^*. Dynamic Channel-Aware Subgraph Interactive Networks for Skeleton-Based Action Recognition. IEEE Signal Processing Letters. 2022(29): 2592-2596  [paper][video][code]

[+] Chaohao, Wen, Xun Gong^*. SDGFormer: An Efficient Convolution Network Structurally Similar to Transformer. 2023 IEEE International Conference on Multimedia and Expo (ICME). Brisbane, Australia, July 10 - 14, 2023. 1181-1186 [paper][video][code]

[+] Lin Fan, Xun Gong^*, Ying Guo. General multi-scenario ultrasound image tumor diagnosis method based on unsupervised domain adaptation. Ultrasound in Medicine & Biology. 2023 [paper][code]

[+] Xun Gong, Zu Yao, Xin Li. LAG-Net: Multi-granularity network for person re-identification via local attention system. IEEE Transactions on Multimedia. 2022, 24(1), 217 - 229 [paper][code][video][web]

[+] Shijie Wu, Xun Gong^*. BoundaryFace: A mining framework with noise label self-correction for Face Recognition. European Conference on Computer Vision (ECCV 2022) [paper][code][video][web]

[+] Xun Gong^*, Xu Zhao, Lin Fan, Tianrui Li, Ying Guo^*, Jun Luo. BUS-net: A Bimodal Ultrasound Network for Breast Cancer Diagnosis. International Journal of Machine Learning and Cybernetics. 2022.7.7 [paper]

[+] Yueqiao Fan, Xun Gong^*, Yuning He. DSF-Net: Occluded Person Re-identification Based on Dual Structure Features. Neural Computing and Applications. 2022. 10.1007/s00521-022-07927-6 [video][paper][code]

[+] Chenzhong Wang, Xun Gong^*. Bounding box regression with balance for harmonious object detection, Journal of Visual Communication and Image Representation, 2022, doi: /10.1016/j.jvcir.2022.103665

[+] Haipeng Zou, Xun Gong*, Jun Luo, Tianrui Li. A Robust Breast ultrasound segmentation method under noisy annotations. Computer Methods and Programs in Biomedicine. Volume 209, 2021.9 [paper]

[+] Donghai Zhai, Bijie Hu*, Xun Gong*, Haipeng Zou, Jun Luo. ASS-GAN:Asymmetric Semi-supervised GAN for Breast Ultrasound Image Segmentation. Neurocomputing，2022, doi: 10.1016/j.neucom.2022.04.021 [code][paper]

[+] Yang Zhou, Xun Gong*, Peng Yang. A directional margin paradigm for noise suppression in face recognition. Journal of Visual Communication and Image Representation, vol. 78, 2021, doi: 10.1016/j.jvcir.2021.103182. 

[+] 姚足，龚勋*，陈锐等. 面向行人重识别的局部特征研究进展、挑战与展望[J]. 自动化学报, 2021

[+] Xun Gong*, Xin Li, Tianrui Li, etc. A Discriminative Multi-Channel Facial Shape (MCFS) Representation and Feature Extraction for 3D Human Faces. Computer Graphics Forum, vol. 39, no.6, 66-81, 2020. doi: 10.1111/cgf.13904 

[+] 龚勋*, 杨菲, 杜章锦等. 甲状腺、乳腺超声影像自动分析技术综述. 软件学报, vol. 31, no. 7, 2020, 1615-1652

[+] 龚勋*, 王国胤, 李天瑞等. 基于混合能量活动轮廓模型的人脸分割方法. 软件学报, vol. 23, no. 4, 623-638, 2013

[+] Xun Gong*, Guoyin Wang, Xinxin Li and Tianrui Li. A Statistical Two-step Method for 3D Face Reconstruction from Single Image. Chinese Journal of Electronics, vol. 20, no. 4, 671-675, 2011

[+] Xun Gong*, Guoyin Wang. Example-based learning for depth estimation of facial landmarks and its application in face modeling. Chinese Journal of Electronics, vol. 19, no. 4, 676-680, 2010

[+] 龚勋*, 王国胤. 基于特征点的三维人脸形变模型. 软件学报, vol. 20, no. 3, 724-733, 2009

***专利清单***

[1] 龚勋，樊琳. 一种基于迁移学习的多尺度特征图像分类方法，中国发明专利，专利号：ZL202210365307.6，申请日期：2021.6.8，授权日期：2023-04-18

[2] 龚勋，王琛中，王立. 基于多目标融合与时空视频序列的手机检测方法，中国发明专利，申请日期：2020-10-10，专利号：ZL202011079614.5，授权日期：2022-9-2

[3] 龚勋，周炀. 一种抗噪声数据的人脸识别模型训练方法，中国发明专利，专利号：ZL201911129505.7，申请日期：2019-11-18，授权日期：2022-11-11

[4] 龚勋，樊剑锋. 一种融合人脸及人体特征的跨镜行人轨迹检测方法，中国发明专利，专利号： ZL202110032091.7，申请日期：2021.01.11，授权日期：2022-08-02

[5] 龚勋，赵绪，杨子奇. 一种乳腺超声造影视频中病灶区形态自动标注方法，中国发明专利，专利号：ZL202010159426.7，申请日期：2020.3.09，授权日期：2022.05.19

[6] 龚勋，陈锐，吴世杰. 一种大规模人脸数据集的双阶段噪声清洗方法，中国发明专利，专利号：ZL202111061863.6，申请日期：2021-09-10，授权日期：2021-12-21

[7] 龚勋，刘瑞楠，马浩，师恩，章哲敏. 一种基于最大生成树的人脸识别数据库构成方法，中国发明专利，专利号：ZL201810441046.5，申请日期：2018.5.10，授权日期：2021.7.2

[8] 龚勋，马冰，刘璐. 一种基于时空信息及人、物交互的人体异常行为检测方法，中国发明专利，专利号：ZL202110030865.2，申请日期：2021.1.12，授权日期：2021-05-06

[9] 龚勋，文超豪，劳博基. 视角可配置的相机全景拼接方法. 中国发明专利，专利号：ZL202110042844.2, 申请日期：2021.1.13，授权日期：2021.4.20

[10] 龚勋，邹海鹏，杨子奇，赵绪. 一种抗噪声数据的乳腺超声结节分割方法，中国发明专利，专利号：ZL201911129522.0，申请日期：2019.11.18，授权日期：2020.8.4

[11] 龚勋，许新，易心一，罗俊.一种基于肝脏超声造影图像的实时跟踪及定量分析方法, 中国发明专利，专利号：ZL201710430522.9，申请日期：2017.06.09，授权日期：2019.11.19

[12] 龚勋，师恩，李昕昕，郭浩龙，黄鑫. 一种基于铁路轨道检测数据进行里程校准的方法, 中国发明专利，专利号：ZL201710437307.1，申请日期：2017.6.12，授权日期：2020.3.27

[13] 龚勋，郭浩龙，杜章锦. 基于小波变换的铁路轨道里程数据的校准方法，中国发明专利，专利号：ZL201810578845.7，申请日期：2018.6.7，授权日期：2019.12.10

[14] 龚勋，李天瑞，李昕昕. 数码照片中的人脸自动分割方法，中国发明专利，专利号：ZL201110215738.6，申请日期：2011.7.29，授权日期：2013.4.10