教师简介

卢宪凯,山东大学软件学院,研究员,硕士生导师,2021年入选中国科协青年人才托举工程,2023年入选山东省高等学校“青创团队计划”团队负责人,山东省科协海智专家。本科毕业于山东大学,博士毕业于上海交通大学模式识别专业,20188月至2020年10月在Inception Institute of Artificial Intelligence(IIAI)担任助理研究员。主要从事计算机视觉,视频目标分割、目标跟踪、机器学习、遥感图像分析等方面的研究工作。主持和参与多项课题研究包括国家自然科学基金青年项目、山东省自然科学青年基金、之江实验室国际青年人才基金。在IEEE TPAMI、IEEE TIP、IEEE TCSVTIEEE ProceedingsCVPRICCV、Neurips、ECCV等国际高水平期刊和顶级会议上发表学术论文30余篇(其中ESI高被引论文3篇),国际专利2项。 担任国际期刊Frontiers in Imaging副编辑(editorial board),模式识别SCI期刊Pattern Recognition客座编委,IJCAI2021 Senior Program Committee Member,长期担任IEEE TPAMI (IF=17.6)TNNLSTCSVTPattern Recognition、TMM等国际期刊审稿人以及ICML/CVPR/ICCV/ECCV/IJCAI/AAAI/ICLR等人工智能顶级会议审稿人,同时是Neurocomputing Pattern Recognition 杰出审稿人。2022年获山东省人工智能优秀青年奖。



招生方向:

欢迎有意向攻读人工智能、软件工程的硕士生联系我,请在邮件附上简历;(PS:表现优秀且有意向读博者,可推荐到澳门大学、悉尼科技大学、上海交通大学、浙江大学、武汉大学等高水平大学读博!)

课题组长期接收山东大学本科生进课题组进行科研训练,有兴趣的同学请邮件联系luxiankai@sdu.edu.cn

所在团队:山东大学人工智能研究中心(http://www.sai.sdu.edu.cn/


研究方向

计算机视觉、深度学习、视频分析(视频目标分割,目标跟踪,跨模态视频检索)、视觉关系建模(图神经网络、自监督学习)


object_tracking_dlib_example01.gif687474703a2f2f7777772e726f626f74732e6f782e61632e756b2f7e797a2f696d672f6769662e676966.gif3117 (1).gif




                  视频目标跟踪                     视频目标分割                       视频实例分割

tsvg.jpg

                                              视频-文本定位

时空对比学习.png

                        图神经网络学习



[Google Scholar]:https://scholar.google.com/citations?user=QS5V5b8AAAAJ&hl=zh-CN


课程信息

智能机器人导论》,上课时间:2020-2021学年第二学期,1-16周,周五14:00-16:00,AI18级本科生,48课时。




News:

05/2024, our team wins the third place on CVPR 2024 MeViS: Motion expressions guided Video Segmentation challenge, congratulation to Hao Fang and Feiyu Pan!

04/2024, one paper about visible-depth-thermal object detection is accepted to IEEE TIP.

04/2024, one paper about video moment localization is accepted to IEEE TMM, congratulation to Tong Zhang.

12/2023, 第二届海军“金海豚”杯算法挑战赛全国第二名(亚军,2/400),恭喜王志成!!!

10/2023, one paper about video correspondance learning is accepted to IEEE TIP (CCF-A)congratulation to Zheyun Qin

09/2023, one paper about unified 3D segmentation (instance, semantic, panoptic) is accepted to NeurIPS 2023 (软件学院第一篇), congratulation to Zheyun Qin

09/2023, we set up special issue about Transfomer on <山东大学学报>(中文核心)[https://mp.weixin.qq.com/s/WhVli2asYo_1aJAzL7WdgQ]

08/2023, we set up a special issue on  'Frontiers in Remote Sensing' website [https://www.frontiersin.org/research-topics/59165/recent-trends-of-vision-transformer-vit-in-remote-sensing-methods-and-application]

08/2023, one paper about Video temporal grounding is accepted to IEEE TMM, congratulation to Tong Zhang.

07/2023, one paper about video based human mesh reconstruction is accepted to ACM International Conference on Multimedia 2023 (ACM MM), congratulation to Peng Wu.

07/2023, one paper about Video Corpus Moment Retrieval is accepted to IEEE TCSVT, congratulation to Xuemei Zhang.

04/2023, our team wins the first price in the 2rd "山东高速杯" Intelligent construction and intelligent transportation, congratulation to Zhicheng Wang, Chenchen Han and Peng Wu, etc. 

04/2023, one paper Adaptive Learning With Incomplete Data  is accepted to IEEE TPAMI.

02/2023, I served as the session Chair of AAAI 2023.

01/2023, one paper about video instance segmentation is accepted to IEEE/CAA Journal of Automatica Sinica (JAS), congratulation to Zheyun Qin.

11/2022, one paper about self-supervised video correspondance learning is accepted to Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023), congratulation to Zheyun Qin.

10/2022, we set up a special issue on <市政技术> [https://mp.weixin.qq.com/s/tRmP3dFwKGpMMIDLSZG_IA].

07/2022, One paper about label  denoise is accepted to ECCV 2022, congratulations to Qi Wei.

07/2022, One paper about safe semi-supervised learning is accepted to ACMMM 2022 (oral), congratulations to Rundong He.

05/2022, I serve as the editorial board of Frontiers in Imaging [https://www.frontiersin.org/journals?domain=all].

03/2022,  One papers about  safe semi-supervised learning are accepted to CVPR 2022, congratulations to Rundong He. 

01/2022, we set up Special Issue "Deep Perception in Autonomous Driving" in Electronics [https://www.mdpi.com/journal/electronics/special_issues/DPAD_electronics].

11/2021, One paper about Distilled Siamese Networks for Visual Tracking is accepted to IEEE TPAMI.

10/2021, One paper about Video Moment Retrieval is accepted to IEEE TMM, congratulation to Junya Teng.

09/2021, One paper about relational object segmentation is accepted to IEEE TPAMI.

07/2021, One paper (IEEE CSVT 2019) becomes the ESI highly cited paper. 

07/2021, One paper is accepted to ACM Multimedia 2021, congratulation to Zheyun Qin.

03/2021, One paper is accepted to CVPR 2021. 

01/2021, I serve as the IJCAI2021 Senior Program Committee Member. 

12/2020, One paper is accepted to IEEE TPAMI.


主持或参与科研项目:

1. 国家自然科学基金青年项目(2022.1-2024.12),主持 

2. 山东省自然科学青年基金项目(2022.1-2024.12),主持 

3. 人工智能教育部重点实验室2021年度开放基金 (2021.11-2023.12), 主持

4. 中国科协青年人才托举项目 (2021.12-2023.12), 主持

5. 澳门大学智慧城市与物联网国家重点实验室基金(2023.1-2024.12),主持

6. 山东省科技型中小企业创新能力提升工程 (2023.7-2025.7),主持

7. 山东省高等学校“青创团队计划”团队(2023-2025), 负责人



代表专著:

1.Ning Xu , Weiyao Lin , Xiankai Lu , Yunchao Wei. Video Object Tracking Tasks, Datasets, and Methods, Springer, 2023. [https://link.springer.com/book/9783031446597]


代表论文和期刊:


1. Liuxin Bao, Xiaofei Zhou, Xiankai Lu, Yaoqi Sun, Haibing Yin, Zhenghui Hu, Jiyong Zhang, and Chenggang Yan. Quality-aware Selective Fusion Network for V-D-T Salient Object Detection, IEEE Transactions on Image Processing (TIP), 2024.  (CCF-A, 中科院一区)[paper]

2.  Zheyun Qin, Xiankai Lu, D Liu, X Nie, Y Yin, J Shen, AC Loui. Reformulating Graph Kernels for Self-supervised Space-Time Correspondence Learning, IEEE Transactions on Image Processing (TIP), 2023. (CCF-A, 中科院一区)[paper]

3. Zheyun Qin, C Han, Q Wang, X Nie, Y Yin, Xiankai Lu*. Unified 3D Segmenter As Prototypical Classifiers, Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)  (CCF-A).[paper]

4. Peng Wu, Xiankai Lu*, Jianbing Shen, Yilong Yin. Clip Fusion with Bi-level Optimization for Human Mesh Reconstruction from Monocular Videos, Proceedings of the 31st ACM International Conference on Multimedia (ACMMM 2023) (CCF-A) [paper][code]

5. Y Gong, Z Li, W Liu, Xiankai Lu, X Liu, IW Tsang, Y Yin.  Missingness-Pattern-Adaptive Learning With Incomplete Data,  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023 (CCF A) . [paper]

6. Zheyun Qin, Xiankai Lu*, X Nie, D Liu, Y Yin, W Wang. Coarse-to-Fine Video Instance Segmentation With Factorized Conditional Appearance Flows, IEEE/CAA Journal of Automatica Sinica, 2023. (中科院一区,中国最具国际影响力学术期刊) [paper]

7. Zheyun Qin, Xiankai Lu*,  Xiushan Nie,  Yilong Yin, Jianbing Shen. Exposing the Self-supervised Space-Time Correspondence  Learning via Graph Kernels,  Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023). (CCF-A) [paper]

8. J Shen, Y Liu, X Dong, Xiankai Lu, FS Khan, S Hoi. Distilled Siamese networks for visual tracking, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022. (CCF-A, 中科院一区)

9. Qi Wei, Haoliang Sun, Xiankai Lu, Yilong Yin. "Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization",in the European Conference on Computer Vision (ECCV), 2022. (CCF-B)

10. Rundong He, Zhongyi Han, Xiankai Lu, Yilong Yin. "Safe-Student for Safe Deep Semi-Supervised Learning with Unseen-Class Unlabeled Data", in the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022.(CCF-A)

11. Junya Teng, Xiankai Lu*, Yongshun Gong,  Xinfang Liu, Xiushan Nie, Yilong Yin, "Regularized Two Granularity Loss Function for Weakly Supervised Video Moment Retrieval", IEEE TMM, 2021. (CCF-B, 中科院一区)

12. Xiankai LuWenguan Wang, Jianbing Shen,  D Crandall, L Van Gool, "Segmenting Objects from Relational Visual Data", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 (CCF A) [paper][code(CCF-A, 中科院一区,ESI高被引论文

13. Zheyun Qin, Xiankai Lu*, Xiushan Nie, Xiantong Zhen, Yilong Yin. Learning Hierarchical Embeddings for Video Instance Segmentation, ACMM MM2021 (CCF A). [paper][code(CCF-A)

14. Wenbin Ge, Xiankai Lu*, Jianbing Shen.  "Video Object Segmentation Using Global and Instance Embedding Learning", in the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 (CCF A).[paper]

15. Xiankai Lu, Wenguan Wang, Jianbing Shen, David Crandall, Jiebo Luo "Zero-Shot Video Object Segmentation with Co-Attention Siamese Networks", in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 (CCF A中科院一区,ESI高被引论文)

16. Xiankai Lu, Chao Ma, Jianbing Shen, Xiaokang Yang, Ian Reid, and Ming-Hsuan Yang  "Deep Object Tracking with Shrinkage Loss", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 (CCF A,中科院一区,ESI高被引论文)

17. Xiankai Lu, Wenguan Wang, Martin Danelljan, Tianfei Zhou, Jianbing Shen, Luc Val Gool,  "Video Object Segmentation with Episodic Graph Memory Networks," in European Conference on Computer Vision  (ECCV), spotlight, 2020 (CCF B). [paper][code

18. Xiankai Lu, Wenguan Wang, Jianbing Shen, Yu-Wing Tai, David Crandall, Steven C.H.Hoi,  "Learning Video Object Segmentation from Unlabeled Videos," in the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020 (CCF A).  [paper][code]

19. Wenguan Wang, Jianbing Shen, Xiankai Lu, Steven C. H. Hoi, Haibin Ling, "Paying Attention to Video Object Pattern Understanding", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020 (CCF A, 中科院一区).[paper][code]

20. Xiankai Lu, Chao Ma, Bingbing Ni, Xiaokang Yang, "Adaptive Region Proposal with Channel Regularization for Robust Object Tracking", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2019 (CCF B,ESI高被引论文). [paper][code]

21. Wenguan Wang*, Xiankai Lu*,  Jianbing Shen, David J Crandall, Ling Shao,  "Zero-shot video object segmentation via attentive graph neural networks ", in the IEEE International Conference on Computer Vision (ICCV) Oral, 2019 (CCF A).  [paper][code]

22. Ziyi Shen, Wenguan Wang, Xiankai Lu, Jianbing Shen, Haibin Ling, Tingfa Xu, Ling Shao, "Human-Aware Motion Deblurring", in the IEEE International Conference on Computer Vision (ICCV), 2019 (CCF A).  [paper][code] 

23. Xiankai Lu*, Wenguan Wang*, Chao Ma, Jianbing Shen, Ling Shao, and Fatih Porikli, "See More, Know More: Unsupervised Video Object Segmentation with Co-attention Siamese Network," in the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (CCF A).  [paper][code]

24. Xiankai Lu*, Chao Ma*, Bingbing Ni, Xiaokang Yang, Ian Reid, and Ming-Hsuan Yang, "Deep Regression Tracking with Shrinkage Loss," in European Conference on Computer Vision (ECCV), 2018 (CCF B). [paper][code]

25. Xiankai Lu, Z. Fang, T. Xu, H. Zhang, H. Tuo. “Efficient Image Categorization with Sparse Fisher Vector”, ICASSP 2015. (CCF B)

研究概况

计算机视觉,视频分析与理解,深度学习,机器学习

论文

(1) 张欣欣.Two-phase Parametric Registration for Retinal Images.2024

(2) 吴鹏.Clip Fusion with Bi-level Optimization for Human Mesh Reconstruction from Monocular Videos.2023

(3) Unified 3D Segmenter As Prototypical Classifiers.2023

(4) 秦者云.Coarse-to-Fine Video Instance Segmentation With Factorized Conditional Appearance Flows.IEEE/CAA Journal of Automatica Sinica.2023,10 (5):1192

(5) 张童.Relational Network via Cascade CRF for Video Language Grounding.IEEE transactions on multimedia.2023 :1-15

(6) 宫永顺.Missingness-Pattern-Adaptive Learning With Incomplete Data.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE.2023 (9)

(7) 孙皓亮.Attentional Prototype Inference for Few-Shot Segmentation. Pattern Recognition.2023 (142)

(8) 秦者云.Learning hierarchical embedding for video instance segmentation.2021

(9) 卢宪凯.Segmenting objects from relational visual data.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE.2022 (11)

(10) 秦者云.Coarse-to-Fine Video Instance Segmentation With Factorized Conditional Appearance Flows.IEEE/CAA Journal of Automatica Sinica.2023,10 (5)

(11) 孙皓亮.Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization.2022

(12) 卢宪凯.CubeNet: X-shape connection for camouflaged object detection. Pattern Recognition.2022,127 (127)

(13) 卢宪凯.Zero-Shot Video Object Segmentation with Co-Attention Siamese Networks.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE.2022 (4)

(14) 卢宪凯.Video Object Segmentation Using Global and Instance Embedding Learning.2021

(15) 滕隽雅.Regularized Two Granularity Loss Function for Weakly Supervised Video Moment Retrieval. IEEE Transactions on Multimedia.2021,24 :1141

(16) Ji, Jinsheng.Multi-level dictionary learning for fine-grained images categorization with attention model.Neurocomputing.2021,453 :403

(17) Ji, Jinsheng.Multi-level dictionary learning for fine-grained images categorization with attention model.Neurocomputing.2021,453 :403

(18) Xiankai Lu.See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks.CVPR.2019

(19) Learning Video Object Segmentation from Unlabeled Videos.CVPR 2020.2020

版权所有   ©山东大学 地址:中国山东省济南市山大南路27号 邮编:250100 
查号台:(86)-0531-88395114
值班电话:(86)-0531-88364731 建设维护:山东大学信息化工作办公室