浙大计算机学院朱建科,朱建科

朱建科，男，博士，浙江大学计算机科学与技术学院教授，博士生导师[1]

。

中文名

朱建科

毕业院校

学位/学历

博士职 业

教师

专业方向

计算机视觉、机器学习

就业院校

浙江大学计算机科学与技术学院

朱建科研究方向

编辑

语音

计算机视觉、机器学习[1]

朱建科人物经历

编辑

语音

IEEE资深会员身份自2009年起获得这一领域最高荣誉。凭借该博士学位, 他同时获得了该年度香港中文大学工程学院最优博士论文奖以及香港中文大学青年学者论文奖两项殊荣。在攻读博士学位期间, 他作为访问学者身份参与了UIUC ECE系I mage Processing Group的合作研究项目。自2009年1月起, 他便正式加入瑞士ETH Zurich的BIWI计算机视觉实验室, 开展博士后研究工作。现为阿里巴巴-浙江大学前沿技术联合研究中心下设计算机视觉与视频分析实验室负责人。

朱建科主讲课程

编辑

语音

数据结构基础

计算机视觉

视觉目标识别与检索

信息检索与搜索引擎(香港中文大学吕荣聪教授暑期班)[1]

朱建科学术成果

编辑

语音

朱建科科研项目

该团队主导开发的"俪知虚拟人"项目荣获阿里巴巴集团最佳学术合作项目奖。其任国际期刊Neurocomputing与Springer Big Data Analytics编辑委员会委员，并即是IEEE TPAMI、TIP、TNNLS等国际知名期刊的审稿专家；同时担任AAAI/IJCAI/CVPR等重要会议的程序委员会(PC)和指导委员会(SPC)成员。

朱建科期刊/著作

[1]Hantang Liu,Yinghao Xu,Jialiang Zhang,Yang Li,Steven C.H.Hoi and Jian-Kai Zhu*, "A Deep-Learning-Based Method forFacade Parsing Task with Symmetry-Oriented Loss",IEEE Trans.on Multimedia,2020

该研究团队提出了SuPer框架，在IEEE机器人学与自动化 letters（RA-L）以及国际机器人自动化大会(ICRA)上发表。

[3]Wu Xiongwei, Zhang Daoxin, Hoi Steven C.H., Zhu Jianke, “基于单阶段双向金字塔网络的高质量物体检测技术”, Neurocomputing, 2020.

[4] Steven Hoi and Jianke Zhu* Xiongwei Wu and Jialiang Zhang, 基于单一阶段的特征凝聚网络用于面部检测, 神经计算学报, 2020.

Adaptive Saliency-Based Regularization for Object Tracking via Correlation Filters was introduced by Wei Feng, Ruize Han, Qing Guo, Jianke Zhu, and Song Wang in IEEE Transactions on Image Processing, volume 28, issue 7, pages 3232 to 3245 in the year 2019.

[6]Qingqun Ning, Zhao Liu,Jianke Zhu, Mingli Song, Jiajun Bu and Chun Chen, “Noise-aware Co-segmentation with Local and Global Priors”,Neurocomputing287: 221-231 (2018)

[7] Song Wenji, Li Yang, Zhu Jianke and Chen Chun, "Time-Aligned Correlational Filtering-Based Tracking", Neurocomputing (Published in the Neurocomputing journal, Volume 286): 121–129 (2018)

该研究团队提出了一种高效的方法用于图像分割，在《认知计算》期刊上发表的文章中提到，在第10卷第1期中报道了这一方法，并且在第62到72页（2018年）

[9] Xingyu Gao et al., "Sparse Online Learning of Image Similarity." 发表于 ACM Transactions on Interactive and Smart Systems, 第8卷第5期, 页码为64:1至64:22 (2017).

Qingqun Ning, Jianke Zhu, Zhiyuan Zhong和Chun Chen, "高效率的图像检索基于稀疏的产品量化方法", IEEE Transactions on Multimedia, March 2017.

[11]Jianke Zhu, Chenxia Wu, Chun Chen and Deng Cai, “Treelets Binary Feature Retrieval for Fast Keypoint Recognition”,IEEE Trans. onCybernetics,vol. 45, issue 10. Oct. 2015, pp. 2129 – 2141.

Wenjie Song et al., "Image Registration via Online Robust PCA Using SGD-based Optimization", IEEE Trans. Circuits Syst. Video Techn. 26(7): 1241-1250 (2016).

[编号]研究者团队，“一种基于直接空间匹配的对象检索方法”，IEEE Transactions on Multimedia第十七卷第八期（2015年8月），第十四页至第二十五页

Jianke Zhu, Chun Chen, Jiajun Bu和Zhao Liu对人类姿态估计方法进行了综述，并详细探讨了基于体部分割的方法。

Jianke Zhu, Chun Chen, Jiajun Bu和Zhao Liu对人类姿态估计方法进行了综述，并详细探讨了基于体部分割的方法

[15]Xinyu Wang,Jianke Zhu*,Zibin Zheng,Wenjie Song,Yuanhong Shen,and Michael R.Lyu,"基于时空服务质量预测的方法用于基于时间的Web服务推荐",ACM Transactions on Web,2016.

[16]Xinyu Wang,Jianke Zhu*and Yuanhong Shen, “Network-aware QoS prediction for Service Composition Using Geolocation”,IEEE Trans. on Service Computing(TSC),vol. 8, issue 4. July-Aug 2015, pp.630 – 643.

该文献由Dayong Wang及其合著者Steven C. H. Hoi,Ying He,Jianke Zhu,Tao Mei和Jiebo Luo共同撰写，并介绍了"基于检索的方法用于弱标签正则化局部坐标编码的面部注释"这一创新性研究。该研究发表于《模式分析与机器智能 transactions》期刊的第36卷中，在2014年3月号上占据了第550至563页。

This method of mining weakly labeled web facial images has been utilized for search-based face annotation by corresponding authors Dayong Wang, Steven C.H. Hoi, Ying He and Jianke Zhu in their work titled "Mining weakly labeled web facial images for search-based face annotation" published in the IEEE Transactions on Knowledge and Data Engineering in January 2014, covering pages 166 to 179.

[19]Luming Zhang, Yue Gao, Chaoqun Hong, Yinfu Feng,Jianke Zhuand Deng Cai, 'Feature Correlation Hypergraph: Exploiting High-order Potentials for Multimodal Recognition,'IEEE Trans. on Cybernetics, vol. 44. Aug. 2014, 1397-1407.

[20]Zhao Liu,Jianke Zhu, Jiajun Bu and Chun Chen, “Object Cosegmentation by Nonrigid Mapping”,Neurocomputing, vol. 135, 2014, pp. 107-116.

[21]Xia Chen,Jianke Zhu,Deng Cai, Chun Chen and Jiajun Bu, “基于半监督增强学习的非线性序列投影编码哈希算法”，IEEE Trans. on Knowledge and Data Engineering, vol. 25, June 2013, pp. 1380-1393.

Chaoqun Hong and Jianke Zhu's work titled "A Hypergraph-Based Multi-Example Ranking with Sparse Representation for Image Retrieval via Transductive Learning" was published in the journal Neurocomputing in February 2013, Volume 101, pages 94 to 103.

[23]Lei Wu, Steven C.H. Hoi, Rong Jin, Jianke Zhu and Nenghai Yu,"Learning Bregman Distance Functions for Semi-supervised Clustering,"IEEE Trans. on Knowledge and Data Engineering, 2012

[24]Wu Hao, Bu Jiajun, Chen Chun, Jianke Zhu, Zhang Lijun, Liu Haifeng, Wang Can and Cai Deng,"Local discriminativity topic modeling."Pattern Recognition45(1): 617-625 (2012).

[25]Lei Wu, Steven C.H. Hoi, Rong Jin,Jianke Zhuand Nenghai Yu, “Distance Metric Learning from Uncertain Side Information for Automated Photo Tagging,”ACM Trans. on Intelligent Systems and Technology, Nov., 2011.

[26] Jianke Zhu, Steven C.H. Hoi, Michael R. Lyuand Shuicheng Yan, "An unsupervised method for identifying similar keyframes in multimedia retrieval," ACM Transactions on Multimedia Computing and Applications (TOMCCAP), February 2011.]

[27]Hao Ma,Jianke Zhu, Michael R. Lyuand Irwin King, “Bridging the Semantic Gap between Image Contents and Tags,”IEEE Trans. on Multimedia, August 2010.

Jianke Zhu、Michael R. Lyu和Thomas S. Huang提出了一种高效的方法用于二维形状重建：通过融合特征与外观信息实现快速形状恢复。该方法发表于IEEE Trans. on Pattern Analysis and Machine Intelligences(TPAMI)期刊上，在第31卷中于7月号呈现了pp.1210-1224的研究成果。

[29]Steven C.H. Hoi, Rong Jin,Jianke Zhuand Michael R. Lyu, “Semi-Supervised SVM Batch Mode Active Learning with Applications to Image Retrieval,”ACM Trans. on Information Systems(TOIS),vol. 27, May 2009.

Zenglin Xu, Kaizhu Huang、Jianke Zhu、Irwin King以及Michael R. Lyu在《神经网络》期刊上发表了一篇题为《一种基于核的最大后验分类方法》的研究论文。该论文详细探讨了该分类方法在神经网络领域中的应用与效果分析，并在第22卷第977至987页中进行了详细阐述

[31]Jianke Zhu, Steven C.H. Hoi and Michael R. Lyu, 'Robust Regularized Kernel Regression,'IEEE Trans. on Systems, Man, and Cybernetics - Part B: Cybernetics, 2008.

Jian KE ZHU, STEVEN C.H. HOI and MICHAEL R. LYU employed the method 'Transductive Kernel Fisher Discriminant' in their work 'Face Annotation,' published in IEEE Transactions on Multimedia in January 2008, volume 10, pages 86–96

Jian KE ZHU, STEVEN C.H. HOI and MICHAEL R. LYU employed the method 'Transductive Kernel Fisher Discriminant' in their work 'Face Annotation,' published in IEEE Transactions on Multimedia in January 2008, volume 10, pages 86–96

Conference Paper

[33]Shu-Ting Shi, Wenhao Zheng, Jun Tang, Qing-Guo Chen, Yao Hu,Jianke Zhu, Ming Li, “Deep Time-Stream Framework for Click-Through Rate Prediction by Tracking Interest Evolution”,AAAI 2020.

[34] Jianbo Wang et al., "AI Coach: Deep Human Pose Estimation and Analysis for Personalized Athletic Training Assistance," ACM Multimedia 2019: 374-382. Full paper in the main track.

Jianbo Wang, Kai Qiu, Houwen Peng, Jianlong Fu,Jianke Zhu,"An AI-Powered Coaching System: Advanced Human Pose Estimation and Insight into Tailored Athletic Training."ACM Multimedia 2019:2228-2230.DemoPaper.

Li Yang,Jianke Zhu*,Steven Hoi,Wenjie Song,Zhefeng Wang and Hantang Liu,"Resilient Estimation of Similarity Transform on Visual Object Tracking",AAAI 2019:8666-8673.

Jianke Zhu的研究表明，在双目相机中应用基于图像梯度的联合直接视觉定位技术能够显著提升精度

[38] Yang Li, Zhan Xu, Jianke Zhu*, the CFNN model represents a significant advancement in visual object tracking technology through its innovative integration of correlation filters and neural network architectures. This study was presented at the IJCAI conference in 2017.

[39]Hantang Liu、Jialiang Zhang、Jianke Zhu*、Steven C.H. Hoi提及了一种基于深度学习的方法用于Facade解析，在IJCAI 2017年会议论文集中有详细阐述

Yang Li, Jianke Zhu, and Steven C.H. Hoi propose the following reference文献格式 for robust visual tracking employing reliable patch extraction methods, as presented at the CVPR 2015 conference.

Li and Zhu developed a scale-invariant kernel correlation filter tracker that integrates feature matching, achieving outstanding results in the VOT'14 challenge held during the ECCV 2014 workshop. Their work ranked second among thirty-eight submissions.

[42]Ji Wan, Dayong Wang, Steven C.H. Hoi, Pengcheng Wu,Jianke Zhu, Yongdong Zhang and Jintao Li, “Deep Learning for Content-based Image Retrieval: A Comprehensive Study”,ACM Multimedia 2104.

Xia Chen等人在IEEE Big Data 2013年会议上发表了题为《基于稀疏泊松编码的高维文档聚类方法》的短文

[44]Jianke Zhu,Yuanhong Shen,Xinyu Wang,Liang Cai,Xiaohu Yang,and Bo Zhou,"基于地理位置的网络意识QoS预测服务组合",Research Track,ICWS 2013

[45] Wang D., Hoi S.C.H., Wu P., Zhu J., He Y., and Miao C., "Facial Name Learning: A Cross-Modal Learning Framework for Annotation for Face Retrieval", SIGIR 2013.

该研究提出了一种名为FANS的方法，在WWW 2013会议的演示环节中展示了基于大规模网络面部图像的面部注释技术

[47] Jiemi Zhang, Chenxia Wu, Deng Cai and Jianke Zhu. "双层视觉单词编码用于图像分类", IJCAI 2013.

In their study titled "A Convolutional Treelets Binary Feature Approach to Fast Keypoint Recognition", Chenxia Wu and her colleagues presented a novel method at the ECCV 2012 conference.

[49]Chaoqun Hong, Jianke Zhu, Mingli Song, and Yinting Wang, "Real-time Object Matching with Robust Dominant Orientation Template," presented at the 10th International Conference on Pattern Recognition in 2012.

[50]Chenxia Wu, Zhuang Jianke and Jiemi Zhang, "一种基于内容的视频复制检测方法与随机二元投影特征," CVPR 工作坊 on LSVSM 2012.

Jiajun Bu et al. presented an unsupervised method for face-name association based on the concept of commute distance at the ACM Multimedia Conference in 2012.

该团队开发了一种低秩半定规划的社会推荐方法，在AAAI 2011会议上进行了展示

[53]Dayong Wang et al., "Face annotation based on retrieval techniques utilizing weakly labeled data and local coordinate coding," ACM Multimedia 2011: 353-362.

[54]Zhu Jianke,Luc Van Goolen,Steven C.H.Ho,"无需监督的面部对齐方法基于稳健的非刚性映射",IEEE International Conference on Computer Vision (ICCV2009).

Zenglin Xu et al., "An Adaptive Regularization Framework for Transductive Support Vector Machines," Advances in Neural Information Processing Systems (NIPS2009).

[56]Lei Wu, Rong Jin, Steven C.H. Hoi, Jianke Zhu and Nenghai Yu, 'Developing Bregman Divergence Measures and Their Use in Semi-Supervised Clustering,' Advances in Neural Information Processing Systems (NIPS 2009).

[57] Jianke Zhu, Steven C.H. Ho, and Michael R. Lyu, "Nonrigid Shape Recovery via Gaussian Process Regression," IEEE Conference on Computer Vision and Pattern Recognition (CVPR2009).

基于不确定侧面信息的距离度量学习及其在自动化的照片标签应用中的研究

[59] Jianke Zhu, Steven C.H. Hoi, Michael R. Lyu and Shuicheng Yan, “Near-Duplicate Keyframe Retrieval based on Nonrigid Image Matching,” ACM Multimedia Conference Proceedings 2008.

Jianke Zhu et al. presented a powerful method for 3D deformable surface tracking at the 10th European Conference on Computer Vision in 2008.

Steven C.H. Hoi等提出了基于半监督支持向量机的批模式主动学习方法用于图像检索的研究，在IEEE 会议（CVPR2008）上进行了详细阐述

Jianke Zhu and Michael R. Lyu presented the Progressive finite Newton method for real-time non-rigid surface detection at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) in June 19–21, 2007.

该研究组提出了一种多层次的Tikhonov正则化方案用于隐式曲面建模，并在IEEE CVPR 2007会议上发表了论文

Zenglin Xu and his co-authors presented an Effective Semidefinite Relaxation method for the Transductive SVM problem at the Advances in Neural Information Processing Systems (NIPS 2007) conference.

[65]Jianke Zhu, Steven C.H. Hoi and Michael R. Lyu, “The Real-Time Non-Rigid Shape Recovery via Active Appearance Models for Augmented Reality,” inProceedings of The 9th European Conference on Computer Vision (ECCV2006), LNCS 3951,Graz, May 7-13, 2006, pp.12-23.

[66]Steven C.H. Hoi, Rong Jin,Jianke Zhuand Michael R. Lyu, “Batch Mode Active Learning and Its Application to Medical Image Classification,”The 23th International Conference on Machine Learning (ICML2006),Pittsburgh, June 25-29, 2006.

Zenglin Xu and his colleagues, including Kaizhu Huang, Jianke Zhu, Irwin King, and Michael R. Lyu, presented their work titled 'Kernel Maximum a Posteriori (KMP) Classification with Error Bounds Analysis' at the International Conference on Neural Information Processing in 2007 (referred to as ICONIP 2007), where their research was published in volume 4984 of the Lecture Notes in Computer Science series.

Xu Zenglin, Zhu Jianke, Lyu Michael R., 和 King Irwin 在 IJCNN 2007 上发表了论文《Semi-supervised Spectral Kernel Learning》

Hongbo Deng Jianke Zhu Michael R. Lyu Irwin King提出了一种双阶段多类别Adaboost算法用于面部表情识别的研究，并在国际神经网络系统联合会议上发表。

Chon Fong Wong Jianke Zhu Mang I Vai Peng Un Mak 在《应用与数值调和分析系列》一书中提出了利用提升小波特征实现基于相关反馈的面部图像检索的方法。

Zhu Jianke, Steven C.H. Hoi et al., "Automatic three-dimensional face modeling based on two-dimensional active appearance models," In Proceedings of the 13th Pacific Conference on Computer Graphics and Applications (PG2005), held in Macau, China during October 12–14, 2005.

Steven C.H. Hoi, Jianke Zho and Michael R. Lyu presented in the proceedings of the Cross Language Evaluation Forum (CLEF2005) with their work CUHK at ImageCLEF 2005: advancing cross-language and cross-media image retrieval techniques as part of LNCS 4022 held in Vienna, Austria during the year 2006.

Chon Fong Wong, Jianke Zhu, Mang I. Vai, and Peng Un Mak presented "Face Image Retrieval using the Lifting Wavelet Transform Feature Extraction Technique in Video Sequences" at the International Conference on Computer Electronics (ICCE) held in Macau during ICSE 2005.

[74]Jianke Zhu,Mang I Vai and Peng Un Mak,“Gabor Wavelets Transform and Extended Nearest Feature Space Classifier for Face Recognition,”inProceedings Third International Conference on Image and Graphics (ICIG2004),Hong Kong, Dec. 28-30, 2004, pp.372-379.

[75]Jianke Zhu,Mang I Vai and Peng Un Mak,“A New Enhanced Nearest Feature Space (ENFS) Classifier for Gabor Wavelets Features Based Face Recognition,”inProceedings First International Conference on Biometrics Authentication (ICBA2004), LNCS 3072,Hong Kong, July 15-17, 2004, pp.124-131.

Jianke Zhu,Mang I Vai and Peng Un Mak,"2D DCT combined with PCA for face recognition."Proceedings of the 4th Chinese Conference on Biometric Recognition (Biometrics'03),Beijing,P.R.China.

朱建科学术论文

Jianke Zhu earned his Doctoral Dissertation in the field of computer science under the supervision of Prof. Michael R. Lyu at The Chinese University of Hong Kong in 2008, where his research focused on 'Deformable Surface Recovery and Its Applications'.

Jianke Zhu completed his Master's Thesis entitled "Real-Time Face Recognition Technology", supervised by Prof. Mang I Vai and Prof. Peng Un Mak at the Department of Electrical and Electronics Engineering, University of Macau, in March 2005.

词条图册

更多图册

参考资料

朱建科

．浙江大学[引用日期2020-04-07]