田彦,男,教授、硕士生导师,民盟盟员,美国卡内基梅隆大学与北京邮电大学联合培养博士,浙江大学博士后。主要研究方向为计算机视觉、几何分析、机器学习等。已在IEEE Transactions on ITS、PR、NC等SCI TOP期刊上以第一作者发表十余篇学术论文,其中ESI高被引论文3篇;在UAI等CCF-B高水平学术会议做大会演讲2次;已出版《计算机视觉前沿发展: 目标检测专题》等学术专著;授权20余项国家发明专利和软件著作权,其中多项已经成功成果转化。主持国家自然科学基金(3项)、浙江省自然科学基金等项目10余项。入选“西湖学者拔尖人才”、“浙江省高校领军高层次人才”计划,任中国计算机学会计算机辅助设计与图形学专委会委员、浙江省人工智能协会增强现实分会副秘书长。
从2015年起参与研究生和实习生的培养工作,指导硕士研究生在读期间入选新苗人才计划,每个培养的研究生和实习生均发表了高水平科研论文或发明专利,学生毕业时起薪均在20万/年以上。具体研究工作和发表论文可搜索个人主页:yaletian
- 发表论文
Yan Tian, Tao Chen, Guohua Cheng, Shihao Yu, Xi Li, Jianyuan Li, Bailin Yang*, “Global Context Assisted Structure-aware Vehicle Retrieval,” IEEE Transactions on Intelligent Transportation Systems, 23(1), 2022: 165-174. (SCI TOP, CCF-B, IF=6.31)
Yan Tian, Yujie Zhang, Huayi Xu, Jianfeng Han, Wei-Gang Chen, Dongsheng Liu, Yiwen Ge, Huiyan Wang*. 3D Tooth Instance Segmentation Learning Objectness and Affinity in Point Cloud. ACM Transactions on Multimedia Computing Communications and Applications, 2022. (CCF-B, IF=3.98)
Wanting Ji, Ruili Wang, Yan Tian, Xun Wang. An attention based dual learning approach for video captioning. Applied Soft Computing. 2022. (SCI Q2, IF=6.72)
Di Zhou, Yan Tian*, Wei-Gang Chen, Gang Huang. “Self-Supervised Saliency Estimation for Pixel Embedding in Road Detection”, IEEE Signal Processing Letters, 28(8), 2021: 1325-1329. (SCI Q2, IF=3.10)
Yan Tian, Guohua Cheng, Shihao Yu, Judith Gelernter, Chao Song, Bailin Yang*, “Joint Temporal Context Exploitation and Active Learning for Video Segmentation,” Pattern Recognition, 100, 2020: 107158. (CCF-B, IF=7.19)
Yan Tian, Yujie Zhang, Di Zhou, Guohua Cheng, Wei-Gang Chen, Ruili Wang*, “Triple Attention Network for Video Segmentation,” Neurocomputing, 2020, 417: 202-211. (SCI Q2, IF=4.43)
Xun Wang, Yan Tian*, Xuran Zhao, Tao Yang, Judith Gelernter, Jialei Wang, Guohua Cheng, and Wei Hu, “Improving Multiperson Pose Estimation by Mask-aware Deep Reinforcement Learning,” ACM Transactions on Multimedia Computing, Communications, and Applications, 16(3), 2020, in press. (CCF-B, IF=3.98)
Guohua Cheng*, Hongli Ji, Yan Tian, “Walking on Two Legs: Learning Image Segmentation with Noisy Labels”, Uncertainty in Artificial Intelligence (UAI), 2020. (CCF-B, 142/515=27.5%) (Oral)
Guohua Cheng*, Jingliang Cheng, Mengyan Luo, Linyang He, Yan Tian, and Ruili Wang, “Effective and Efficient Multitask Learning for Brain Tumor Segmentation,” Journal of Real-time Image Processing, 2020, 17: 1951-1960. (SCI Q3, IF=1.96)
Zhe Chen, Hongmin Gao, Zhen Zhang, Helen Zhou, Xun Wang*, YanTian, “Underwater salient object detection by combining 2D and 3D visual features”, Neurocomputing, 2020, 391: 249-259. (SCI Q2, IF=4.43)
Yan Tian, Judith Gelernter, Xun Wang*, Jianyuan Li, and Yizhou Yu, “Traffic Sign Detection Using a Multi-Scale Recurrent Attention Network,” IEEE Transactions on Intelligent Transportations Systems, 20(12), 2019: 4466-4475. (SCI TOP, CCF-B, IF=6.31)
Yan Tian, Xun Wang*, Jiachen Wu, RuiliWang, Bailin Yang, “Multi-scale Hierarchical Residual Network for Dense Captioning,” Journal of Artificial Intelligence Research, 64, 2019: 181-196. (CCF-B, IF=2.44)
Yan Tian*, Wei Hu, Hangsen Hang, Jiachen Wu*, “Densely Connected Attentional Pyramid Residual Network for Human Pose Estimation”, Neurocomputing, 347, 2019:13-23. (SCI Q2, IF=4.43)
Yan Tian, Yifan Cao, Wei Hu, Jiachen Wu, Chao Song, Tao Yang*, “Multi-cue Combination Network for Action-based Video Classification”, IET Computer Vision, 13(6), 2019: 542-548. (SCI Q4, IF=1.51)
Bailing Yang, Shulin Sun, Jianyuan Li, Xianxuan Lin, and Yan Tian*, “Traffic Flow Prediction Using LSTM with Feature Enhancement”, Neurocomputing, 332, 2019: 320-327. (SCI Q2, IF=4.43, ESI highly cited paper)
Wei-Gang Chen, Yuxuan Chen, Xun Wang, Yan Tian, RunYi Yu, “A learning-based method for lane detection using regionlet representation”, IET Intelligent Transport Systems, 13(12), 2019: 1745-1753. (SCI Q4, IF=2.05)
Wanting Ji, Yirui Wu, Xiaozhong Ji, Yan Tian, Helen Zhou, “CASR: A Context-aware Residual Network for Single Image Super-Resolution”, Neural Computing and Applications, 2019: 1-16. (CCF-C, IF=4.77)
Yan Tian, Kaili Zhang, Jianyuan Li, Xianxuan Lin, and Bailing Yang*, “LSTM Based Traffic Flow Prediction with Missing Data,” Neurocomputing, 318, 2018: 297-305. (SCI Q2, IF=4.43, ESI highly cited paper)
Yan Tian, Judith Gelernter, Xun Wang*, Weigang Chen, Junxiang Gao, Yujie Zhang, and Xiaolan Li, “Lane Marking Detection via Deep Convolutional Neural Network,” Neurocomputing, 280, 2018: 46-55. (SCI Q2, IF=4.43)
Yan Tian, Huiyan Wang, and Xun Wang*, “Object Localization via Evaluation Multi-task Learning,” Neurocomputing, 253, 2017: 34-41. (SCI Q2, IF=4.43)
Wei-Gang Chen*, Xun Wang, and Yan Tian, “A two-stage algorithm for the early detection of zero-quantized discrete cosine transform coefficients in High Efficiency Video Coding,” EURASIP Journal on Image and Video Processing, 2017. (SCI Q4 IF=1.74)
Bailin Yang, Zhaoyi Jiang, Yan Tian, Jiantao Shangguan, Chao Song, Yibo Guo and Minglinang Xu, “A Novel Dynamic Mesh Sequence Compression Framework for Progressive Streaming”, International Conference on Virtual Reality and Visualization (ICVRV), 2017: 49-54.
Yan Tian, Gang Huang, Huiyan Wang, and Xun Wang*, “Multi-task Network Combing Multi-Level Information for Object Localization,” International Conference on Chinagraph 2016, Hangzhou, P.R.China, 2016.
Yan Tian*, Leonid Signal, Fernando de La Torre, and Yonghua Jia, “Canonical Locality Preserving Latent Variable Model for Discriminative Pose Inference”, Image and Vision Computing, 31(3), 2013: 223-230. (SCI Q3, IF=3.10)
Yan Tian*, Yuan Shi and Yong Liu, “Inferring 3D Body Pose Using Variational Semi-Parametric Regression”, IEEE International Conference on Image Processing (ICIP), Brussels, Belgium, 2011. (Oral)
H Ji*, R Liu, F Su, Z Su, Yan Tian, “Robust head pose estimation via convex regularized sparse regression”, IEEE International Conference on Image Processing (ICIP), Brussels, Belgium, 2011.
- 在审/授权专利(仅列出所有权归浙江工商大学的专利)
徐照程, 田彦,一种基于多尺度跨图像弱监督学习的违禁物检测方法,专利申请号2021102756403, 申请日2021-03-15。
田彦,王勋,王慧燕,华璟,基于集成学习级联分类器的车道线检测方法,授权号201610563188.X,授权日2019-05-14。
田彦,王勋,吴佳辰,一种基于多尺度循环注意力网络的交通标识符检测方法,授权号201810360701.4,授权日2020-08-14。
徐照程, 田彦,一种基于自监督学习显著性估计像素嵌入的道路检测方法,申请号202110600086.1,公开日2021-08-12。
来锴楠,田彦,基于弱监督学习的域自适应实例分割方法及装置,申请号202210236149.4,申请日2022-03-11。
田彦, 王勋, 吴佳辰,一种基于掩码感知深度强化学习的多人物姿态估计方法,授权号201810968949.9,申请日2020-09-29。(已转让)
田彦, 王勋, 蒋杭森,一种结合密集连接注意力金字塔残差网络和等距限制的人体3D姿势估计方法. 授权号201810362559.7, 授权日2020-08-28。 (已转让)
田彦,王勋,黄刚,一种基于多尺度分层残差网络的图像多字幕自动生成方法,专利号201710896059.7,授权日2020-04-28。
徐照程,田彦,一种基于跨图注意力机制和代价函数学习的牙模点云分割方法,申请号202111012399.1,申请日2021-08-31。
- 主持/参与项目
国家自然科学基金,61972351,面向口腔医学的视频驱动3D重建及异质信息融合,2020/01-2023/12,59万元,在研,主持
国家自然科学基金,62111530300,数据驱动的3D数字化及异质数据分析研究,2022/01-2023/12,20万元,在研,主持
国家自然科学基金,61602407,基于数据驱动的移动终端非刚体3D重建,2017/01-2019/12,20万元,结项,主持
国家自然科学基金,U1609215,面向移动电子商务的可视体验计算,2017/01-2020/12,210万元,结项,参与
国家自然科学基金,61672460,分布式智能摄像机协同的非正常事件检测技术研究,2017/01-2020/12,62万元,结项,参与(3/8)
国家自然科学基金,6211101461,显著性和骨架驱动的动态点云流传输机制研究,2022/01-2025/12,万元,在研,参与
国家自然科学基金,61702453,基于对抗式生成网络和用户交互的单目图像深度估计,2018/01-2020/12,24万元,结项,参与
–
教育部国际司,促进与加拿大、澳大利亚、新西兰及拉美地区科研合作与高层次人才培养项目,2020/01-2022/12, 10万元,在研,主持
浙江省自然科学基金,LY19F030005,基于对抗式生成网络的交通场景目标检测,2019/01-2021/12,9万元,在研,主持
浙江省自然科学基金,LY18F020008,基于深度学习的人体运动识别、解释和预测,2018/01-2020/12,8万元,在研,参与
省重点研发计划项目,2021C01120,多谱超高清智能视频监控系统关键技术研究及应用,2021/01-2023/12,万元,在研,参与(4/25)
–
北京航空航天大学虚拟现实与系统国家重点实验室开放课题, VRLAB2020B15,面向口腔医学的视频驱动3D重建, 2020/05-2021/05,4万元,在研,主持
智能信息处理与实时工业系统湖北省重点实验室,znxx2018MS04,基于注意力机制的多人3D姿势估计,2017/10-2019/10,2万,结项,主持
浙江大学CAD&CG国家重点实验室开放课题,A1811,面向人机交互的多人3D姿势估计,2018.1-2018.12,2万元,结项,主持
北京航空航天大学虚拟现实与系统国家重点实验室开放课题, BUAA-VR-16KF-19,基于卷积神经网络的非刚体目标3D重建, 2016/05-2018/05,4万元,结项,主持
–
银江股份有限公司,2017ERCITZJ-KF04,基于数据驱动的卡口图像车辆检索研究,2017/09-2018/09,5万元,结项,主持
银江股份有限公司,2016ERCITZJ-KF02,车辆出行行为画像分析研究,2016/09-2017/09,5万元,结项,参与