王诗言
副教授 Supervisor of Doctorate Candidates Supervisor of Master's Candidates
Gender:Female
Alma Mater:浙江大学
Education Level:With Certificate of Graduation for Doctorate Study
Degree:Doctoral Degree in Engineering
Status:在岗
School/Department:教育发展研究院
Business Address:四教4420
E-Mail:
| |
王诗言,博士,副教授,博士生导师,目前在重庆邮电大学从事教学和科研工作。主要研究方向包括:面向自动驾驶的目标检测、分割、跟踪与识别、智能视频分析技术、图像复原技术等。主持并参与国家重大专项、国家自然科学基金等国家级课题20余项,相关研究成果在重要国内外SCI/EI期刊IEEE Transactions on Intelligent Transportation Systems, IEEE Transactions on Neural Network and Learning Systems, Knowledge-Based Systems, Pattern Recognition, 自动化学报等发表30余篇,授权专利10余项。相关教育教学成果获国家级教学成果奖二等奖1项,重庆市教学成果奖一等奖1项。
主要工作经历
· 2014-至今 重庆邮电大学
· 2013-2014 中国电子科技集团第二十四研究所
主要学习经历
· 2008-2013 浙江大学 博士
· 2004-2008 西安交通大学 本科
研究方向
图像处理、计算机视觉、人工智能、深度学习
主要研究项目
[1] 国家自然科学基金面上项目,面向损伤检测的域自适应模型构建与多模态特征融合方 法研究,(62571077),2026/1-2029/12,主持。
[2] 重庆市科学技术研究计划重点项目,面向自动驾驶场景的轻量化视觉感知方法研究(KJZD-K202600611),2026.7-2029.6,主持。
[3] 国家自然科学基金面上项目,目标检测的深度神经网络优化与模型压缩方法研究,(62471076),2025/01-2028/12,主研。
[4] 智能网联汽车AI视觉感知与辅助驾驶系统研发,横向项目,2026/07-2027/06,主持。
[5] 重庆市自然科学基金面上项目, 面向实际应用的自监督型图像超分辨率技术研究(cstc2021jcyj-msxmX0518),2021/10-2024/09,主持。
[6] 重庆市前沿与应用基础研究计划项目,基于图像协同分割的颅内出血区域快速诊断方法(cstc2016jcyjA0542),2016/07-2019/06,主持。
[7] 重庆市教委科技项目,三维视频中的运动分割与运动估计统一模型研究(KJ1500426),2016/01-2017/12,主持。
[8] 国家重大科技专项“新一代宽带无线移动通信网”课题“基于TD-LTE/TD-SCDMA的应急通信系统研发”子课题(2014ZX03001024-005),2014/01-2016/12,主持。
[9] 空地宽带通信系统(ATG )体制及关键技术研究,国防单位横向项目,2014.6-2015.6,主持。
[10] 国家重大科技专项“新一代宽带无线移动通信网”课题“面向C-RAN的低功耗通用处理器平台研发”子课题(2014ZX03003004-003), 2013/2-2015/12,主研。
[11] 国家重大科技专项“新一代宽带无线移动通信网”课题“TD-LTE多频射频商用芯片研发”子课题(2013ZX03001010-005),2014/01-2016/12, 主研。
[12] 国家重大科技专项“新一代宽带无线移动通信网”课题“面向LTE-Advanced的终端软基带技术”子课题(2013ZX03003014-004), 2014/1-2015/12, 主研。
[13] 国家自然基金青年基金,基于合成视点感知失真模型的三维视频编码率失真优化及码率分配研究(61501074),2016.1-2018.12,主研。
[14] 国家自然基金青年基金,具有消极关系的耦合非线性系统同步与控制研究(11502039),2016.1-2018.12,主研。
[15] 重庆市前沿与应用基础研究计划项目,基于视觉感知失真度量的三维视频编码算法研究,2015.8-2018.7,主研。
代表论文/专利
[1] S.Y. Wang, M.T. Meng , M.X. Chang , Z.N. Yang. Learning Spatial-Frequency Adaptive Prototype for Remote Sensing Few-shot Segmentation[J], Knowledge-Based Systems, 2026, Volume 349, 116464. (SCI一区TOP期刊, IF:8.0, 通讯作者)
[2] S.Y. Wang, J.W. Zhao, J.J. Tang. Structure-aware Coarse-to-Fine Upsampling Network for Arbitrary-Scale Super-Resolution of Remote Sensing Images[J], Engineering Applications of Artificial Intelligence, 2026, Volume 164, Part A, 113046. (SCI一区TOP期刊, IF:11.2, 通讯作者)
[3] S.Y. Wang, J.W. Zhao, J.J. Tang. Multiscale Spatial-Spectral Attention Network for Arbitrary-Scale Hyperspectral Image Super-Resolution[J], Neurocomputing, 2026, Volume 661, 131950. (SCI二区期刊, IF: 6.5, 通讯作者).
[4] S.Y. Wang, J. Chen, H.P. Zhong, J.W. Zhao. HaarReformer: Haar Wavelet-based Transformer for Low-Light Image Enhancement[J], IEEE Multimedia, 2026, DOI:10.1109/MMUL.2026.3660217. (SCI四区, IF:3.3, 通讯作者)
[5] X.J. Han, Z. Qu, S.Y. Wang. Object Detection With Physical Prior and AWConv in Foggy Weather for Traffic Scenes[J], IEEE Transactions on Neural Network and Learning Systems, 2025, 36(10):18722-18736. (SCI一区TOP期刊, IF: 8.9, 通讯作者)
[6] S.Y. Wang, M.T. Meng. Few-shot Segmentation via Information Interaction Enhancement and Multi-scale Feature Aggregation[J], IEEE Multimedia, 2025, DOI: 10.1109/MMUL.2025.3607098. (SCI四区, IF:3.3, 通讯作者)
[7] J. Li, Z. Qu, S.Y. Wang, S. F. Xia. A method of road damage detection for complex background images based on region guidance network[J]. Pattern Recognition, 2025, Volume 168, 111780. (SCI一区TOP期刊, IF: 7.6)
[8] J. Li, Z. Qu, S. Y. Wang, S. F. Xia. YOLOX-RDD: A Method of Anchor-Free Road Damage Detection for Front-View Images[J]. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(10): 14725-14739. (SCI一区TOP期刊, IF: 8.4)
[9] L. Y. Gao, Z. Qu, S. Y. Wang, S. F. Xia. A Lightweight Neural Network Model of Feature Pyramid and Attention Mechanism for Traffic Object Detection[J]. IEEE Transactions on Intelligent Vehicles, 2024, 9(2): 3422-3435. (SCI一区, IF: 14.3)
[10] Z. Qu, C. Y. Wang, S. Y. Wang, F. R. Ju. A Method of Hierarchical Feature Fusion and Connected Attention Architecture for Pavement Crack Detection[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(9): 16038-16047. (SCI一区TOP期刊, IF: 8.4, 通讯作者)
[11] Q. Zhou, Z. Qu, S. Y. Wang. A Method of Potentially Promising Network for Crack Detection with Enhanced Convolution and Dynamic Feature Fusion[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10): 18736-18745. (SCI一区TOP期刊, IF: 8.4, 通讯作者)
[12] Z. Qu, W. Chen, S. Y. Wang , T. M. Yi, L. Liu. A Crack Detection Algorithm for Concrete Pavement Based on Attention Mechanism and Multi-Features Fusion[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(8): 11710-11719. (SCI一区TOP期刊, IF: 8.4, 通讯作者)
[13] S. Y. Wang, J. S. Zhang, X. Yu, F. Shi. SVDN: A Spatially Variant Degradation Network for Blind Image Super-resolution[J]. Pattern Recognition Letters, 2022, 153(1): 214-221.(SCI三区, IF: 3.9, 通讯作者)
[14] S. Y. Wang, X. Zeng, T. Zhou, H. D. Wu. Image Super Resolution Via Nonlocal and Second-order Feature Fusion Network[J]. Journal of Electronic Imaging, 2020, 29(2): 023022. (SCI四区, IF: 1.1, 通讯作者)
[15] X. J. Han, Z. Qu, S. Y. Wang, S. F. Xia. End-to-End Object Detection by Sparse R-CNN with Hybrid Matching in Complex Traffic Scenes[J]. IEEE Transactions on Intelligent Vehicles, 2023, 9(1): 2296-2306. (SCI一区, IF: 14.3)
[16] Shiyan Wang ; Yaoyao Wei ; Ken Long ; Xi Zeng ; Min Zheng. Image Super-Resolution via Self-Similarity Learning and Conformal Sparse Representation, IEEE Access, 2018.11.12,6: 68277 – 68287.
[17] Shiyan Wang ,Huimin Yu ,Roland Hu,(#) (*) 3D Video Based Segmentation and Motion Estimation with Active Surface Evolution, Journal of Signal Processing Systems for Signal Image and Video Technology, 2013.4.01, 71(1) :21~34.
[18] Shiyan Wang, Huimin Yu (#) (*). Convex relaxation for a 3D spatiotemporal segmentation model using the primal-dual method,Journal of Zhejiang University-Science C(Computers and Electronics), 2012.6.01, 13(6) :428~439.
[19] Shiyan Wang. Spatiotemporal Tracking Model Based on 3D Videos via Split Bregman Algorithm, 9th International Congress on Image and Signal Processing, CISP 2016, Datong, 2016.10.15-2016.10.17
[20] Shiyan Wang ,Huimin Yu(#)(*). A variational approach for ego-motion estimation and segmentation based on 3D TOF camera, 4th International Congress on Image and Signal Processing, CISP 2011,2011.10.15-2011.10.17
[21] Tiecheng Songa, Jie Fenga, Shiyan Wang, Yurui Xie. Spatially weighted order binary pattern for color texture classification, Expert Systems with Applications, v 147, 1 June 2020.
[22] Yu, Xiang, Xiao, Haoyue, Wang, Shiyan, Li, Yujie. An adaptive back-off scheme based on improved markov model for vehicular ad hoc networks, IEEE Access, v 6, p 67373-67384, 2018.
[23] Wu, Yichao, Zhou, Qiang, Hu, Haoji, Rong, Guanghua, Li, Yongwu, Shiyan Wang. Hepatic Lesion Segmentation by Combining Plain and Contrast-Enhanced CT Images with Modality Weighted U-Net, Proceedings - International Conference on Image Processing, ICIP, v 2019-September, p 255-259, September 2019.
[24] Fei Chen,Huimin Yu,Roland Hu, Shiyan Wang, Reduced set density estimator for object segmentation based on shape probabilistic representation,Journal of Visual Communication and Image Representation, 2012.10.01, 23(7):1085~1094.
[25] 王诗言(#),于慧敏, 基于全变分的运动分割模型及分裂Bregman算法, 自动化学报, 2014.10.01, (02) :396~404.
[26] 王诗言(#),于慧敏, 运动场景下的时空域跟踪模型及原始-对偶算法, 浙江大学学报(工学版), 2013.4.15,(04):630~637+649.
[27] 王诗言;李竟. 一种融合CNN和Transformer的道路裂纹实时检测方法, 202211342286.2. (授权专利)
[28] 王诗言;张青松;雷国芳. 一种基于掩膜信息的在线更新目标跟踪方法, ZL2022 1 0444849.2 (授权专利)
[29] 王诗言;陈熙兰;胡拓锦. 夜间语义分割方法、夜间语义分割模型训练方法和装置, ZL 2025 1 0010489.9 (授权专利)
[30] 王诗言;唐佳佳等. 一种基于AGFI和CFUM的遥感图像任意尺度超分辨率重建方法,ZL 2024 1 1639455.8 (授权专利)
[31] 王诗言;唐佳佳等. 基于动态尺度频域卷积的遥感图像任意尺度超分辨率方法,ZL 2024 1 1639674.6 (授权专利)
[32] 王诗言;郭大川等. 基于多尺度特征融合的遥感目标检测方法、系统以及介质, ZL 2024 1 1695051.0 (授权专利)
[33] 王诗言;杨灿等 一种基于残差信道先验引导的多尺度 Transformer 图像去雨方法, ZL 2024 1 1772314.3 (授权专利)
[34] 王诗言,一种融合结构张量与非局域全变分的图像去噪方法, 2018.11.06, CN105608679B(授权专利)
[35] 王诗言, 基于3D视频的时空域运动分割与运动估计方法, 2013.12.04, CN201110431984.5(授权专利)
[36] 王诗言,于慧敏, 基于3D视频的时空域运动分割与估计模型的凸优化方法, 2014.06.04,CN201110457371.9(授权专利)