基本信息
刘宏  女  硕导  中国科学院计算技术研究所
电子邮件: hliu@ict.ac.cn
通信地址: 北京科学院南路6号
邮政编码: 100190

研究领域

图像视频处理与分析,医学图像识别,视频监控,深度学习

招生信息

   
招生专业
081203-计算机应用技术
招生方向
图像视频处理和分析,医学图像识别,深度学习

教育背景

2002-09--2007-07   中国科学院计算技术研究所   博士
学历
博士
学位
计算机应用博士学位

工作经历

2000年进入中国科学院计算技术研究所工作,目前为副研究员,硕士生导师
工作简历
2000-07~现在, 中国科学院计算技术研究所, 副研究员

专利与奖励

   
专利成果
( 1 ) 基于自监督预训练和多示例学习的病理图像乳腺癌分子分型方法及系统, 发明专利, 2023, 第 1 作者, 专利号: 202310706236.6

( 2 ) 一种基于深度学习的手写盲文识别方法及系统, 发明专利, 2022, 第 1 作者, 专利号: 202210653603.6

( 3 ) 一种通用盲文到汉字的转换方法及系统, 发明专利, 2022, 第 3 作者, 专利号: 202210569910.6

( 4 ) 一种汉字到通用盲文的转换方法及系统, 发明专利, 2021, 第 4 作者, 专利号: 202111566326.7

( 5 ) 一种汉字-通用盲文对照语料库的构建方法及系统, 发明专利, 2021, 第 4 作者, 专利号: 202111566342.6

( 6 ) 一种基于影像数据和深度学习的肿瘤良恶性识别方法和系统, 发明专利, 2021, 第 1 作者, 专利号: CN113743463A

( 7 ) 一种汉语盲文语音合成方法及系统, 发明专利, 2021, 第 4 作者, 专利号: 202110749716.1

( 8 ) 一种基于深度学习的盲文图像自动识别方法和系统, 发明专利, 2019, 第 1 作者, 专利号: CN110298236A

( 9 ) 一种中国盲文错误自动检测方法、系统及存储介质, 专利授权, 2019, 第 4 作者, 专利号: CN110276069A

( 10 ) 一种汉盲对照双语语料库的构建方法和系统, 专利授权, 2019, 第 4 作者, 专利号: CN109344389A

( 11 ) 一种基于深度神经网络的汉盲自动转换方法和系统, 专利授权, 2019, 第 4 作者, 专利号: CN109241540A

( 12 ) 一种盲文点辅助标注方法及系统, 发明专利, 2018, 第 1 作者, 专利号: CN107886808A

( 13 ) 一种盲文方辅助标注方法及系统, 专利授权, 2021, 第 1 作者, 专利号: CN107886808B

( 14 ) 一种高精度盲文识别方法及系统, 专利授权, 2018, 第 1 作者, 专利号: CN108052955A

( 15 ) 一种盲文方自适应定位方法及系统, 专利授权, 2018, 第 1 作者, 专利号: CN108062548A

( 16 ) 一种盲文点检测方法及系统, 专利授权, 2018, 第 1 作者, 专利号: CN107958261A

( 17 ) 盲文点交互式标注方法及系统, 发明专利, 2018, 第 1 作者, 专利号: CN108062886A

( 18 ) 一种盲文图像自动倾斜校正方法及系统, 发明专利, 2018, 第 1 作者, 专利号: CN108052936A

( 19 ) 一种自适应的语音识别的方法和设备, 专利授权, 2017, 第 5 作者, 专利号: CN106297800A

( 20 ) 一种用于盲人读取汉字的方法及系统, 发明专利, 2016, 第 4 作者, 专利号: CN105404621A

( 21 ) 一种融合非确定性反馈的语音识别错误修正方法及系统, 专利授权, 2015, 第 4 作者, 专利号: CN105206267A

( 22 ) 一种融合用户反馈的汉语语音识别方法及系统, 发明专利, 2015, 第 4 作者, 专利号: CN104538032A

( 23 ) 障碍物检测装置及方法, 发明专利, 2015, 第 3 作者, 专利号: CN104574365A

( 24 ) 盲人避障提示装置及方法, 发明专利, 2015, 第 2 作者, 专利号: CN104287946A

( 25 ) 一种智能电视的交互方法与系统, 发明专利, 2012, 第 3 作者, 专利号: CN102547466A

( 26 ) 基于定位遥控器的智能电视人机交互方法、装置和系统, 发明专利, 2013, 第 1 作者, 专利号: CN103051964A

( 27 ) 智能电视人机交互方法、装置和系统, 发明专利, 2013, 第 1 作者, 专利号: CN103051934A

( 28 ) 基于遥控器的智能电视人机交互方法、装置和系统, 发明专利, 2013, 第 1 作者, 专利号: CN103051942A

( 29 ) 一种运动目标分类方法和系统, 发明专利, 2011, 第 2 作者, 专利号: CN102063726A

( 30 ) 团队成员即时清点系统和方法, 发明专利, 2009, 第 1 作者, 专利号: CN101566681A

( 31 ) LED路灯的智能控制装置及智能控制方法, 发明专利, 2009, 第 4 作者, 专利号: CN101541123A

( 32 ) 一种电梯优化调度智能监控系统, 实用新型, 2009, 第 1 作者, 专利号: CN201201830Y

( 33 ) 一种目标场所优化调度方法及系统, 发明专利, 2008, 第 2 作者, 专利号: CN101200252A

( 34 ) 一种电话连续语音识别系统性能的评测方法及其系统, 发明专利, 2006, 第 5 作者, 专利号: CN1811915A

( 35 ) 一种人脸检测系统的评测方法及评测系统, 发明专利, 2006, 第 1 作者, 专利号: CN1808465A

( 36 ) 基于局部特征分析的计算机笔迹鉴别方法, 发明专利, 2006, 第 1 作者, 专利号: CN1258737C

出版信息

发表期刊论文:

  1. Zichao Guo, Hong Liu, Haomiao Ni, Xiangdong Wang, Mingming Su, Wei Guo, Kuansong Wang, Taijiao Jiang, Yueliang Qian, A Fast and Refined Cancer Regions Segmentation Framework in Whole-slide Breast Pathological Images, Scientific Reports, 2019-1-29 (SCI)

  2. Hong Liu, Wenshan Wu, Xiangdong Wang, Yueliang Qian. RGB-D joint modelling with scene geometric information for indoor semantic segmentation [J]. Multimedia Tools & Applications,  Volume 77, 2018, pp 22475–22488

  3. Xiangdong Wang, Ying Yang, Hong Liu, Yueliang Qian, Improving speech transcription by exploiting user feedback and word repetition, Multimed Tools Appl (2017) 76:20359–20376

  4. Hong Liu, Tao Xu, Xiangdong Wang, Yueliang Qian, A novel multi-feature descriptor for human detection using cascaded classifiers in static image, Journal of Signal Processing Systems, Volume 81, Issue 3 (2015), Page 377-388 (SCI)

  5. 邵松,刘宏,王向东,钱跃良,基于迁移学习的行人检测研究进展,计算机工程与应用,Vol.50No.242014pp.156-163

  6. 刘宏,王喆,王向东,赵国英,钱跃良,面向盲人避障的场景自适应分割及障碍物检测,计算机辅助设计与图形学学报,Vol.25No.122013pp.1818-1825

  7. 刘宏,李锦涛,刘群,钱跃良,李豪杰,融合颜色和梯度特征的运动阴影消除方法,计算机辅助设计与图形学学报,Vol.19No.102007pp.1279-1285 (EI: 20074510909986)

  8. LIU Qun, WANG Xiangdong, LIU Hong, et al, Introduction to HTRDP evaluations on Chinese information processing and intelligent human-machine interface, Frontiers of Computer Sciences in China, Vol.1, No.1, Springer, Feb. 2007, pp.58-93. EI

  9. 李金国,钱跃良,王向东,刘群,刘宏机动车视频标注规范研究与标注平台的实现,计算机工程,Vol.33, No.4, 2007.2, pp.173-175EI

  10. 钱跃良, 林守勋, 刘群, 刘宏, 2005年度863计划中文信息处理与智能人机接口技术评测回顾, 中文信息学报, Vol. 20, 2006.3, pp.1-6EI

  11. 钱跃良, 林守勋, 刘群, 刘洋, 刘宏, 谢萦, 863计划中文信息处理与智能人机接口基础数据库的设计和实现, 高技术通讯, Vol.15, No.169, 2005.1, pp.107-110EI

  12. 刘宏,李锦涛,崔国勤,唐胜,基于SVM和纹理的笔迹鉴别方法,计算机辅助设计与图形学学报, Vol. 15, 2003.12, pp.1479-1484EI)

  13. Jun MiaoHong LiuWen GaoHongming Zhang, Gang DengXilin Chen. A System for Human Face and Facial Feature Localization, IJIG: International Journal of Image and Graphics, Vol.3, No.3, Jul. 2003, pp461-479.

  14. 刘宏,李锦涛,苗军,多方法融合来解决人脸检测中的光照补偿,系统仿真学报, Vol.132001.11, pp. 486~489

 

发表会议论文:

  1. Haomiao Ni, Hong Liu, Zichao Guo, Xiangdong Wang, Taijiao Jiang, Kuansong Wang, Yueliang Qian, Multiple Visual Fields Cascaded Convolutional Neural Network for Breast Cancer Detection, the 15th Pacific Rim International Conference on Artificial Intelligence, Nanjing, China, 2018-8-28, pp.531-544 (CCF-C)

  2. Wendong Xu, Hong Liu, Xiangdong Wang, Yueliang Qian, “Liver Segmentation in CT base on ResUNet with 3D Probabilistic and Geometric Post Process”, ICSIP 2019 (EI)

  3. Renqiang Li, Hong Liu, Xiangdong Wang, Yueliang Qian, “DSBI: Double-Sided Braille Image Dataset and Algorithm Evaluation for Braille Dots Detection”, International Conference on Video and Image Processing, HongKong, China, ICVIP 2018.12.29, pp.1-5 (EI)

  4. Hong Liu, Lizhen Tang, Jun Wang, Xiangdong Wang, Yueliang Qian, RGB-D Sensor Based Obstacle Detection and Feedback Strategy for the Visual Impaired, International Conference on Computer Vision Theory and Applications, VISAPP 2017, Feb. 27- Mar.1. 595-602

  5. Hong Liu, Jun Wang, Xiangdong Wang, Yueliang Qian, Efficient multi-scale plane extraction based RGBD video segmentation, 23th International Conference on MultiMedia Modeling, MMM2017, LNCS, Iceland, Jan. 4-6.pp. 614-625 (CCF-C)

  6. Haomiao Ni, Hong Liu, Xiangdong Wang, Yueliang Qian, Human Action Recognition Based on Optimal Joint Selection and Discriminative Depth Descriptor, The 13th Asian Conference on Computer Vision, ACCV2016, Nov. 20-24, Taibei, Taiwan. (CCF-C)

  7. Zichao Guo, Hong Liu, Yueliang Qian, Xiangdong Wang, A novel obstacle detection method based on distortion of laser pattern, The 17th IEEE International Conference on Multimedia and Expo, ICME, Seattle, USA, July 11-15, 2016 (oral) pp. 1-6. (CCF-B)

  8. Duan Jia, Xiangdong Wang, Yuzhuo Ma, Yang Yang, Hong Liu and Yueliang Qian. Language Model Adaptation based on Correction Information for Interactive Speech Transcription. The 2016 International Conference on Progress in Informatics and Computing (PIC-2016), Shanghai, China.

  9. Xiangdong Wang, Yang Yang, Jinchao Zhang, Wenbin Jiang, Hong Liu and Yueliang Qian, Chinese to Braille Translation based on One-time Word Segmentation using Statistical Model, The 2015 International Conference on Progress in Informatics and Computing (PIC-2015).

  10. Hong Liu, Jun Wang, Yueliang Qian, Xiangdong Wang, iSee: Obstacle Detection and Feedback System for the Blind (poster), 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2015, Osaka, Japan, Sept. 6-12, 2015197-200

  11. Xiangdong Wang, Xinhui Li, Hong Liu and Yueliang Qian, Automatic Error Correction for Repeated Words in Mandarin, International Conference on Intelligent and Automation Systems (ICIAS 2015), Ho Chi Minh City, Vietnam, February 6-7, 2015

  12. Song Shao, Hong Liu, Xiangdong Wang, Yueliang Qian, Local Associated Features for Pedestrian Detection, workshop Robust local descriptors for computer vision in Conjunction with ACCV 2014

  13. Zhe Wang, Hong Liu, Xiangdong Wang, Yueliang Qian, Segment and Label Indoor Scene based on RGB-D for the Visually Impaired, 20th International Conference on MultiMedia Modeling, MMM2014

  14. Hong Liu, Tao Xu, Xiangdong Wang, and Yueliang Qian, Related HOG Features for Human Detection Using Cascaded Adaboost and SVM Classifiers, 19th International Conference on MultiMedia Modeling, MMM2013, Jan 7-9, China, huangshan, LNCS7733, pp. 345–355

  15. Tao Xu, Hong Liu, Yueliang Qian, Zhe Wang, A fast pedestrian detection framework based on static and dynamic information, IEEE International Conference on Multimedia and Expo, ICME 2012, July 9-13, Melbourne, Australia, pp. 242-247 (EI)

  16. Zhe Wang, Hong Liu, Yueliang Qian, Tao Xu, Crowd Density Estimation Based On Local Binary Pattern Co-Occurrence Matrix, IEEE International Workshop on Advances in Automated Multimedia Surveillance for Public Safety, in Conjunction with ICME 2012, July 9-13,  Melbourne, Australia, pp. 372-377 (EI)

  17. Zhe Wang, Hong Liu, Yueliang Qian, Tao Xu, Real-Time Plane Segmentation and Obstacle Detection of 3D Point Clouds for Indoor Scenes, IEEE International Workshop on Consumer Depth Cameras for Computer Vision, in Conjunction with ECCV 2012, Oct. 7-13, Firenze, Italy, LNCS7584, pp.22-31. (EI)

  18. Xutao, Hong Liu, Yueliang Qian, A Novel Method for People and Vehicle Classification Based on Hough Line Feature, Proceedings of 1th IEEE International Conference on Information Science and Technology, ICIST 2011, March 26-28, Nanjing, China, pp. 240-245, (EI)

  19. Hong Liu, Yueliang Qian, Shuoxun Lin, Detecting Persons Using Hough Circle Transform in Surveillance Video, International Conference on Computer Vision Theory and Applications, VISAPP 2010, May (17-22), Angers, France, pp.267-270 (EI)

  20. Hong Liu, Yueliang Qian, Qun Liu, Jintao Li, Count passengers based on haar-like feature in elevator application, Proceedings of Seventh International Conference on Machine Learning and Cybernetics, ICMLC 2008, July (12-15), Kunming, China, pp. 1202-1206. (EI)

  21. Hong Liu, Jintao Li, Yueliang Qian, Qun Liu, Robust Multi-target Tracking Using Mean Shift and Particle Filter with Target Model Update, International Conference on Computer Vision Theory and Applications, VISAPP 2008, January (22-25) in Funchal, Madeira, Portugal, PP.605-610 (EI)

  22. 刘宏,黄赟,刘群,SSMT2007机器翻译评测报告,第三届统计机器翻译研讨会论文集,哈尔滨,中国,2007812-13.

  23. Hong Liu, Jintao Li, Yueliang Qian, Qun Liu, Shadow Elimination in Traffic Video Segmentation, The 10th IAPR Conference on Machine Vision Applications, MVA 2007, Japan, Tokyo, 2007, May, pp. 445-448. (EI)

  24. Hong Liu, Jintao Li, Yueliang Qian, Shouxun Lin, Qun Liu, Motion and Gray Based Automatic Road Segment Method MGARS in Urban Traffic Surveillance, Lecture Notes in Computer Science, Volume 4135, Springer-Verlag Berlin Heidelberg, Aug. 2006, pp. 85-94(SCI), IWICPAS 2006

  25. Qian YueLiang, LIN ShouXun, Zhang YongDong, LIU Yang, LIU Hong and LIU Qun. An Introduction to Corpora Resources of 863 Program for Chinese Language Processing and Intelligent Human-Machine Interaction. In Proceedings of The 4th Workshop on Asian Language Resources (ALR-04)March 25, 2004, Sanya City, Hainan Island, China.

  26. Hong Liu, Jintao Li, Guoqin Cui, Text-Dependent Chinese Writer Identification Using Optimal Gabor Filter, ACCV 2004: The 6th Asian Conference on Computer Vision, Jeju Island, Korea. 23--25 January 2004, pp.188-192.

  27. Hong Liu, Wen Gao, Jun Miao, Jintao Li. A Novel Method to Compensate Variety of Illumination in Face Detection. Proc. 6th Joint Conference on Information Sciences (CVPRIP), North Carolina, America, 2002, pp. 692~695 (ISTP)

  28. Hong Liu, Wen Gao, Jun Miao, Debin Zhao, Gang Deng, Jintao Li. Illumination Compensation and Feedback of Illumination Feature in Face Detection. ICII 2001: Proc. International Conferences on Information-technology and Information-net, Beijing, China, Vol. III, 2001, pp. 444~449

  29. Jun Miao, Hongming Zhang, Wen Gao,Gang Deng, Hong Liu and Xilin Chen. FaceTracker: A Human Face Tracking and Facial Organ Localizing System, ICCV 2001: the Proc. of the 8th International Conference on Computer Vision, Vancouver, Cananda, 2001, pp.743~743

 

授权和申请专利:

1.     刘宏,李锦涛,崔国勤。基于局部特征分析的计算机笔迹鉴别方法,专利号:ZL200310104462.X

2.     刘宏,林守勋,钱跃良,李锦涛。一种人脸检测系统的评测方法及评测系统,专利号:ZL200510001787.4

3.     王向东,栾焕搏,林守勋,钱跃良,刘宏,张勇东。一种电话连续语音识别系统性能评测方法,专利号:ZL200510011285.X

4.     钱跃良,刘宏,高扬,赵丹,刘群。一种目标场所优化调度方法及系统。专利号:ZL200710179079.9

5.     钱跃良,张博宁,王向东,刘宏,陈益强。LED路灯的智能控制装置及智能控制方法。申请号:ZL200910083487.3

6.     许涛,刘宏,钱跃良。一种基于直线特征的运动目标分类方法及系统。专利号:ZL201010620374.5

7.     刘宏,钱跃良,李锦涛。团队成员即时清点系统和方法。专利号:ZL200910084294.X

8.     钱跃良,王向东,刘宏。一种智能电视的交互方法和系统。专利号:ZL201210048441.X

9.     刘宏,钱跃良,王向东。基于遥控器的智能电视人机交互方法、装置和系统。专利号:ZL2011103122350

10.   钱跃良,刘宏,王喆,王向东。盲人避障提示装置及方法。专利号:ZL2014105756941

11.   刘宏,钱跃良,王向东。基于定位遥控器的智能电视人机交互方法、装置和系统。专利号:ZL201110312134.3

12.   刘宏,钱跃良,刘群,李锦涛。一种电梯优化调度智能监控系统。专利号:ZL200820078670.5

13.   钱跃良,王向东,刘宏。障碍物检测装置和方法。专利申请号:201410795401.0

14.   王向东,杨阳,钱跃良,刘宏。一种融合用户反馈的汉语语音识别方法及系统。申请号:201410806233.0

15.   王向东,杨阳,钱跃良,刘宏,张金超,姜文斌。一种用于盲人读取汉字的方法及系统, 专利申请号:201510623525.5

16.   王向东,蔡佳,钱跃良,刘宏。一种融合非确定性反馈的语音识别错误修正方法及系统, 专利申请号:201510569945.X

17.   王向东 贾端 马玉卓 钱跃良 刘宏,一种自适应的语音识别的方法和设备,专利申请号:201610651850.7

18.   刘宏,钱跃良,王向东,盲文点交互式标注方法及系统,申请号:201711070494.0

19.   刘宏,钱跃良,王向东,一种盲文点检测方法及系统,申请号:201711071085.2

20.   刘宏,黎仁强,王向东,钱跃良,一种盲文图像自动倾斜校正方法及系统,申请号:201711071084.8

21.   刘宏,黎仁强,王向东,钱跃良,一种盲文方自适应定位方法及系统,申请号:201711071082.9

22.   刘宏,黎仁强,王向东,钱跃良,一种盲文点辅助标注方法及系统,申请号:201711071554.0

23.   刘宏,黎仁强,王向东,钱跃良,一种高精度盲文识别方法及系统,申请号:201711070466.9

24.   王向东 蔡佳 钱跃良 刘宏,一种汉盲对照双语语料库的构建方法和系统,申请号:201810929248.4

25.   王向东 蔡佳 钱跃良 刘宏,一种基于深度神经网络的汉盲自动转换方法和系统,申请号:201810889881.5

发表论文
[1] Jianguo Mao, Wenbin Jiang, Hong Liu, Xiangdong Wang, Yajuan Lyu. Inferential Knowledge-Enhanced Integrated Reasoning for Video Question Answering. AAAI 2023. 2023, 第 3 作者
[2] Hong Liu, Menglei Jiao, Yuan Yuan, Hanqiang Ouyang, Jianfang Liu, Yuan Li, Chunjie Wang, Ning Lang, Liang Jiang, Yueliang Qian, Huishu Yuan, Xiangdong Wang. Benign and Malignant Prediction of Spinal Tumors based on Deep Learning and Weighted Fusion Framework on MRI. Insights into imaging[J]. 2022, 第 1 作者  通讯作者  13(7): 
[3] Jianguo Mao, Wenbin Jiang, Xiangdong Wang, Hong Liu, Yu Xia, Yajuan Lyu, Qiaoqiao She. Explainable Question Answering based on Semantic Graph by Global Differentiable Learning and Dynamic Adaptive Reasoning. EMNLP 2022. 2022, 第 4 作者
[4] Meng-Lei Jiao, Hong Liu, Jian-Fang Liu, Han-Qiang Ou-Yang, Xiang-Dong Wang, Liang Jiang, Hui-Shu Yuan, Yue-Liang Qian. MAL: Multi-modal attention learning for tumor diagnosis via bipartite graph and multiple branches. International Conference on Medical Image Computing and Computer Assisted Intervention. 2022, 第 2 作者
[5] Hong Liu, Wendong Xu, Zihao Shang, Xiangdong Wang, Kuansong Wang, Yueliang Qian. Breast Cancer Molecular Subtypes Prediction on H&E Pathological Images Based on Discriminative Patch Selecting and Multi-Instance Learning. Frontiers in Oncology[J]. 2022, 第 1 作者  通讯作者  
[6] Jianguo Mao, Jiyuan Zhang, Zengfeng Zeng, Weihua Peng, Wenbin Jiang, Xiangdong Wang, Hong Liu, Yajuan Lyu. Hierarchical Representation-based Dynamic Reasoning Network for Biomedical Question Answering. COLING 2022. 2022, 第 7 作者
[7] Li, Yiming, Guo, Zhifang, Ye, Zhirong, Wang, Xiangdong, Liu, Hong, Qian, Yueliang, Tao, Rui, Yan, Long, Ouchi, Kazushige. A Hybrid System of Sound Event Detection Transformer and Frame-wise Model for DCASE 2022 Task 4. DCASE workshop 2022. 2022, 第 5 作者http://arxiv.org/abs/2210.09529.
[8] Jianguo Mao, Wenbin Jiang, Xiangdong Wang, Zhifan Feng, Yajuan Lyu, Hong Liu, Yong Zhu. Dynamic Multistep Reasoning based on Video Scene Graph for Video Question Answering. NAACL 2022. 2022, 第 6 作者
[9] Jianguo Mao, Jingwen Zhu, Xiangdong Wang, Hong Liu, Yueliang Qian. Speech Synthesis of Chinese Braille with Limited Training Data. 2021IEEEINTERNATIONALCONFERENCEONMULTIMEDIAANDEXPOICME2021. 2021, 第 4 作者
[10] 刘宏. A Deep Learning Method Based on Multi-model Weighted Fusion to Distinguish Benign and Malignant Spinal Tumors with Magnetic Resonance Imaging. Radiological Society of North America. 2021, 第 1 作者
[11] 刘宏. CoUNet: An edge enhanced UNet for Colonoscopy lesion segmentation and classification of WSI. International Conference on Video and Image Processing 2020[J]. 2020, 第 1 作者
[12] Lin, Liwei, Wang, Xiangdong, Liu, Hong, Qian, Yueliang. GUIDED LEARNING FOR WEAKLY-LABELED SEMI-SUPERVISED SOUND EVENT DETECTION. 2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING. 2020, 第 3 作者626-630, 
[13] 刘宏. Guided Learning convolution system for DCASE 2019 task4. International Conference on Acoustics, Speech and Signal Processing. 2020, 第 1 作者
[14] Huang, Yuxin, Lin, Liwei, Ma, Shuo, Wang, Xiangdong, Liu, Hong, Qian, Yueliang, Liu, Min, Ouch, Kazushige. Guided multi-branch learning systems for sound event detection with sound separation. Workshop on Detection and Classification of Acoustic Scenes and Events 2020. 2020, 第 5 作者http://arxiv.org/abs/2007.10638.
[15] Lin, Liwei, Wang, Xiangdong, Liu, Hong, Qian, Yueliang. Specialized Decision Surface and Disentangled Feature for Weakly-Supervised Polyphonic Sound Event Detection. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING[J]. 2020, 第 3 作者28: 1466-1478, http://dx.doi.org/10.1109/TASLP.2020.2989575.
[16] Zichao Guo, Hong Liu, Haomiao Ni, Xiangdong Wang, Mingming Su, Wei Guo, Kuansong Wang, Taijiao Jiang, Yueliang Qian. Publisher Correction: A Fast and Refined Cancer Regions Segmentation Framework in Whole-slide Breast Pathological Images. SCIENTIFIC REPORTS[J]. 2020, 第 2 作者10(1): 1, http://dx.doi.org/10.1038/s41598-020-65026-9.
[17] Huang, Yuxin, Wang, Xiangdong, Lin, Liwei, Liu, Hong, Qian, Yueliang. MULTI-BRANCH LEARNING FOR WEAKLY-LABELED SOUND EVENT DETECTION. 2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING. 2020, 第 4 作者641-645, 
[18] 刘宏. Optical Braille Recognition Based On Semantic Segmentation Network With Auxiliary Learning Strategy. CVPR workshop Text and Documents in the Deep Learning Era. 2020, 第 1 作者
[19] 蔡佳, 王向东, 唐李真, 崔晓娟, 刘宏, 钱跃良. 基于汉盲对照语料库和深度学习的汉盲自动转换. 中文信息学报[J]. 2019, 第 5 作者33(4): 60-67, http://lib.cqvip.com/Qikan/Article/Detail?id=7002147298.
[20] Ni, Haomiao, Liu, Hong, Wang, Kuansong, Wang, Xiangdong, Zhou, Xunjian, Qian, Yueliang, Suk, HI, Liu, M, Yan, P, Lian, C. WSI-Net: Branch-Based and Hierarchy-Aware Network for Segmentation and Classification of Breast Histopathological Whole-Slide Images. MACHINE LEARNING IN MEDICAL IMAGING (MLMI 2019). 2019, 第 11 作者11861: 36-44, 
[21] Guo, Zichao, Liu, Hong, Ni, Haomiao, Wang, Xiangdong, Su, Mingming, Guo, Wei, Wang, Kuansong, Jiang, Taijiao, Qian, Yueliang. A Fast and Refined Cancer Regions Segmentation Framework in Whole-slide Breast Pathological Images. SCIENTIFIC REPORTS[J]. 2019, 第 2 作者  通讯作者  9(1): http://dx.doi.org/10.1038/s41598-018-37492-9.
[22] Liwei Lin, Xiangdong Wang, Hong Liu, Yueliang Qian. Guided Learning Convolution System for DCASE 2019 Task 4. Workshop on Detection and Classification of Acoustic Scenes and Events. 2019, 第 3 作者http://arxiv.org/abs/1909.06178.
[23] Liu, Hong, Wu, Wenshan, Wang, Xiangdong, Qian, Yueliang. RGB-D joint modelling with scene geometric information for indoor semantic segmentation. MULTIMEDIA TOOLS AND APPLICATIONS[J]. 2018, 第 1 作者  通讯作者  77(17): 22475-22488, https://www.webofscience.com/wos/woscc/full-record/WOS:000441364500039.
[24] Ni Haomiao, Liu Hong, Guo Zichao, Wang Xiangdong, Jiang Taijiao, Wang Kuansong, Qian Yueliang, Geng X, Kang BH. Multiple Visual Fields Cascaded Convolutional Neural Network for Breast Cancer Detection. PRICAI 2018: TRENDS IN ARTIFICIAL INTELLIGENCE, PT I. 2018, 第 11 作者11012: 531-544, 
[25] Hong Liu. Efficient multi-scale plane extraction based RGBD video segmentation. 23th International Conference on MultiMedia Modeling(MMM2017). 2017, 第 1 作者  通讯作者  
[26] Wang, Xiangdong, Yang, Ying, Liu, Hong, Qian, Yueliang. Improving speech transcription by exploiting user feedback and word repetition. MULTIMEDIA TOOLS AND APPLICATIONS[J]. 2017, 第 3 作者76(19): 20359-20376, https://www.webofscience.com/wos/woscc/full-record/WOS:000409180500058.
[27] Hong Liu. RGB-D Sensor based Obstacle Detection and Feedback Strategy for the Visual Impaired. International Conference on Computer Vision Theory and Applications[J]. 2017, 第 1 作者  通讯作者  
[28] Jia, Duan, Wang, Xiangdong, Ma, Yuzhuo, Yang, Yang, Liu, Hong, Qian, Yueliang, Wang, Y, Sun, Y. Language Model Adaptation Based on Correction Information for Interactive Speech Transcription. PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON PROGRESS IN INFORMATICS AND COMPUTING (PIC), VOL 1. 2016, 第 5 作者258-263, 
[29] Guo, Zichao, Liu, Hong, Qian, Yueliang, Wang, Xiangdong. A NOVEL OBSTACLE DETECTION METHOD BASED ON DISTORTION OF LASER PATTERN. 2016 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO (ICME)[J]. 2016, 第 2 作者  通讯作者  
[30] Hong Liu. Human Action Recognition Based on Optimal Joint Selection and Discriminative Depth Descriptor. ASIANCONFERENCEONCOMPUTERVISION. 2016, 第 1 作者  通讯作者  
[31] Liu, Hong, Xu, Tao, Wang, Xiangdong, Qian, Yueliang. A Novel Multi-Feature Descriptor for Human Detection Using Cascaded Classifiers in Static Images. JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY[J]. 2015, 第 1 作者  通讯作者  81(3): 377-388, https://www.webofscience.com/wos/woscc/full-record/WOS:000362575300005.
[32] Shao Song, Liu Hong, Wang Xiangdong, Qian Yueliang, Jawahar CV, Shan S. Local Associated Features for Pedestrian Detection. COMPUTER VISION - ACCV 2014 WORKSHOPS, PT I. 2015, 第 11 作者9008: 513-526, 
[33] Hong Liu. A novel multi-feature descriptor for human detection using cascaded classifiers in static image. THEJOURNALOFSIGNALPROCESSINGSYSTEMS[J]. 2015, 第 1 作者  通讯作者  
[34] 刘宏. iSee: Obstacle Detection and Feedback System for the Blind. UbiComp 2015. 2015, 第 1 作者
[35] Li, Liang, Liu, Hong, Wang, Hao, Liu, Taoying, Li, Wei. A Parallel Algorithm for Game Tree Search Using GPGPU. IEEETRANSACTIONSONPARALLELANDDISTRIBUTEDSYSTEMS[J]. 2015, 第 2 作者26(8): 2114-2127, https://www.webofscience.com/wos/woscc/full-record/WOS:000358226400004.
[36] Zhe Wang, Hong Liu, Xiangdong Wang, Yueliang Qian. Segment and Label Indoor Scene Based on RGB-D for the Visually Impaired. Multimedia modeling : Part I /. 2014, 第 2 作者449-460, 
[37] 邵松, 刘宏, 王向东, 钱跃良. 基于迁移学习的行人检测研究进展. 计算机工程与应用[J]. 2014, 第 2 作者156-163, http://lib.cqvip.com/Qikan/Article/Detail?id=663467715.
[38] 高韬, 姚振静, 王向东, 刘宏. 采用物联网技术的震后多生命体目标定位研究. 应用基础与工程科学学报[J]. 2013, 第 4 作者21(5): 991-1003, http://lib.cqvip.com/Qikan/Article/Detail?id=47631321.
[39] 刘宏, 王喆, 王向东, 赵国英, 钱跃良. 面向盲人避障的场景自适应分割及障碍物检测. 计算机辅助设计与图形学学报[J]. 2013, 第 1 作者25(12): 1818-1825, https://www.jcad.cn/cn/article/id/09e515c6-8feb-4e8d-ae5b-3cecd1b7cd4a.
[40] Hong Liu. Related HOG Features for Human Detection Using Cascaded Adaboost and SVM Classifiers. 19th International Conference on MultiMedia Modeling, MMM2013. 2013, 第 1 作者  通讯作者  
[41] Wang Zhe, Liu Hong, Qian Yueliang, Xu Tao, IEEE. Crowd Density Estimation Based On Local Binary Pattern Co-Occurrence Matrix. 2012 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO WORKSHOPS (ICMEW). 2012, 第 2 作者372-377, 
[42] Hong Liu. A fast pedestrian detection framework based on static and dynamic information. IEEE International Conference on Multimedia and Expo, ICME2012. 2012, 第 1 作者  通讯作者  
[43] Wang Zhe, Liu Hong, Qian Yueliang, Xu Tao, Fusiello A, Murino V, Cucchiara R. Real-Time Plane Segmentation and Obstacle Detection of 3D Point Clouds for Indoor Scenes. COMPUTER VISION - ECCV 2012, PT II. 2012, 第 2 作者7584: 22-31, 
[44] Hong Liu. A Novel Method for People and Vehicle Classification Based on Hough Line Feature. Proceedings of 1th IEEE International Conference on Information Science and Technology, ICIST 2011. 2011, 第 1 作者  通讯作者  
[45] Liu Hong, Qian Yueliang, Lin Shouxun, Richard P, Braz J. DETECTING PERSONS USING HOUGH CIRCLE TRANSFORM IN SURVEILLANCE VIDEO. VISAPP 2010: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOL 2. 2010, 第 1 作者267-270, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000393008600041.
[46] Liu Hong, Li Jintao, Qian Yueliang, Liu Qun, Ranchordas AN, Araujo HJ. Robust multi-target tracking using mean shift and particle filter with target model update. VISAPP 2008: PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOL 2. 2008, 第 1 作者605-610, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000256791600094.
[47] Liu, Hong, Qian, YueLiang, Liu, Qun, Li, JinTao, IEEE. Count passengers based on Haar-like feature in elevator application. PROCEEDINGS OF 2008 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7. 2008, 第 1 作者1202-1206, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000259604900218.
[48] 刘宏, 李锦涛, 刘群. 融合颜色和梯度特征的运动阴影消除方法. 计算机辅助设计与图形学学报[J]. 2007, 第 1 作者19(10): 1279-1285, http://lib.cqvip.com/Qikan/Article/Detail?id=25632560.
[49] 刘宏. Shadow Elimination in Traffic Video Segmentation. The 10th IAPR Conference on Machine Vision Applications, MVA 2007. 2007, 第 1 作者
[50] 李金国, 钱跃良, 王向东, 刘群, 刘宏. 机动车视频标注规范研究与标注平台的实现. 计算机工程[J]. 2007, 第 5 作者33(4): 173-175, http://lib.cqvip.com/Qikan/Article/Detail?id=24849235.
[51] Wang Xiaoning, Li Wei, Liu Hong, Xu Zhiwei, OConner L. A language-based approach to service deployment. 2006 IEEE INTERNATIONAL CONFERENCE ON SERVICES COMPUTING, PROCEEDINGS. 2006, 第 3 作者69-+, 
[52] 钱跃良, 林守勋, 刘群, 刘宏. 2005年度863计划中文信息处理与智能人机接口技术评测回顾. 中文信息学报[J]. 2006, 第 4 作者20(B03): 1-6, http://lib.cqvip.com/Qikan/Article/Detail?id=21481950.
[53] Liu, Hong, Li, Jintao, Qian, Yueliang, Lin, Shouxun, Liu, Qun, Zheng, N, Jiang, X, lan, X. Motion and gray based automatic road segment method MGARS in urban traffic surveillance. ADVANCES IN MACHINE VISION, IMAGE PROCESSING, AND PATTERN ANALYSIS[J]. 2006, 第 1 作者  通讯作者  4153: 85-94, https://www.webofscience.com/wos/woscc/full-record/WOS:000240262900009.
[54] 钱跃良, 林守勋, 刘群, 刘洋, 刘宏, 谢萦. 863计划中文信息处理与智能人机接口基础数据库的设计和实现. 高技术通讯[J]. 2005, 第 5 作者15(1): 107-110, http://lib.cqvip.com/Qikan/Article/Detail?id=11709629.
[55] 刘宏, 李锦涛, 崔国勤, 唐胜. 基于SVM和纹理的笔迹鉴别方法. 计算机辅助设计与图形学学报[J]. 2003, 第 1 作者15(12): 1479-1484, http://lib.cqvip.com/Qikan/Article/Detail?id=8814257.

科研活动

   
科研项目
( 1 ) 汉-盲互译关键技术研发与盲用文化资源格式相关标准规范制定, 负责人, 国家任务, 2015-01--2017-12
( 2 ) 病理图像辅助标注技术及系统, 负责人, 境内委托项目, 2018-05--2018-12
( 3 ) 基于智能芯片的病理图像分析程序设计指南, 负责人, 中国科学院计划, 2019-04--2021-06
( 4 ) 面向小样本医疗数据的深度学习方法研究及在脊柱肿瘤诊断中的应用, 参与, 地方任务, 2019-01--2022-12
( 5 ) 基于智能芯片的复杂场景盲文识别, 负责人, 其他国际合作项目, 2020-01--2021-12
( 6 ) 多模态医疗影像颈椎退变解析及其临床诊断与应用的研究, 参与, 地方任务, 2019-01--2023-12
( 7 ) 基于多模态信息的年龄相关性黄斑变性AMD高精度辅助诊断研究, 负责人, 境内委托项目, 2022-05--2024-05
( 8 ) 面向视频问答的知识推理计算技术, 负责人, 境内委托项目, 2021-05--2022-07
( 9 ) 基于自监督预训练和多示例学习的乳腺癌病理图像分子分型预测, 负责人, 国家任务, 2023-01--2026-12
( 10 ) 基于多模态信息融合的肿瘤风险和诊疗智能评估关键技术研发及示范, 参与, 国家任务, 2023-10--2026-10

指导学生

已指导学生

许涛  硕士研究生  081203-计算机应用技术  

王喆  硕士研究生  081203-计算机应用技术  

邵松  硕士研究生  081203-计算机应用技术  

吴文珊  硕士研究生  081203-计算机应用技术  

王君  硕士研究生  081203-计算机应用技术  

郭梓超  硕士研究生  081203-计算机应用技术  

倪浩淼  硕士研究生  081203-计算机应用技术  

黎仁强  硕士研究生  081203-计算机应用技术  

徐文栋  硕士研究生  085211-计算机技术  

焦梦磊  硕士研究生  081203-计算机应用技术  

尚子皓  硕士研究生  081203-计算机应用技术  

现指导学生

雷欣  硕士研究生  081203-计算机应用技术  

杨泽康  硕士研究生  081200-计算机科学与技术  

余澍莘  硕士研究生  081200-计算机科学与技术