金连文

华南理工大学电子与信息学院, 二级教授,博士生导师

深度学习与视觉计算实验室 主任

Email: eelwjin@scut.edu.cn (primary), Lianwen.jin@gmail.com (secondary)

地址:广东省广州市五山路381号华南理工大学逸夫科学馆

Google Scholar: https://scholar.google.com/citations?user=WMUStEUAAAAJ&hl=en&oi=ao

DBLP: https://dblp.org/pid/54/3221.html

[English Version]

 

个人简介

1991年本科毕业于中国科技大学无线电系,获无线电新技术专业及计算机软件及应用技术专业双学位,1996年于华南理工大学通信与电子系统专业获博士学位。2006入选教育部新世纪优秀人才,2011年入选省级人才项目。目前为华南理工大学二级教授,博士生导师,曾兼任IEEE Signal Processing Guangdong Chapter主席(2014-2016),目前兼任广东省图像图形学会理事长、中国图象图形学学会常务理事、中国图象图形学学会文档图像分析与识别专委会主任、中国图象图形学学会机器视觉专委会常务委员、中国人工智能学会模式识别专委会常务委员、中国自动化学会模式识别与机器智能专委会常务委员、中国计算机学会计算机视觉专委会委员、中国计算机学会人机交互专委会委员、广东省高校“音视频图文智能信息处理”工程研究中心主任等职。主要研究领域为光学文字识别(OCR)、多模态大模型、机器学习、深度学习、计算机视觉等。在重要国际期刊、以及权威国际会议论文300余篇,Google Scholar 引用数160000次,H-index65连续多年入选“斯坦福大学全球前2%顶尖科学家”榜单。获得发明专利授权70余项。先后主持了国家科技支撑计划课题、国家重点研发计划课题、国家自然科学基金重点及面上项目、广东省自然科学基金重点及面上项目、广东省重大科技计划、企业合作项目等在内的科研项目50余项。作为主要成员荣获广东省科技进步一等奖(排名第1)、教育部自然科学二等奖(排名第4)及广东省自然科学奖一等奖(排名第5)、广东省科技进步二等奖(排名第3)、广东省科技进步二等奖(排名第5)、2020年吴文俊人工智能科技进步奖(排名第2)、2021年中国图象图形学会科技进步二等奖(排名第2)、2021年中国电子学会科技进步二等奖(排名第3)各1次,荣获国际国内学术竞赛第一名(冠军)二十余次。指导学生入选“华为天才少年”1人次;指导学生荣获中国图象图形学学会“优秀博士论文”奖励1项;指导学生荣获中国 “互联网+”大学生创新创业大赛全国金奖1项。

 

研究方向

²  光学文字识别(OCR),文档智能(Document Intelligence /Document AI

²  手写文字识别、文档图像分析与处理、自然场景文本

²  人工智能、多模态大模型

²  深度学习及其应用

²  计算机视觉及图像处理

²  自然语言处理及其应用

 

--- 发表论文 ---

2024

Journal Papers

1.        Ziyan Li, Yuhao Huang, Dezhi Peng, Mengchao He, Lianwen Jin*,  SideNet: Learning Representations from Interactive Side Information for Zero-shot Chinese Character Recognition, Pattern Recognition, 2024. SCI 2022 IF: 8.518, JCR Q1区,中科院一区/Top期刊

2.        Zhe Li, Wentao Yang, Hengnian Qi, Lianwen Jin*, Yichao Huang, Kai Ding, A Tree-Based Model with Branch Parallel Decoding for Handwritten Mathematical Expression Recognition, Pattern Recognition, 2024. SCI 2022 IF: 8.518, JCR Q1区,中科院一区/Top期刊

3.        Jiaxin Zhang, DaiZhen Jia, Chongyu Liu, Dezhi Peng, Bangdong Chen, Xue Gao, and Lianwen Jin*, Towards Accurate Readings of Water Meters by Eliminating Transition Error: New Dataset and Effective Solution, IEEE Transactions on Instrumentation and Measurement (TIM) SCI 2023 IF: 5.199, JCR Q1区,中科院二区/Top期刊

4.        Jiale Cheng, Dongzi Shi, Chenyang Li, Yu Li, Hao Ni, Lianwen Jin, Xin Zhang*, Skeleton-based Gesture Recognition with Learnable Paths and Signature Features, IEEE Transactions on Multimedia (TMM), 2024SCI 2022 IF: 8.182, JCR Q1区,中科院一区/Top期刊

5.        Yuyi Zhang, Yuanzhi Zhu, Dezhi Peng, Peirong Zhang, Zhenhua Yang, Zhibo Yang, Cong Yao, Lianwen Jin, HierCode: A Lightweight Hierarchical Codebook for Zero-Shot Chinese Text Recognition, Pattern Recognition, 2024. SCI 2023 IF: 7.5, JCR Q1区,CAAI A类期刊,中科院一区/Top期刊

6.        Ziyan Lia, Lianwen Jin, Chengquan Zhang, Jiaxin Zhang, Zecheng Xie, Pengyuan Lyu, Kun Yao, Irregular Text Block Recognition via Decoupling Visual, Linguistic, and Positional Information, Pattern Recognition, 2024. SCI 2022 IF: 8.518, JCR Q1区,中科院一区/Top期刊

7.        Chongyu Liu, Dezhi Peng, Yuliang Liu, Lianwen Jin*, CTRNet++: Dual-path Learning with Local-global Context Modeling for Scene Text Removal, ACM Transactions on Multimedia Computing Communications and Applications (TOMM) 2024. SCI 2022 IF: 5.2, JCR Q1

8.        Zhishu Sun; Luojun Lin*; Yuanlong Yu; Lianwen Jin, Learning feature alignment across attribute domains for improving facial beauty prediction, Expert Systems with Applications, 2024SCI 2022 IF: 8.50, JCR Q1区,中科院一区

9.        Yuliang Liu, Pengjie Wang, Kaile Zhang, Jinpeng Wan, Haisu Guan, Zhebin Kuang, Xinyu Wang, Lianwen Jin, and Xiang Bai*, An open dataset for Oracle bone character recognition and decipherment, Scientific Data. SCI 2023 IF: 5.80, JCR Q1, Nature子刊

Conference Papers

1.        Jiaxin Zhang, Dezhi Peng, Chongyu Liu, Peirong Zhang, Lianwen Jin*, DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks, CVPR 2024 (CCF A类会议,计算机视觉&人工智能顶会).

2.        Mingxin Huang, Hongliang Li, Yuliang Liu, Xiang Bai, Lianwen Jin*, Bridging the Gap Between End-to-End and Two-Step Text Spotting, CVPR 2024 (CCF A类会议,计算机视觉&人工智能顶会).

3.        Chenfan Qu, Yiwu Zhong, Chongyu Liu, Guitao Xu, Dezhi Peng, Fengjun Guo, Lianwen Jin*, Towards Modern Image Manipulation Localization: A Large-Scale Dataset and Novel Methods, CVPR 2024 (CCF A类会议,计算机视觉&人工智能顶会).

4.        Wenhui Liao, Jiapeng Wang, Zening Lin, Longfei Xiong, Lianwen Jin*, PPTSER: A Plug-and-Play Tag-guided Method for Few-shot Semantic Entity Recognition on Visually-rich Documents, ACL 2024 (CCF A类会议,NLP&人工智能顶会)

5.        Haisu Guan, Huanxin Yang, Xinyu Wang, Yongge Liu, Lianwen Jin, Xiang Bai, Yuliang Liu, Deciphering Oracle Bone Language with Diffusion Models, ACL 2024 (CCF A类会议,NLP&人工智能顶会,ACL 2024 Best Paper Award)

6.        Jiapeng Wang, Chengyu Wang, Tingfeng Cao, Jun Huang, Lianwen Jin*, DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation, ACL 2024 (CCF A类会议,NLP&人工智能顶会)

7.        Jiahuan Cao, Dezhi Peng, Peirong Zhang, Yongxin Shi, Yang Liu, Kai Ding, Lianwen Jin*Jiahuang Cao, Yang Liu, Lianwen Jin*, TongGu: Mastering Classical Chinese Understanding with Knowledge-Grounded Large Language Models, EMNLP 2024. (CAAI A类会议,CCF B类会议,NLP&人工智能顶会)

8.        Jiapeng Wang, Chengyu Wang, Kunzhe Huang, Jun Huang, Lianwen Jin*, VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models, EMNLP 2024 (CAAI A类会议,CCF B类会议,NLP&人工智能顶会)

9.        Dezhi Peng, Zhenhua Yang, Jiaxin Zhang, Chongyu Liu, Yongxin Shi, Kai Ding, Fengjun Guo, Lianwen Jin*UPOCR: Towards Unified Pixel-Level OCR Interface, ICML 2024. (CCF A类会议)

10.      Jiahuan Cao, Yang Liu, Yongxin Shi, Kai Ding, Lianwen Jin*, WenMind: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Classical Literature and Language Arts, NeurIPS 2024. (CCF A类会议)

11.      Dezhi Peng, Chongyu Liu, Yuliang Liu, Lianwen Jin*, ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining, AAAI 2024 (CCF A类会议)

12.      Ning Zhang, Hiuyi Cheng, Jiayu Chen, Zongyuan Jiang,  Jun Huang , Yang Xue, Lianwen Jin*, M2Doc: A Multi-Modal Fusion Approach for Document Layout Analysis, AAAI 2024 (CCF A类会议)

13.      Zhenhua Yang, Dezhi Peng, Yuxin Kong, Yuyi Zhang, Cong Yao, Lianwen Jin*, FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning, AAAI 2024 (CCF A类会议)

14.      Ruilu Wang, Yang Xue*, Lianwen Jin, DocNLC: A Document Image Enhancement Framework with Normalized and Latent Contrastive Representation for Multiple Degradations , AAAI 2024 (CCF A类会议)

15.      Zening Lin, Jiapeng Wang, Teng Li, Wenhui Liao, Dayi Huang, Longfei Xiong, Lianwen Jin*. PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction, ACM MM 2024. (CCF A类会议)

16.      Yaqiang Wu, Zhen Xu, Yong Duan, Yanlai Wu, Qinghua Zheng, Hui Li, Xiaochen Hu, Lianwen Jin. RDLNet: A Novel and Accurate Real-world Document Localization Method. ACM MM 2024. (CCF A类会议)

17.      Zhen Xu, Ziqiang Chen, Yaqiang Wu, Hui Li, Wanjun Lv, Lianwen Jin, Qianying Wang, A Multi-Scale Bimodal Fusion Network For Robust and Accurate Online Handwriting Recognition, ICASSP 2024 (CCF B类会议)

18.      Zongyuan Jiang, Jiayu Chen, Chongyu Liu, Ning Zhang, Jun Huang, Xue Gao*, Lianwen Jin*, RISC: Boosting High-quality Referring Image Segmentation via Foundation Model CLIPICME 2024 (CCF B类会议)

19.      Yuxin Kong, Weihong Ma, Lianwen Jin* and Xue Yang, GARDEN: Generative Prior Guided Network for Scene Text Image Super-Resolution, ICDAR 2024 (CCF C类会议, CAAI B类会议)

20.      Pengjie Wang, Kaile Zhang, Xinyu Wang, Shengwei Han, Yongge Liu, Lianwen Jin, Xiang Bai and Yuliang Liu*, Puzzle Pieces Picker: Deciphering Ancient Chinese Characters with Radical Reconstruction, ICDAR 2024 (CAAI B类会议,CCF C类会议)

21.      Xinhong Chen, Bangdong Chen, Chenfan Qu, Dezhi Peng, Chongyu Liu and Lianwen Jin*, DTSM: Toward Dense Table Structure Recognition with Text Query Encoder and Adjacent Feature Aggregator, ICDAR 2024 (CAAI B类会议,CCF C类会议)

22.      Linger Deng, Mingxin Huang, Xudong Xie, Yuliang Liu*, Lianwen Jin and Xiang Bai, Progressive Evolution from Single-Point to Polygon for Scene Text, ICDAR 2024 (CAAI B类会议,CCF C类会议)

23.      Zening Lin, Jiapeng Wang, Wenhui Liao, Weicong Dai, Longfei Xiong, Lianwen Jin*, ROISER: Towards Real World Semantic Entity Recognition from Visually-rich Documents ICPR 2024 (CCF C类会议,CAAI B类会议,IAPR旗舰会议)

 

2023

Journal Papers

24.     Yuliang Liu, Jiaxin Zhang, Dezhi Peng, Mingxin Huang, Xinyu Wang, Jingqun Tang, Can Huang,Dahua Lin, Chunhua Shen, Xiang Bai, Lianwen Jin*, SPTS v2: Single-Point Scene Text Spotting, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)2023 SCI 2021 IF=24.314,中科院一区/Top期刊,JCR Q1, CCF A类期刊

25.      Chongyu Liu, Cheng Jian, Jiarong Huang, Wentao Yang, Yongxin Shi, Qing Jiang, and Lianwen Jin, A Robust and Efficient Algorithm for Chinese Historical Document Analysis and Recognition, National Science Review  (NSR), 2023. SCI 2022 IF: 23.178, JCR Q1区,中科院一区/Top期刊

26.      Zhe Li, Xinyu Wang, Yuliang Liu*, Lianwen Jin*, Yichao Huang, Kai Ding, Improving Handwritten Mathematical Expression Recognition via Similar Symbol Distinguishing, IEEE Transactions on Multimedia (TMM), 2023SCI 2022 IF: 8.182, JCR Q1区,中科院一区/Top期刊

27.      Jiaxin Zhang, Lingyu Liang, Kai Ding*, Fengjun Guo, and Lianwen Jin*, Appearance Enhancement for Camera-captured Document Images in the Wild, IEEE Transactions on Artificial Intelligence (TAI), 2023

28.      Jiale Cheng, Dongzi Shi, Chenyang Li, Yu Li, Hao Ni, Lianwen Jin, Xin Zhang*, Skeleton-based Gesture Recognition with Learnable Paths and Signature Features, IEEE Transactions on Multimedia (TMM), 2023SCI 2022 IF: 8.182, JCR Q1区,中科院一区/Top期刊

29.      Zhile Chen, Yuhui Quan, Ruotao Xu, Lianwen Jin, Yong Xu*, Enhancing texture representation with deep tracing pattern encoding, Pattern Recognition, 2023. SCI 2022 IF: 8.518, JCR Q1区,中科院一区/Top期刊

30.      Hongyi Wang, Yang Xue*, Jiaxin Zhang, Lianwen JinScene table structure recognition with segmentation collaboration and alignment, Pattern Recognition Letters, 2023. (SCI IF=4.757, JCR Q1)

31.      刘成林,金连文,白翔,李晓辉,殷飞,文档智能分析与识别前沿:回顾与展望,中国图象图形学报2023. (CCF B类中文期刊)

32.      严昊; 刘禹良; 金连文; 白翔,类ChatGPT大模型发展、应用和前景,中国图象图形学报, 2023, 28(9): 2749-2762 (CCF  B类中文期刊)

33.      刘禹良; 李鸿亮; 白翔; 金连文,浅析ChatGPT: 历史沿革、应用现状及前景展望,中国图象图形学报, 2023, 28(4): 893-902 (CCF  B类中文期刊)

 

Conference Papers:

34.      Chenfan Qu, Chongyu Liu, Yuliang Liu, Xinhong Chen, Dezhi Peng, Fengjun Guo, Lianwen Jin*, Towards Robust Tampered Text Detection in Document Image: New dataset and New Solution, CVPR 2023 (CCF A类会议,计算机视觉&人工智能顶会).

35.      Hiuyi Cheng, Sihang Wu, Peirong Zhang, Jiaxin Zhang, Qiyuan Zhu, Xiezecheng Xie, Jing Li, Kai Ding, Lianwen Jin*, M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis, CVPR 2023 (CCF A类会议,计算机视觉&人工智能顶会).

36.      Weifeng Lin , Wu Ziheng, Jiayu Chen , Jun Huang , Lianwen Jin*, Scale-Aware Modulation Meet Transformer, ICCV 2023  (CCF A类会议,计算机视觉&人工智能顶会).

37.      Mingxin Huang, Jiaxin Zhang, Dezhi Peng, Yuliang Liu, Hao Lu, Can Huang, Xiang Bai, Lianwen Jin*, ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer, ICCV 2023  (CCF A类会议,计算机视觉&人工智能顶会).

38.      Qing Jiang, Jiapeng Wang, Dezhi Peng, Chongyu Liu, Lianwen Jin*, Revisiting Scene Text Recognition: A Data Perspective, ICCV 2023  (CCF A类会议,计算机视觉&人工智能顶会).

39.      Wentao Yang, Zhe Li, Dezhi Peng, Lianwen Jin*, Mengchao He, Cong Yao, Read Ten Lines at One Glance: Line-Aware Semi-Autoregressive Transformer for Multi-Line Handwritten Mathematical Expression Recognition, ACM MM 2023 (CCF A类会议).

40.      Yongxin Shi, Chongyu Liu, Dezhi Peng, Cheng Jian, Jiarong Huang, Lianwen Jin*, M5HisDoc: A Large-scale Multi-style Chinese Historical Document Analysis Benchmark, NeurIPS 2023 (Datasets & Benchmarks Track) (CCF A类会议).

41.      Jiapeng Wang, Chengyu Wang, Xiaodan Wang, Jun Huang and Lianwen Jin, CocaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval, ACL 2013 (Industry Track). (ACLNLP领域CCF A类会议)

42.      Bingyan Liu, Weifeng Lin, Zhongjie Duan, Chengyu Wang, Wu Ziheng, Zhang Zipeng, Kui Jia, Lianwen Jin, Cen CHEN and Jun Huang, Rapid Diffusion: Building Domain-Specific Text-to-Image Synthesizers with Fast Inference Speed, ACL 2013 (Industry Track).  (ACLNLP领域CCF A类会议)

43.      Li Zhuoming, Peng Fan, Xue Yang, Ni Hao and Jin Lianwen, Scene Table Structure Recognition with Segmentation and Key Point Collaboration, ICDAR 2023 oral (CCF C类会议)

44.      Cheng Jian, Lianwen Jin*, Lingyu Liang and Chongyu Liu, HisDoc R-CNN: Robust Chinese Historical Document Text Line Detection with Dynamic Rotational Proposal Network and Iterative Attention Head, ICDAR 2023 oral (CCF C类会议)

45.      Jiarong Huang, Dezhi Peng, Hongliang Li, Hao Ni and Lianwen Jin*, SegCTC: Offline Handwritten Chinese Text Recognition via Better Fusion between Explicit and Implicit Segmentation, ICDAR 2023 (CCF C类会议)

46.      Liufeng Huang, Bangdong Chen, Chongyu Liu, Dezhi Peng, Weiying Zhou, Yaqiang Wu, Hui Li, Hao Ni and Lianwen Jin*, EnsExam: A Dataset for Handwritten Text Erasure on Examination Papers, ICDAR 2023 (CCF C类会议)

47.      Haiyang Li, Chongyu Liu, Jiapeng Wang, Mingxin Huang, Weiying Zhou and Lianwen Jin*, DTDT: Highly Accurate Dense Text Line Detection in Historical Documents via Dynamic Transformer, ICDAR 2023 oral (CCF C类会议)

48.      Dongliang Luo, Yu Zhou, Rui Yang, Yuliang Liu, Xianjin Liu, Jishen Zeng, Enming Zhang, Biao Yang, Ziming Huang, Lianwen Jin and Xiang Bai, ICDAR 2023 Competition on Detecting Tampered Text in Images, ICDAR 2023 (invited paper) (CCF C类会议)

49.      Chenyang Gao, Yuliang Liu, Shiyu Yao, Jinfeng Bai, Xiang Bai, Lianwen Jin and Cheng-Lin Liu, ICDAR 2023 Competition on Recognition of Multi-line Handwritten Mathematical Expressions, ICDAR 2023 (invited paper) (CCF C类会议)

50.      Zongyuan Jiang, Jiapeng Wang, Jiahua Cao, Xue Gao, Lianwen Jin*, Towards Better Translations from Classical to Modern Chinese: A New Dataset and a New Method. NLPCC 2023 (CCF C类会议)

 

2022

Journal Papers

51.  Songxuan Lai, Lianwen Jin*, Yechen Zhu, Ze Li, Luojun Lin, SynSig2Vec: Forgery-free Learning of Dynamic Signature Representations by Sigma Lognormal-based Synthesis, IEEE TPAMI2022 SCI 2021 IF=24.31,中科院一区/Top期刊,JCR Q1, CCF A类期刊

52.      Yuliang Liu, Chunhua Shen*, Lianwen Jin*, Tong He, Peng Chen, Chongyu Liu, Hao Chen, ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting, IEEE TPAMI2022 SCI 2021 IF=24.31,中科院一区/Top期刊,JCR Q1, CCF A类期刊

53.      Jiajia Jiang, Songxuan Lai, Lianwen Jin*, Yecheng Zhu, DsDTW: Local Representation Learning with Deep soft-DTW for Dynamic Signature Verification, IEEE Transactions on Information Forensics and Security (TIFS), 2022.SCI 2022 IF=7.231, JCR Q1区,CCF A类期刊,中科院一区/Top期刊)

54.  Canjie Luo, Yuanzhi Zhu, Lianwen Jin*; Zhe Li, Dezhi Peng, SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text, IEEE TNNLS, 2022SCI 2022 IF: 14.255, JCR Q1区,中科院一区/Top期刊

55.      Dezhi Peng, Lianwen Jin*, Weihong Ma, Canyu Xie, Hesuo Zhang, Shenggao Zhu, and Jing Li, Recognition of Handwritten Chinese Text by Segmentation: A Segment-annotation-free Approach, IEEE Transactions on Multimedia (TMM), 2022SCI 2022 IF: 8.182, JCR Q1区,中科院一区/Top期刊

56.      Lingyu Liang, Lianwen Jin*, Yong Xu, PDE Learning of Filtering and Propagation for Task-Aware Facial Intrinsic Image Analysis,  IEEE Transactions on Cybernetics (TCYB) , vol.52, no. 2, pp 1021-1034, 2022.SCI 2021 IF: 11.448, JCR Q1区,中科院一区/Top期刊

57.      Dezhi Peng, Lianwen Jin*, Yuliang Liu, Canjie Luo, Songxuan Lai, PageNet: Towards End-to-End Weakly Supervised Page-Level Handwritten Chinese Text Recognition, International Journal of Computer Vision (IJCV), 2022. SCI 2021 IF: 13.369, JCR Q1区,中科院二区/Top期刊

58.  Jiajia Jiang, Songxuan Lai, Lianwen Jin*, Yecheng Zhu, Jiaxin Zhang, Bangdong Chen, Learning to Generate Realistic Signatures for Forgery-free Offline Handwritten Signature Verification, Neurocomputing, 2022SCI 2021 IF= 5.779, JCR Q1区)

59.      Ruben Tolosana, Ruben Vera-Rodriguez, Carlos Gonzalez-Garcia, Santiago Rengifo, Aythami Morales Julian Fierrez, Javier Ortega-Garcia, Juan Carlos Ruiz-Garcia, Sergio Romero-Tapiador, Jiajia Jiang, Songxuan Lai, Lianwen Jin, et al., SVC-onGoing: Signature Verification Competition, Pattern Recognition, 2022. SCI 2022 IF: 8.518, JCR Q1区,中科院一区/Top期刊

60.      Ying Cai, Yuliang Liu*, Chunhua Shen, Lianwen Jin*, Yidong Li, Daji Ergu, Arbitrarily Shaped Scene Text Detection with Dynamic Convolution, Pattern Recognition, 2022. SCI 2022 IF: 8.518, JCR Q1区,中科院一区/Top期刊

61.      高良才, 李一博, 都林, 张新鹏, 朱子仪, 卢宁, 金连文, 永帅, 汤帜,表格识别技术研究进展,中国图象图形学报vol.24, no.6, 2022. CCF B类中文期刊

 

Conference Papers:

62.      Jiapeng Wang, Lianwen Jin*, Kai Ding, LiLT: A Simple yet Effective Language-Independent Layout Transformer for Multilingual Structured Text Understanding, ACL 2022 (CCF A, NLP领域顶会)

63.  Canjie Luo, Lianwen Jin*, Jingdong Chen, SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization, CVPR 2022 (CCF A类会议,计算机视觉&人工智能顶会)

64.      Mingxin Huang, Yuliang Liu, Zhenghao Peng, Chongyu Liu, Dahua Lin, S.G. Zhu, N. Yuan, K. DingLianwen Jin*, SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition, CVPR 2022 (CCF A类会议,计算机视觉&人工智能顶会)

65.  Yuxin Kong, Canjie Luo, Weihong Ma, Qiyuan Zhu, Shenggao Zhu, N. Yuan, Lianwen Jin*, Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator, CVPR 2022 (CCF A类会议,计算机视觉&人工智能顶会)

66.      Dezhi Peng, Xinyu Wang, Yuliang Liu, Jiaxin Zhang, Mingxin Huang, Songxuan Lai, Jing Li, Shenggao Zhu, Dahua Lin, Chunhua Shen, Xiang Bai, Lianwen Jin*, SPTS: Single-Point Text Spotting, ACM MM 2022. oral (CCF A类会议,多媒体&图像处理顶会)

67.      Jiaxin Zhang, Canjie Luo, Lianwen Jin*, Fengjun Guo, Kai Ding, Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the Wild, ACM MM 2022 (CCF A类会议,多媒体&图像处理顶会)

68.      Chongyu Liu, Lianwen Jin*, Yuliang Liu, Canjie Luo, Bangdong Chen, Fengjun Guo, Kai Ding, Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context, ECCV 2022. (CCF B类会议,计算机视觉顶会)

69.  Peirong Zhang, Jiajia Jiang, Yuliang Liu, Lianwen JinMSDS: A Large-Scale Chinese Signature and Token Digit String Dataset for Handwrting VerificationNeurIPS 2022 (Tracks on Datasets and Benchmarks) (CCF A类会议)

70.      Jizhao Ma, Lianwen Jin*, Jiaxin Zhang, Jiajia Jiang, TextSRNet: Scene Text Super-Resolution Based on Contour Prior and Atrous Convolution, ICPR 2022 (oral) ICPR 2022 Best Scientific Paper Award! (CCF C类会议)

71.      Yujin Ren, Jiaxin Zhang, Bangdong Chen, Xiaoyi Zhang, Lianwen Jin, Look from a Higher-level Perspective: Attention and Recognition Enhanced Multi-scale Segmentation Network for Scene Text, ACCV 2022  Oral (CCF C类会议, Oral论文录取率4.9%)

72.      Xiaoyi Zhang, Jiapeng Wang, Lianwen Jin*, Yujin Ren, Yang Xue, CMT-Co: Contrastive Learning with Character Movement Task for Handwritten Text Recognition, ACCV 2022 Oral (CCF C类会议, Oral论文录取率4.9%, 最佳应用论文提名奖)

73.      Xiaoyi Zhang, Tianwei Wang, Jiapeng Wang, Lianwen Jin, Canjie Luo and Yang Xue, ChaCo: Character Contrastive Learning for Handwritten Text Recognition, ICFHR 2022. 最佳学生论文奖

74.      Bangdong Chen, Dezhi Peng, Jiaxin Zhang, Yujin Ren and Lianwen Jin, Complex Table Structure Recognition in the Wild using Transformer and Identity Matrix-based Augmentation, ICFHR 2022.

75.      Xiaoyi Zhen, Lianwen Jin, SCUT-CAB: A New Benchmark Dataset of Ancient Chinese Books with Complex Layouts for Document Layout Analysis, ICFHR 2022.    

 

2021

Journal Papers:

76.     Songxuan Lai, Lianwen Jin*, Yechen Zhu, Ze Li, Luojun Lin, SynSig2Vec: Forgery-free Learning of Dynamic Signature Representations by Sigma Lognormal-based Synthesis, IEEE TPAMI2021 SCI IF=16.389,中科院一区/Top期刊,JCR Q1, CCF A类期刊

77.     Yuliang Liu, Chunhua Shen*, Lianwen Jin*, Tong He, Peng Chen, Chongyu Liu, Hao Chen, ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting, IEEE TPAMI2021 SCI IF=16.389,中科院一区/Top期刊,JCR Q1, CCF A类期刊

78.  Canjie Luo, Qingxiang Lin, Yuliang Liu, Lianwen Jin*, Chunhua Shen, Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild, IJCV 2021 SCI IF = 7.410, JCR Q1区,中科院二区, CCF A类期刊/Top期刊

79.      Yuliang Liu, Tong He, Hao Chen, Xinyu Wang, Canjie Luo, Shuaitao Zhang, Chunhua Shen*, Lianwen Jin*, Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection, IJCV 2021 SCI IF =7.410, JCR Q1区,中科院二区, CCF A类期刊/Top期刊

80.      Tasweer Ahmad, Lianwen Jin*, Xin Zhang, Songxuan Lai, Guozhi Tang, Luojun Lin, Graph Convolutional Neural Network for Action Recognition: A Comprehensive Survey, IEEE Trans. Artificial Intelligence, 2021.

81.  Xiaoxue Chen, Lianwenn Jin*, Yuanzhi Zhu, Canjie Luo, Tianwei Wang, Text Recognition in the Wild: A Survey, ACM Computing Surveys, 2021. SCI IF = 10.282, JCR Q1, 中科院一区/Top期刊

82.  Songbin Xu, Yang Xue*, Xin Zhang, Lianwen Jin, A Novel Unsupervised Domain Adaptation Method for Inertia-Trajectory Translation of In-air Handwriting, Pattern Recognition, 2021. SCI IF=7.740, JCR Q1,中科院二区/Top期刊

83.  Yong Xu, Haoyang Zou,Yan Huang, Lianwen Jin, Haibin Ling, Super-resolving blurry face images with identity preservation, Pattern Recognition Letters, 2021. (SCI IF=3.756, JCR Q1

84.  刘崇宇,陈晓雪,罗灿杰,金连文*,薛洋*,刘禹良,自然场景文本检测与识别的深度学习方法,中国图象图形学报vol. 26, no.6, pp1330-1368, 2021.  ( In Chinese)

Conference Papers:

85.      Tianwei Wang, Yuanzhi Zhu, Lianwen Jin*, Dezhi Peng, Zhe Li, Mengchao He, Yongpan Wang, Canjie Luo, Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter, CVPR 2021. (CCF A类会议,计算机视觉&人工智能顶会)

86.      Yiqin Zhu, Jianyong Chen, Lingyu Liang, Zhanghui Kuang, Lianwen Jin, Wayne Zhang, Fourier Contour Embedding for Arbitrary-Shaped Text Detection, CVPR 2021. (CCF A类会议,计算机视觉&人工智能顶会)

87.      Towards Robust Visual Information Extraction in Real World: New Dataset and Novel SolutionAAAI 2021.  (人工智能顶会,CCF A类会议)

88.      Jiapeng Wang, Tianwen Wang, Guozhi Tang, Lianwen Jin*, Weihong Ma, Kai Ding, Yichao Huang, Tag, Copy or Predict: A Unified Weakly-Supervised Learning Framework for Visual Information Extraction using Sequences, IJCAI 2021.  (人工智能顶会,CCF A类会议)

89.      Guozhi Tang, Lele Xie, Liannwen Jin*, Jiapeng Wang, Jingdong Chen, Zhen Xu, Qianying Wang, Yaqiang, Wu, Hui Li, MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction, IJCAI 2021.  (人工智能顶会,CCF A类会议)

90.      Yuhao Huang, Lianwen Jin and Dezhi Peng Zero-Shot Chinese Text Recognition via Matching Class Embedding, ICDAR 2021.  (CCF C类会议)

91.      Sihang Wu, Canyu Xie, Yuhao Huang, Guozhi Tang, Qianying Liao, Jiapeng Wang, Bangdong Chen, et al., Improving Machine Understanding of Human Intent in Charts, ICDAR 2021. (CCF C类会议)

92.      Hesuo Zhang, Weihong Ma, Lianwen Jin, et al., DeMatch: Towards Understanding the Panel of Chart Documents, ICDAR 2021. (CCF C类会议)

93.      Weihong Ma, Hesuo Zhan, et al., Towards an efficient framework for Data Extraction from Chart Images, ICDAR 2021. (CCF C类会议)

94.      Dezhi Peng, Canyu Xie, Hongliang Li, Lianwen Jin, et al., Towards Fast, Accurate and Compact Online Handwritten Chinese Text Recognition, ICDAR 2021. (CCF C类会议)

95.      Qianying Liao, Qingxiang Lin, Lianwen Jin, Canjie Luo, Jiaxin Zhang, Dezhi Peng and Tianwei Wang, A Multi-level Progressive Rectification Mechanism for Irregular Scene Text Recognition, ICDAR 2021. (CCF C类会议)

 

2020

Journal Papers:

96.      Chongyu Liu, Yuliang Liu, Lianwen Jin*, Suaitao Zhang, Canjie Luo, Yongpan Wang, EraseNet: End-to-End Text Removal in the Wild, IEEE Transactions on Image Processing (TIP), 2020.SCI IF=10.856, JCR Q1区,CCF A类期刊,中科院一区,Top期刊

97.      Yuliang Liu, Lianwen Jin* Chuanming Fang, Arbitrarily Shaped Scene Text Detection with a Mask Tightness Text Detector, IEEE Transactions on Image Processing (TIP), vol.29, pp 2918-2930, 2020.SCI IF=10.856, JCR Q1区,CCF A类期刊,中科院一区,Top期刊

98.     Songxuan Lai, Yecheng Zhu, Lianwen Jin*, Encoding Pathlet and SIFT Features with Bagged VLAD for Historical Writer Identification, IEEE Transactions on Information Forensics and Security (TIFS), vol.15, no. 6, pp 3553-3566, 2020.SCI IF=7.178, JCR Q1区,CCF A类期刊,中科院二区,Top期刊

99.      Sheng Zhang, Yuliang Liu, Lianwen Jin, Zhongrong Wei, Chunhua Shen, OPMP: An Omni-directional Pyramid Mask Proposal Network for Arbitrary-shape Scene Text Detection, IEEE Transactions on Multimedia (TMM) , vol.1xx, no. x, pp xx, 2020.SCI IF = 6.513, JCR Q1区,中科院二区,Top期刊

100.Lingyu Liang, Lianwen Jin*, Yong Xu, PDE Learning of Filtering and Propagation for Task-Aware Facial Intrinsic Image Analysis,  IEEE Transactions on Cybernetics (TCYB) , vol.52, no.2, pp 1021-1034, 2020.SCI IF = 11.448, JCR Q1区,中科院一区,Top期刊

101.   Sihang Wu, Jiapeng Wang, Weihong Ma, Lianwen Jin*Precise Detection of Chinese Characters in Historical Documents with Deep Reinforcement Learning, Pattern Recognition, 2020. SCI IF=7.740, JCR Q1区,中科院二区,Top期刊

102.  Hesuo Zhang, Lingyu Liang*, Lianwen Jin, SCUT-HCCDoc: A New Benchmark Dataset of Handwritten Chinese Text in Unconstrained Camera-captured Documents, Pattern Recognition, 2020. SCI IF=7.740, JCR Q1区,中科院二区,Top期刊

103.  Qingxiang Lin, Canjie Luo, Lianwen Jin*, Songxuan Lai, STAN: A Sequential Transformation Attention-based
Network for Scene Text Recognition,
Pattern Recognition, 2020. SCI IF=7.740, JCR Q1区,中科院二区,Top期刊

104. Xiaoxue Chen, Tianwei Wang, Yuanzhi Zhu, Lianwen Jin*, Canjie Luo, Adaptive Embedding Gate for Attention-Based Scene Text Recognition, Neurocomputing, vol.381, pp261-271, 2020. SCI IF= 5.719, JCR Q1区,中科院二区,Top期刊)

105.   Yunlong Huang, Zenghui Sun, Lianwen Jin*, Canjie Luo, EPAN: Effective Parts Attention Network for Scene Text Recognition, Neurocomputing, 2020.SCI IF= 5.719, JCR Q1区,中科院二区,Top期刊)

106.Tasweer Ahmad, Lianwen Jin*, Luojun Lin, Guozhi Tang, Action recognition using sparse spatio-temporal GCN with edge effective resistance, Neurocomputing, 2020.SCI IF= 5.719, JCR Q1区,中科院二区,Top期刊

107.   Jiaxin Zhang; Canjie Luo; Lianwen Jin, PhD; Tianwei Wang; Ziyan Li; Weiying Zhou, SaHAN: Scale-aware hierarchical attention network for scene text recognition, Pattern Recognition Letters, 2020. (SCI IF=3.756 JCR Q2

 

Conference Papers:

108.   Songxuan Lai, Lianwen Jin*, Yecheng Zhu, Huiyun Mao, SynSig2Vec: Learning Representations from Synthetic Dynamic Signatures for Real-world Verification, AAAI 2020.  (CCF A类会议)

109.   Tianwei Wang, Yuanzhi Zhu, Lianwen Jin*, Canjie Luo, Xiaoxue Chen, Yapeng Wu, Qianyin Wang, Decoupled Attention Network for Text Recognition, AAAI 2020.  (CCF A类会议)

110.   Canjie Luo, Yuanzhi Zhu, Lianwen Jin, Yongpan Wang, Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition, CVPR 2020. (CCF A类会议)

111.   Yuliang Liu, Hao Cheng, Chunhua Shen, Tong He, Lianwen Jin, Liangwei Wang, ABCNet: Arbitrarily-Shaped Scene Text Spotting with Adaptive Bezier-Curve Network, CVPR 2020. (CCF A类会议)

112.   Xinyu Wang, Yuliang Liu, Chunhua Sheng, CC Ng, Canjie Luo, Lianwen Jin, et al, On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering, CVPR 2020. (CCF A类会议)

113.   Yaoxiong Huang, Mengchao He, Lianwen Jin, Yongpan Wang, RD-GAN: Few/Zero-Shot Chinese Character Style Transfer via Radical Decomposition and Rendering, ECCV 2020. (CCF B类会议,CV领域顶会之一)

114.   Canyu Xie, Songxuan Lai, Lianwen Jin and Qianying Liao, High performance offline handwritten Chinese text recognition with a new data preprocessing and augmentation pipeline, DAS 2020.

115.   Weihong Ma, Hesuo Zhang, Lianwen Jin, Sihang Wu, Jiapeng Wang and Yongpan Wang, A Joint OCR and Layout Analysis Framework for Historical Document Digitization, ICFHR 2020.

116.   Zhe Li, Lianwen Jin, Songxuan Lai and Yecheng Zhu, Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attention, ICFHR 2020.

117.   Yecheng Zhu, Songxuan Lai, Zhe Li and Lianwen Jin, Point-to-Set Similarity Based Deep Metric Learning for Offline Signature Verification, ICFHR 2020.

 

2019

Journal papers:

118.   Songxuan Lai, Lianwen Jin*, Recurrent Adaptation Networks for Online Signature Verification, IEEE Transactions on Information Forensics and Security (TIFS), vol.14, no. 6, pp 1624-1637, 2019.SCI IF=7.178, JCR Q1区,中科院二区,Top期刊

119.   Luojun Lin, Yuliang Liu, Lianwen Jin*, Regression Guided by Relative Ranking Using Convolutional Neural Network (R^3CNN) for Facial Beauty Prediction, IEEE Transactions on Affective Computing (TAFFC), 2019. (SCI IF=10.506, JCR Q1区,中科院一区

120.   Canjie Luo, Lianwen Jin*, Zenghui Sun, MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition, Pattern Recognition, vol. 90, no.6, pp109-118, 2019SCI IF=7.740, JCR Q1区中,中科院二区,Top期刊

121.   Yuliang Liu, Lianwen Jin*, Shuaitao Zhang, Canjie Luo and Sheng ZhangCurved Scene Text Detection via Transverse and Longitudinal Sequence ConnectionPattern Recognition, vol. 90, no.6, pp337-345, 2019SCI IF=7.740, JCR Q1区中,中科院二区,Top期刊

122.   Zecheng Xie, Yiaoxiong Huang, Lianwen Jin*, Yuliang Liu,Yuanzhi Zhua, Liangcai Gao, Xiaode Zhang, Weakly Supervised Precise Segmentation for Historical Document Images, NeuroComputing, 2019 (SCI IF= 5.719, JCR Q1区,中科院二区,Top期刊

123.   Yuanzhi Zhu, ZeCheng Xie, Lianwen Jin*, Xiaoxue Chen, Yaoxiong Huang, Ming Zhang, SCUT-EPT: a New Dataset and Benchmark for Offline Chinese Text Recognition in Examination Paper, IEEE Access, vol.7, no.1, pp.370-382, 2019. (SCI IF=3.367, JCR Q1

124.   Fan Yang, Lianwen Jin*, Songxuan Lai, Xue Gao, Zhaohai Li, Fully Convolutional Sequence Recognition Network for water meter Number Reading, IEEE Access, vol.7, no.1, pp 11679-11687, 2019. (SCI IF=3.367, JCR Q1

125.   Yuliang Liu, Lianwen Jin*, Songxuan Lai, Automatic Labeling of Large Amounts of Handwritten Characters with Gate-guided Dynamic Deep Learning, Pattern Recognition Letters, vol.119, no.3, pp94-102, 2019. (SCI IF=3.756JCR Q1

126.   Tasweer Ahmad*, Lianwen Jin, Jialuo Feng, Guoizhi Tang, Human Action Recognition in unconstrained trimmed videos using Residual Attention network and Joints Path Signature, IEEE Access, 2019. (SCI IF=3.367, JCR Q1

 

Conference papers:

127.    Zecheng Xie, Yiaoxiong Huang, Yuanzhi Zhu, Lianwen Jin*, Yuliang Liu, Lele Xie, Aggregation Cross-Entropy for Sequence Recognition, CVPR 2019 (Oral).  (CCF A类会议)

128.    Yuliang Liu, Lianwen Jin*, Zecheng Xie, Canjie Luo, Lele Xie, Shuaitao Zhang, Tightness-aware Evaluation Protocol for Scene Text Detection, CVPR 2019.  (CCF A类会议)

129.    Lele Xie, Yuliang Liu, Lianwen Jin*, Zecheng Xie, DeRPN: Taking a further step toward more general object detection, AAAI 2019.  (CCF A类会议)

130.    Shuaitao Zhang, Yuliang Liu, Lianwen Jin*, Yaoxiong Huang, Songxuan LaiEnsNet: Ensconce Text in the Wild, AAAI 2019.  (CCF A类会议)

131.    Yang Chen, Xin Zhang, Lufan Liao, Lianwen Jin, Weixin Yang, Skeleton-based Gesture Recognition Using Several Fully Connected Layers with Path Signature Features and Temporal Transformer Module, AAAI 2019.  (CCF A类会议)

132.    Luojun Lin, Linyu Liang, Lianwen Jin*, Weijie Chen, Attribute-Aware Convolutional Neural Networks for Facial Beauty Prediction, IJCAI 2019. (CCF A类会议)

133.   Yuliang Liu, Sheng Zhang, Lianwen Jin*, Lele Xie, Yaqiang Wu, Zhepeng Wang, Omnidirectional Scene Text Detection with Sequential-free Box Discretization, IJCAI 2019. (CCF A类会议)

134.   Lingyu Liang, Lianwen Jin, Yong Xu, Adaptive GNN for Image Analysis and Editing, NeurIPS 2019. (CCF A类会议)

135.   Dezhi Peng, Lianwen Jin, Yaqiang Wu, Zhepeng Wang, Mingxiang Cai, A Fast and Accurate Fully Convolutional Network for End-to-End Handwritten Chinese Text Segmentation and Recognition , ICDAR 2019. (CCF C类会议)

136.   Yunlong Huang , Canjie Luo , Lianwen Jin , Qingxiang Lin , Weiying Zhou, Attention After Attention: Reading Text in the Wild with Cross Attention, ICDAR 2019. (CCF C类会议)

137.   Yaoxiong Huang , Zecheng Xie , Lianwen Jin , Yuanzhi Zhu , Shuaitao Zhang, Adversarial Feature Enhancing Network for End-to-End Handwritten Paragraph Recognition, ICDAR 2019. (CCF C类会议)

138.   Shuangping Huang , Haobin Wang , Yongge Liu, Xiaosong Shi, Lianwen Jin, OBC306: A Large-Scale Oracle Bone Character Recognition Dataset681, ICDAR 2019. (CCF C类会议)

139.   Songxuan Lai , Lianwen Jin, Offline Writer Identification Based on the Path Signature Feature, ICDAR 2019. (CCF C类会议)

140.   Jinrong Li , Zijian Zhou, Zhizhong Su, Shuangping Huang , Lianwen Jin, A New Parallel Detection-Recognition Approach for End-to-End Scene Text Extraction, ICDAR 2019. (CCF C类会议)

141.   Yipeng Sun , Zihan Ni , Chee-Kheng Chng , Yuliang Liu , Canjie Luo , Chun Chet Ng , Junyu Han , Errui Ding , Jingtuo Liu , Dimosthenis Karatzas, Chee Seng Chan , Lianwen Jin, ICDAR 2019 Competition on Large-Scale Street View Text with Partial Labeling - RRC-LSVT, ICDAR 2019. (CCF C类会议)

142.   Chee Kheng Chng, Yuliang Liu , Yipeng Sun , Chun Chet Ng , Canjie Luo , Zihan Ni , ChuanMing Fang , Shuaitao Zhang , Junyu Han , Errui Ding , Jingtuo Liu , Dimosthenis Karatzas, Chee Seng Chan , Lianwen Jin, ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT, ICDAR 2019. (CCF C类会议)

 

 

2018

Journal papers:

143.   Zecheng Xie, Zenghui Sun, Lianwen Jin*, Hao Ni and Terry LyonsLearning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol.40, no.8, pp 1903-1917, 2018.SCI IF=16.389, JCR Q1区,中科院一区,Top期刊

144.   Zhaoyang Yang, Kathryn Merrick, Lianwen Jin, Hussein Abbass, Hierarchical Deep Reinforcement Learning for Continuous Action Control, IEEE Transactions on Neural Networks and Learning Systems, 2018. SCI IF=10.451, JCR Q1区,中科院区,Top期刊

145.   Lele Xie, Tasweer Ahmad, Lianwen Jin*, Yuliang Liu, and Sheng Zhang, A New CNN based Method for Multi-directional Car License Plate Detection, IEEE Transactions on Intelligent Transportation Systems, vol. 19, no.2, pp. 507-517, 2018SCI IF=6.492, JCR Q1区,中科院二区,Top期刊

146.   Jingcong Li, Zhu Liang Yu*, Zhenghui Gu, Wei Wu, Yuanqing Li and Lianwen Jin,“A Hybrid Network for ERP Detection and Analysis Based on Restricted Boltzmann Machines”, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2018, VOL. 26, NO. 3, pp63-572, 2018. (SCI IF=3.802, JCR Q1

147.   Pengwei Wang, Lei Ji, Jun Yan, Dejing Dou, Nisansa De Silva, Yong Zhang, Lianwen Jin, Concept and Attention Based CNN for Question Retrieval in Multi-View Learning, ACM Transactions on Intelligent Systems and Technology,vol.9, no.4, pp1-24, 2018. (SCI IF=4.654, JCR Q1

148.   Shuangping Huang, Zhuoyao Zhong, Lianwen Jin* Shuye Zhang, Haobin Wang, DropRegion Training of Inception Font Network for High-Performance Chinese Font Recognition, Pattern Recognition, vo. 77, no. 5, pp 395-411, 2018SCI IF=7.740, JCR Q1区,中科院二区,Top期刊

149.   Hailin Yang, Lianwen Jin*, Weiguo Huang, Zhaoyang Yang, Songxuan Lai, Jifeng Sun, Dense and Tight Detection of Chinese Charactersin Historical Documents: Datasets and a Recognition Guided Detector, IEEE Acess, 2018. (SCI IF=3.367, JCR Q1

 

Conference papers:

150.   Sheng Zhang, Yuliang Liu, Lianwen Jin, Canjie LuoFeature Enhancement Network: A Refined Scene Text Detector, AAAI 2018. (CCF A类会议)

151.   Zikai Sun, Dezhi Peng, Zirui Cai, Zirong Chen, Lianwen JinScale Mapping And Dynamic Re-Detecting In Dense Head Detection, ICIP 2018. (CCF C类会议)

152.   Dezhi Peng, Zikai Sun, Zirong Chen, Zirui Cai, Lele Xie, Lianwen Jin, Detecting Heads Using Feature Refine Net and Cascaded Multi-Scale Architecture, pp2528-2533, ICPR 2018.  (CCF C类会议)

153.   Luojun Lin, Lingyu Liang and Lianwen Jin*, R^2-ResNeXt: A ResNeXt-Based Regression Model with Relative Ranking for Facial Beauty Prediction, pp85-90, ICPR 2018.  (CCF C类会议)

154.   Lingyu Liang, Luojun Lin, Lianwen Jin*, Duorui Xie and Mengru Li, SCUT-FBP5500: A Diverse Benchmark Dataset for Multi-Paradigm Facial Beauty Prediction, pp1598-1633, ICPR 2018.  (CCF C类会议)

155.   Haobin Wang, Shuangping Huang and Lianwen JinFocus on Scene Text Using Deep Reinforcement Learning, pp3759-3765, ICPR 2018.  (CCF C类会议)

156.   Mengchao He, Yuliang Li2, Zhibo Yang, Sheng Zhang, Canjie Luo, Feiyu Gao, Qi Zheng, Yongpan Wang, Xin Zhang and Lianwen Jin ICPR2018 Contest on Robust Reading for Multi-Type Web Imagespp7-13, ICPR 2018.  (CCF C类会议)

157.   Manfei Liu, Zecheng Xie, YaoXiong Huang, Lianwen Jin*, Weiyin Zhou, Distilling GRU with Data Augmentation for Unconstrained Handwritten Text Recognition, pp56-61, ICFHR 2018.

158.   Yafeng Yang, Kaihuan Liang, Xuefeng Xiao, Zecheng Xie, Lianwen Jin*, Jun Sun, Weiying Zhou, Accelerating and Compressing LSTM Based Model for Online Handwritten Chinese Character Recognition, pp110-115, ICFHR 2018.

159.   Songxuan Lai, Lianwen Jin, Learning Discriminative Feature Hierarchies for Off-Line Signature Verification, pp175-180, ICFHR 2018.

160.   Hailin Yang, Lianwen Jin*, Jifeng Sun, Recognition of Chinese Text in Historical Documents with Page-Level Annotations, pp199-204, ICFHR 2018.

161.   Zhe Li, Lianwen Jin, Songxuan Lai, Rotation-Free Online Handwritten Chinese Character Recognition using Two-Stage Convolutional Neural Network, pp205-210, ICFHR 2018.

162.   Yaoxiong Huang, Zecheng Xie, Manfei Liu, Shuaitao Zhang, and Lianwen Jin, Deep Word Association: A Flexible Chinese Word Association Method with Iterative Attention MechanismPRCV 2018. Lecture Notes in Computer Science, vol 11258. Springer

163.   Qingxiang Lin, Lingyu Liang, Yaoxiong Huang, and Lianwen Jin, Learning to Generate Realistic Scene Chinese Character Images by Multitask Coupled GAN, PRCV 2018. Lecture Notes in Computer Science, vol 11258. Springer.

 

 

2017

Journal papers:

164.   Pengwei Wang  Tianyong Hao  Jun Yan  Lianwen Jin, Largescale extraction of drug–disease pairs from the medical literature, JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY, 68(11):2649–2661, 2017 (SCI IF=2.687, JCR Q1

165.   Lingyu Liang, Lianwen Jin and Deng Liu, Edge-Aware Label Propagation for Mobile Facial Enhancement on the Cloud. IEEE Transactions on Circuits and Systems for Video Technology. 2016.SCI IF=4.685, JCR Q1区,中科院二区

166.   Xuefeng Xiao, Lianwen Jin*, Yafeng Yang, Weixin Yang, Jun Sun, Tianhai Chang, Building Fast and Compact Convolutional Neural Networks for Offline Handwritten Chinese Character Recognition, Pattern Recognition, vo. 72, no. 12, pp 72-81, 2017SCI IF=7.740, JCR Q1区,中科院二区,Top期刊

167.   Songxuan Lai, Lianwen Jin*, Weixin Yang, Toward high-performance online HCCR: a CNN approach with DropDistortion, path signature and spatial stochastic max-pooling, Pattern Recognition Letters, DOI information: 10.1016/j.patrec.2017.02.011, 2017. (SCI IF=3.756, JCR Q1区)

168.   Yuliang Liu, Lianwen Jin*, Songxuan Lai, Automatic Labeling of Large Amounts of Handwritten Characters with Gate-guided Dynamic Deep Learning, Pattern Recognition Letters (2017), doi: 10.1016/j.patrec.2017.09.042 Pattern Recognition Letters, DOI information: 10.1016/j.patrec.2017.02.011, 2017. (SCI IF=3.756, JCR Q1区)

169.   Feng Ziyong, Yang Zhaoyang, Jin Lianwen, Huang Shuangping*, Sun Jun, Robust shared feature learning for script and handwritten/machine-printed identification, Pattern Recognition Letters,  100 (12): 6-13, 2017. (SCI IF=3.756, JCR Q1区)

 

Conference papers:

170.   Yuliang Liu, Lianwen Jin*, Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection, CVPR 2017. (CCF A类会议)

171.   Zhaoyang Yang, Kathryn Merrick, Hussein Abbass, Lianwen JinMulti-Task Deep Reinforcement Learning for Continuous Action Control, IJCAI 2017. (CCF A类会议)

172.   Pengwei Wang, Zhongyuan Wang, Lei Ji, Jun Yan, Lianwen Jin, Can Machines Intelligently Propose Novel and Reasonable Scientific Hypotheses, WWW 2017, (CCF B类会议)

173.   Zhuoyao Zhong, Lianwen Jin*, Shuangping Huang, DeepText: A New Approach for Text Proposal Generation and Text Detection in Natural Images, ICASSP 2017. (CCF B类会议)

174.   Jie Xu, Linyu Liang, Lianwen Jin*, Huiyun Mao, Facial Attractiveness Prediction using Psychologically Inspired Convolutional Neural Networks (PI-CNN), ICASSP 2017. (CCF B类会议)

175.   Pengwei Wang, Yong Zhang, Jie Li, Jun Yan, Lianwen Jin,  Concept Embedded Convolutional Semantic Model for Question Retrieval, Proceedings of the Tenth ACM International Conference on Web Search and Data Mining WSDM 2017. (CCF B类会议)

176.   Lingyu Lianwen, Duorui Xie, Lianwen Jin, et al, region-aware scattering convolution networks for facial beauty prediction, IEEE ICIP 2017. (CCF C类会议)

177.   Zhaoyang Yang, Lianwen Jin, et al, Identifying Machine-Printed and Handwritten Texts using DropRegion and Deep Convolutional Network, ICDAR 2017. (CCF C类会议)

178.   Xuefeng Xiao, Yafeng Yang, Tasweer Ahmad, Lianwen Jin, Tianhai Chang, Design of a Very Compact CNN Classifier for Online Handwritten Chinese Character Recognition Using DropWeight and Global Pooling, ICDAR 2017. (CCF C类会议)

179.   Kaihuan Liang, Lianwen Jin, et al, A Comprehensive Analysis of Misclassified Handwritten Chinese Character Samples by Incorporating Human Recognition,  ICDAR 2017. (CCF C类会议)

180.   Manfei Liu, Lianwen Jin, Zecheng Xie, PS-LSTM- Capturing Essential Sequential Online Information with Path Signature and LSTM for Writer Identification, ICDAR 2017. (CCF C类会议)

181.   Songxuan Lai, Lianwen Jin, Weixin Yang,   Online Signature Verification using Recurrent Neural Network and Length-normalized Path Signature Descriptor, ICDAR 2017. (CCF C类会议)

182.   Wenbin Wu, Chenyang Li, Zhuo Chen, Xin Zhang, Lianwen Jin,  YOLSE- Egocentric Fingertip Detection From Single RGB Images, ICCV 2017 HAND workshop, 2017. (Best paper award, 最佳论文奖)

183.   Chenyang Li, Zhuo Chen, Xin Zhang, Lianwen Jin, LPSNet- A Novel Log Path Signature Feature based Hand Gesture Recognition, ICCV 2017 HAND workshop, 2017.

 

2016

Journal papers:

184.   Weixin Yang, Lianwen Jin and Manfei Liu, Deepwriterid: An End-to-End Online Text-Independent Writer Identification System. IEEE Intelligent Systems. 31: 45-53, 2016. (SCI IF=3.405, JCR Q1区)

185.   Weixin Yang, Lianwen Jin, Dacheng Tao, Zecheng Xie, Ziyong Feng, DropSample: A New Training Method to Enhance Deep Convolutional Neural Networks for Large-Scale Unconstrained Handwritten Chinese Character Recognition, Pattern Recognition, 2016. SCI IF=7.740, JCR Q1区,中科院二区,Top期刊

186.   Shuye Zhang, Lianwen Jin and Liang Lin, Discovering Similar Chinese Characters in Online Handwriting with Deep Convolutional Neural Networks. International Journal on Document Analysis and Recognition (IJDAR). 1-16, 2016. (SCI IF=2.085, JCR Q2区)

187.   Dapeng Tao, Lianwen Jin, Yuan Yuan and Yang Xue, Ensemble Manifold Rank Preserving for Acceleration-Based Human Activity Recognition. IEEE Transactions on Neural Networks and Learning Systems. 27: 1392-1404, 2016. SCI IF=10.451, JCR Q1区,中科院一区,Top期刊

188.   Dapeng Tao, Xu Lin, Lianwen Jin and Xuelong Li, Principal Component 2-D Long Short-Term Memory for Font Recognition on Single Chinese Characters. IEEE Transactions on Cybernetics. 46: 756-765, 2016. SCI IF=11.448, JCR Q1区,中科院区,Top期刊

 

Conference papers:

189.   Shuye Zhang1, Mude Lin, Tianshui Chen, Lianwen Jin, Liang Lin, CHARACTER PROPOSAL NETWORK FOR ROBUST TEXT EXTRACTIO, ICASSP 2016. (CCF B 类会议)

190.   Ziyong Feng, Zenghui Sun, Lianwen Jin, LEARNING DEEP NEURAL NETWORK USING MAX-MARGIN MINIMUM CLASSIFICATION ERROR, ICASSP 2016. (CCF B 类会议)

191.   Chengcheng Wang, Harold Mouchere, Christian Viard-Gaudin, Lianwen Jin, Combined Segmentation and Recognition of Online Handwritten Diagrams with High Order Markov Random Field, pp 252-257, Shenzhen, Guangdong, China, October 23-26, ICFHR 2016.

192.   Zenghui Sun, Lianwen Jin, Zecheng Xie, Ziyong Feng, Shuye Zhang, Convolutional Multi-directional Recurrent Network for Offline Handwritten Text Recognition, pp 240-245, Shenzhen, Guangdong, China, October 23-26, ICFHR 2016.

193.   Zhuoyao Zhong, Weishen Pan, Lianwen Jin, Harold Mouchère, Christian Viard-Gaudin, SpottingNet: Learning the Similarity of Word Images with Convolutional Neural Network for Word Spotting in Handwritten Historical Documents, pp 295-300, ICFHR 2016.

194.   Fan Yang, Lianwen Jin, Weixin Yang, Ziyong Feng, Shuye Zhang, Handwritten/Printed Receipt Classification using Attention-Based Convolutional Neural Network, pp 384-389, Shenzhen, Guangdong, China, October 23-26, ICFHR 2016.

195.   Zecheng Xie, Zenghui Sun, Lianwen Jin, Ziyong Feng, Shuye Zhang, Fully Convolutional Recurrent Network for Handwritten Chinese Text Recognition, pp 4000-4005, Cancun, Mexico, December 4 - 8, ICPR 2016. (CCF C类会议)

196.   Weixin Yang, Lianwen Jin, Hao Ni, Terry Lyons, Rotation-free Onine Handwritten Character Recognition using Dyadic Path Signature Features, Handging Normalization, and Deep Neural Network, pp 4072-4077, Cancun, Mexico, December 4 - 8, ICPR 2016. (CCF C类会议)

197.   Xiaorui Liu, Yichao Huang, Xin Zhang , Lianwen Jin, Fingertip in the Eye: An Attention-Based Method for Real-Time Hand Tracking and Fingertip Detection in Egocentric Videos, Volume 662 of the series Communications in Computer and Information Science, pp 145-154.

198.   Yichao Huang, Xiaorui Liu, Xin Zhang, Lianwen Jin, A Pointing Gesture Based Egocentric Interaction System: Dataset, Approach and Application, CVPR Workshop, 2016.

199.   Pengwei Wang, Jie Li, Jun Yan, Lianwen Jin, W.Y. Ma, Learning to Extract Conditional Knowledge for Question Answering using Dialogue, pp 277-286, Indianapolis, Indiana, USA, October 24 - 28, CIKM 2016. (CCF B类会议)

 

2015

Journal papers:

200.   Lingyu Liang, Lianwen Jin*, Xin Zhang and Yong Xu*, Multiple Facial Image Editing Using Edge–Aware PDE Learning Computer Graphics Forum 34(7): 203–212, 2015. (SCI IF=2.078, JCR Q1区)

201.   Shuangping Huang, Lianwen Jin+, Kunnan Xue, Yuan Fang, Online Primal-dual Learning for a Data-dependent Multi-kernel Combination Model with Multi-class Visual Categorization Applications, Information Science, doi:10.1016/j.ins.2015.05.009, 2015.SCI IF=6.795, JCR Q1区,中科院二区,Top期刊

202.   Shuangping Huang, Lianwen Jin, Online Multi-kernel Learning Based on a Triple Norm Regularizer for Semantic Image Classification, Mathematical Problems in Engineering, 2015. (SCI IF=1.305, JCR Q2区)

203.   Ziyong Feng, Lianwen Jin+, et.al, DLANet: A Manifold-Learning-based Discriminative Feature Learning Network for Scene Classification, Neurocomputing, doi:10.1016/j.neucom.2015.01.043, online on Feb.3, 2015.SCI IF=5.719, JCR Q1区,中科院二区,Top期刊

204.   Feibin Yanga, Qinghua Huang, Lianwen Jin, Alan Wee-Chung Liew, Segmentation and recognition of multi-model photo event, NeuroComputing, 172(8):159-167, 2015.SCI IF=5.719, JCR Q1区,中科院二区,Top期刊

205.   Dapeng Tao, Lianwen Jin, Y. Wang, X. Li, Person Re-Identification by Minimum Classification Error-Based KISS Metric Learning, IEEE Transactions on Cybernetics, 45 (2), 242-252, 2015. SCI IF=11.448, JCR Q1区,中科院一区,Top期刊

 

Conference papers:

206.   Zhuoyao Zhong, Lianwen Jin and Ziyong Feng, Multi-font Printed Chinese Character Recognition using Multi-pooling Convolutional Neural Network, ICDAR 2015. CCF C类会议)

207.   Weixin Yang, Lianwen Jin and Manfei Liu, Chinese Character-level Writer Identification using Path Signature Feature, DropStroke, and Deep CNN, ICDAR 2015. CCF C类会议)

208.   Weixin Yang, Lianwen Jin, Zecheng Xie and Ziyong Feng, Improved Deep Convolutional Neural Network For online Handwritten Chinese Character Recognition using Domain-Specific Knowledge, ICDAR 2015. CCF C类会议)

209.   Zhuoyao Zhong, Lianwen Jin and Zecheng Xie, High Performance Offline Handwritten Chinese Character Recognition Using GoogLeNet and Directional Feature Maps, ICDAR 2015.CCF C类会议)

210.   Liquan Qiu, Lianwen Jin, Ruifen Dai, Yuxiang Zhang and Lei Li, An Open SourceTesting Tool for Evaluating Handwriting Input Methods, ICDAR 2015. CCF C类会议)

211.   Meijun He, Shuye Zhang, Huiyun Mao and Lianwen Jin, Recognition Confidence Analysis of Handwritten Chinese Character with CNN, ICDAR 2015. CCF C类会议)

212.   Duorui Xie, Lingyu Liang, Lianwen Jin, Jie Xu, Mengru Li, SCUT-FBP-A Benchmark Dataset for Facial Beauty Perception, IEEE SMC 2015

213.   Yichao Huang, Xiaorui Liu, Lianwen Jin, Xin Zhang, DeepFinger: A Cascade Convolutional Neuron Network Approach to Finger Key Point Detection in Egocentric Vision with Mobile Camera, IEEE SMC 2015

214.   Lingyu Liang, Deng Liu and Lianwen Jin, FaceMore: A Face Beautification Algorithm Platform on the Cloud, IEEE SMC 2015

 

2014

Journal papers:

215.   Lingyu Liang, Lianwen Jin, Xuelong Li, Facial Skin Beautification Using Adaptive Region-Aware Masks, IEEE Transactions on Cybernetics,, vol.44, no.12, pp2600 – 2612, 2014.SCI IF=11.448JCR Q1区,中科院一区,Top期刊

216.   Dapeng Tao, L. Jin et al. “Rank Preserving Discriminant Analysis for Human Behavior Recognition on Wireless Sensor Networks,” IEEE Transactions on Industrial Informatics, vol.10, no.1, pp813-823, 2014.SCI IF=10.215JCR Q1区,中科院一区,Top期刊

217.  Dapeng Tao, Lianwen Jin, Shuye Zhang, Zhao Yang, Yongfei Wang, Sparse Discriminative Information Preservation for Chinese Character Font Categorization, NeuroComputing129pp 159-167, 2014.SCI IF=5.719JCR Q1区,中科院二区,Top期刊

218.  Dapeng Tao, Lianwen Jin, Similar Handwritten Chinese Character Recognition by Kernel Discriminative Locality Alignment, Pattern Recognition Lettersvol.35, no.1, pp186-194, 2014. (SCI IF=3.756, JCR Q1区)

219.   杨钊,金连文,陶大鹏,大数据下的基于深度神经网的相似汉字识别,《通信学报》,2014

220.   Qinghua Huang; Xiao Bai; Yingguang Li; Lianwen Jin; Xuelong LiOptimized graph-based segmentation for ultrasound imagesNeurocomputing, 2014SCI IF=5.719JCR Q1区,中科院二区,Top期刊

 

2013

Journal papers:

221.  Xin Zhang, Zhichao Ye , Lianwen Jin, Ziyong Feng, A New Writing Experience: Finger Writing in the Air Using a Kinect Sensor, IEEE Multimedia, 20(4), pp85-93, 2013. SCI IF=5.633JCR Q1区,中科院二区

222.  Lingyu Liang, Lianwen Jin*, A New Face Relighting Method Based on Edge-Preserving FilterIEICE TRANSACTIONS on Information and Systems Vol.E96-D, No.12,pp. 2904-2907, 2013.SCI IF=0.559

223.  Huang, Shuangping, Lianwen Jin*, Yuan Fang, Xiaoxin Wei. "Online Heterogeneous Feature Fusion Machines for Visual Recognition." Neurocomputing (2013), online on July 2, 2013.SCI IF=5.719JCR Q1区,中科院二区,Top期刊

224.  D. Tao, L. Jin, Z. Yang, and X. Li, “Rank Preserving Sparse Learning for Kinect based Scene Classification,” IEEE Transactions on Cybernetic, vol. 43, no. 5, pp. 1406-1417, 2013. SCI JCR分区1区)SCI IF=11.448JCR Q1区,中科院一区,Top期刊

225.  Dapeng Tao, Lianwen Jin, Yongfei Wang, Yuan Yuan, and Xuelong Li, Person Re-Identification by Regularized Smoothing KISS Metric Learning, IEEE Transactions On Circuits and Systems for Video Technology, vol.23, no.10, pp1675-1685, 2013.SCI IF=4.685JCR Q1区,中科院二区,Top期刊

226.   D. Tao, L. Jin, W. Liu, and X. Li., “Hessian Regularized Support Vector Machines for Mobile Image Annotation on the Cloud,” IEEE Transactions on Multimedia, vol. 15no. 4, pp. 833-844, 2013.SCI IF=6.513JCR Q1区,中科院二区,Top期刊

227.   Qinghua Huang, Zhao Yang, Wei Hu, Lianwen Jin, Gang Wei, Linear tracking for 3-D medical ultrasound imaging, IEEE transactions on Cybernetics, vol.43, no.6, pp.1747-1754, 2013.SCI IF=11.448JCR Q1区,中科院一区,Top期刊

 

Conference papers:

228.   Zhichao Ye, Xin Zhang, Lianwen Jin, Ziyong Feng, Shaojie Xu, FINGER-WRITING-IN-THE-AIR SYSTEM USING KINECT SENSOR, in Proc. IEEE ICME 2013CCF B类会议)

229.   Shuye Zhang, Lianwen Jin+, Dapeng Tao, Zhao YangA faster method for Chinese font recognition based on Harris cornerin Proc. IEEE SMC 2013

230.   Linyu Liang, Lianwen Jin, Image-Based Rendering for Ink Painting, in Proc. IEEE SMC 2013.

231.   Linyu Liang, Lianwen Jin, Facial Skin Beautification using Region-Aware Mask, in Proc. IEEE SMC 2013.

232.   Yan Gao, Lianwen Jin, Weixin Yang, An Empirical Comparative Study of Online Handwriting Chinese Character Recognition, ICDAR 2013.CCF C类会议)

 

2012

Journal papers:

233.   Dapeng Tao, Lianwen Jin, Discriminative Information Preservation for Face Recognition, Neurocomputing . 91: 11-20 , 2012.SCI IF=5.719JCR Q1区,中科院二区,Top期刊

234.    Xue Gao, Jinzhi Guo, Lianwen Jin, Dimensionality Reduction by Locally Linear Discriminant Analysis for Handwritten Chinese Character Recognition, IEICE TRANSACTIONS on Information and Systems  Vol.E95-D  No.10  pp.2533-2543. (SCI IF=0.559

235.  Nanxi Li, Lianwen Jin, A Bayesian-based method of unconstrained handwritten offline Chinese text line recognitionInternational Journal on Document Analysis and Recognition, 2012. (SCI IF=2.085

236.   Li, X.T.  Fan, L.S.  Jin LianwenLi, X.T.  Fan, L.S.  Jin Lianwen Analytical density function of sum of Gaussian noise and SαS interferenceElectronics Letters, 281: 47 - 482012. (SCI IF=1.314

237.   Zheng SH, Huang QH*, Jin LW, and Wei G. Real-time Extended-Field-of-View ultrasound based on a standard PC. Applied Acoustics. 73 (4): 423-432, 2012. (SCI IF=2.639

238.   Qinghua Huang, Suying Lee, Longzhong Liu, Minhua Lu, Lianwen Jin and Anhua LiA Robust Graph-Based Segmentation Method for Breast Tumors in Ultrasound ImagesUltrasonics522):266-2752012. (SCI IF=2.890

239.   Xue Gao, Lianwen Jin, A Vision-based Fast Chinese Postal Envelope Identification System, Journal of Information Science and Engineering, 28(1):31-49, 2012.(SCI IF=0.440

 

Conference papers:

240.   Lianwen Jin, Yang Xue, Huiyun Mao, Hengzhi Zhang A new weightlessness-like based fall detection algorithm for a single tri-axial accelerometers, ICPR 2012.CCF C类会议)

241.   Yan Gao, Huiyun Mao, Lianwen Jin, Nanxi Li, Reduce the Storage of Incremental MQDF Classifier for Chinese Writer Adaptation, ICPR 2012.CCF C类会议)

 

2011

Journal papers:

242.  Qinghua Huang, Dacheng Tao, Xuelong Li, Lianwen Jin, Exploiting Local Coherent Patterns for Unsupervised Feature Ranking, IEEE Transactions on Systems, Man, and Cybernetics, vol.41, no.12, pp.1471-1482, 2011.

243.   Yang Xue, Lianwen Jin, Discrimination between Upstairs and Downstairs based on  Accelerometer, IEICE TRANSACTIONS on Information and Systems, Vol.E94-D,No.6,pp1173-1177, 2011. (SCI IF=0.559

244.   Lihua Guo, Lianwen Jin, Laplacian Support vector machines with multi-kernel learning, IEICE TRANSACTIONS on Information and Systems, vol. E94-D, no.2, pp379-383, 2011. (SCI IF=0.559

245.  Lianwen Jin, Yan Gao, et.al,  SCUT-COUCH2009----A Comprehensive Online Unconstrained Chinese Handwriting Database andenchmark Evaluation, International Journal on Document Analysis and Recognition (IJDAR), (SCI IF=1.21) vol.14, no.1, pp53-64, 2011. (SCI IF=2.085

246.  Qinghua Huang , Suying Lee, Longzhong Liu, Minhua Lu, Lianwen Jin, Anhua Li, A robust graph-based segmentation method for breast tumors in ultrasound  images, Ultrasonics, 2011. (SCI IF=2.890

 

Conference papers:

247.   Kai Ding, Lianwen Jin, Gang Liu, Jinglian Gao, Zhonghao Mei, Incremental learning of MQDF for writer adaptation, ICIC Express Letters, Part B: Applications (ICIC-ELB)vol.2, no.1, pp25-30, 2011 (EI源刊)

248.   Shuangping Huang, Lianwen JinA New Multi-Label Scene Categorization Method Using Color Incorporated Biologically Inspired Features and MIML SVMICIC Express Letters, Part B: Applications (ICIC-ELB), vol.2, no.2, pp287-293, 2011 (EI源刊)

249.   薛洋,金连文, 一种基于加速度传感器的书写识别旋转特征提取方法, 模式识别与人工智能vol.24, no.4, pp492-500, 2011. EI源刊)

250.   Xue Gao, Jinzhi Guo, and Lianwen Jin , A New Feature Optimization Method Based on Two-directional 2DLDA For Handwritten Chinese Character Recognition, pp232-236, ICDAR 2011. CCF C类会议)

251.   Dapeng Tao, Linyu Liang, Lianwen Jin, Yan Gao, Similar Handwritten Chinese Character Recognition using Discriminative Locality Alignment Manifold Learning, ICDAR 2011 CCF C类会议)

252.   Yan Gao, Lianwen Jin, Cong He, Guibin Zhou,  Handwriting Character Recognition as a ServiceA New Handwriting Recognition System Based on Cloud Computing,  pp885-889, ICDAR 2011 CCF C类会议)

253.   Shuangping Huang, Lianwen Jin, Online Heterogeneous Feature Fusion Machine for Visual Recognition, ICDM Workshop on LSVA, Dec.2011

 

Before 2010

Journal papers:

254.   Lianwen JinKai Ding, Zhibin Huang, Incremental Linear Discriminant Analysis for Writer-Adaptive Online Chinese Handwriting Recognition, Neurocomputing, 73(10):1614-1623, 2010.SCI IF=5.719JCR Q1区,中科院二区,Top期刊

255.   毛慧芸,金连文,杜明辉,基于几何特征及C4.5的人脸美丽分类方法,模式识别与人工智能vol.23, no.6, pp809-814, 2010.

256.  Teng Long, Lianwen JIN, Building Compact MQDF Classifier for Large Character Set Recognition by Subspace Distribution Sharing, Pattern Recognition (2008 SCI Impact Factor 3.279), vol.41, no.9, pp2916-2926, 2008.SCI IF=7.740JCR Q1区,中科院二区,Top期刊

257.  X.T. LI, J. SUN, L.W. JIN and M. LIU. Bi-parameter CGM model for approximation of α-stable PDF. Electronics Letters, Vol.44, Issue 18, August 2008, pp.1096-1097. (SCI, IF=1.01) SCI IF=1.314

258.  李旭涛,王首勇,金连文. 应用Alpha稳定分布对雷达杂波的辨识. 电子与信息学报 200830(9) :2042-2045. (EI: 084111636418)

259.   Lianwen Jin, Duanduan Yang, Li-Xin Zhen, Jian-Cheng Huang, A Novel Vision based Finger-writing Character Recognition System, Journal of Circuit, System and Computer. Vol.16, no.3, pp421-436.

260.   Lianwen JIN  CaiHong CHEN, Li-Xin ZHEN, Jian-Cheng HUANG, Real-Time Fingertip Detection From Cluttered Background for Vision-based HCI, Journal of Communication and Computer, vol.2, no.9, pp1-8, 2005.

261.   Hong-Bo Deng, Lian-Wen Jin, Li-Xin Zheng, Jian-Cheng Huang, A New Facial Expression Recognition Method Based on Local Gabor Filter Bank and PCA plus LDA, International Journal of Information Technology. Vol.11, no.11. pp86-96, 2005..

262.   Duan-Duan Yang, Lian-Wen JIN, Facial Expression Recognition with Pyramid Gabor Features and Complete Kernel Fisher Linear Discriminant AnalysisInternational Journal of Information Technology, vol.11, no.9, pp91-100,  2005.

263.   高学,徐睿, 金连文, 尹俊勋, 镇立新, 一种基于运动图像的在线手写汉字识别方法, 《电子学报》vol.32, no.8, pp1273-1276, 2004.

264.   金连文,秦剑钊,基于Gabor方向特征及神经网络的车牌字符图像识别,《中国图像图形学报》Vol. 8Spec.,: 643-646, 2003

265.   高学, 金连文,尹俊勋,基于多通道PCA模型的手写汉字识别方法,《中国图像图形学报》Vol.8, No7, pp.788-791, 2003

266.   金连文,黄建成,尹俊勋,变形变换及其在手写体汉字整形中的应用,《中国图像图形学报》Vol.7, No.2, pp.170-175, 2002

267.   高学,金连文,尹俊勋,黄建成,一种基于支持向量机的手写汉字识别方法,《电子学报》vol.30, no.5, pp6516542002年第5期。

268.   高学, 金连文,尹俊勋,基于笔划密度的弹性网格特征提取方法《模式识别与人工智能》vol.15, no.3,  pp.351-354, 2002年。

269.   Lianwen JIN, Gang Wei, “Handwritten Chinese Character Recognition with Directional Decomposition Cellular Features”, Journal of Circuits, Systems, and Computers, Vol.8, No.4, pp.517-524, 1999.SCI IF=1.333

270.   金连文, 徐秉铮,“限定性手写体汉字识别的一种可变形弹性匹配模型”, 《电子学报》vol.25, no.5, pp35-38, 1997年。

271.   金连文, 徐秉铮,“基于多级神经网络结构的手写体汉字识别《通信学报》vol.18no.5, pp21-27, 1997

 

Conference papers:

272.   Shuangping Huang, Lianwen Jin, ENHANCED VISUAL CATEGORIZATION PERFORMANCES BY INCORPORATION OF SIMPLE FEATURES INTO BIM FEATURES, ICIP 2010

273.   Hanyu Yan, Lianwen Jin,      Christian Viard-Gaudin, Harold Mouchère,SCUT-COUCH2009-TL: An Unconstrained Online Handwritten Chinese Text Lines Dataset, ICFHR 2010.

274.   Gang Liu, Lianwen Jin, Kai Ding, Hanyu Yan, A new approach for synthesis and recognition of large scale handwritten Chinese words, ICFHR 2010

275.   Kaiding, Lianwen Jin, Incremental MQDF Learning for Writer Adaptive Handwriting Recognition, ICFHR 2010.

276.   ang Bai, Lihua Guo, Lianwen Jin, Qinghua Huang, A NOVEL FEATURE EXTRACTION METHOD USING PYRAMID HISTOGRAM OF ORIENTATION GRADIENTS FOR SMILE RECOGNITION, IEEE ICIP , 2009 CCF C类会议)

277.   Zhibin Huang, Kai Ding, Lianwen Jin, Xue Gao, Writer Adaptive Online Handwriting Recognition Using Incremental Linear Discriminant Analysis, pp91-95, ICDAR 2009. CCF C类会议)

278.    Kai Ding, Guoqiang Deng, Lianwen Jin, An Investigation of Imaginary Stroke Technique for Cursive Online Handwriting Chinese Character Recognition, pp531-535, ICDAR 2009CCF C类会议)

279.   Zhiyi Zhang, Lianwen Jin, Kai Ding, Xue Gao, Character-SIFT: a novel feature for offline handwritten Chinese character recognition, pp763-767, ICDAR 2009CCF C类会议)

280.   Weiping Xia, Lianwen JinA Kai Style Calligraphic Beautification Method for Handwriting Chinese Character,pp798-802, ICDAR 2009CCF C类会议)

281.   Shengming Huang, Lianwen Jin, Jin Lv, A Novel Approach for Orienta- tion Free Chinese Character Recognition, pp1136-1140, ICDAR 2009CCF C类会议)

282.   Kai Ding, Lianwen Jin, Xue Gao, A New Method for Rotation Free Online Unconstrained Handwritten Chinese Word Recognition A Holistic Approach, International Conference on Document Analysis and Recognition, pp1131-1135, ICDAR 2009CCF C类会议)

283.   Liu ZhiBin, Jin Lianwen, LatticeSVM---A New method for Multi-class support Vector Machines, Proceedings of IEEE IJCNN,vol.1, pp727-733, Hongkong, 2008.6. CCF C类会议)

284.   Teng Long, Lianwen Jin, A Novel Orientation Free Method for Online Unconstrained Cursive Handwritten Chinese Word Recognition, ICPR, Dec. 2008. CCF C类会议)

285.   Xinghua Zhu, Lianwen Jin, Calligraphic Beautification of Handwritten Chinese Characters: A Patternized Approach to Handwriting Transfiguration, in Proceedings of International Conference on Frontier on Handwriting Recognition (ICFHR2008), Aug. 2008-10-25 (EI)

286.   YunYang Li, Lianwen Jin, Xinhua Zhu, Teng Long, SCUT-COUCH2008: A Comprehensive Online Unconstrained Chinese Handwriting Dataset, in Proceedings of International Conference on Frontier on Handwriting Recognition (ICFHR2008) (EI)

287.   Zhenyu He, Zhibin Liu, Lianwen Jin, Weightlessness Feature — A Novel Feature for Single Tri-axial Accelerometer, ICPR 2008, Dec.2008.CCF C类会议)

288.   DangDang YANG, Lianwen JIN, Kernel Modified Quadratic Discriminant Function for Online Handwritten Chinese Characters Recognition, ICDAR 2007 CCF C类会议)

289.   Teng Long, Lianwen JIN, Building Compact MQDF Classifier for Off-line Handwritten Chinese Characters by Subspace Distribution Sharing, ICDAR 2007CCF C类会议)

290.   DangDang YANG, Lianwen JIN, Handwritten Chinese Character Recognition Using Modified LDA and Kernel FDA, ICDAR 2007CCF C类会议)

291.   Lianwen JIN, XiaoNa ZU, Synthesis of Chinese Character sing Affine Transformation, ICDAR 2007CCF C类会议)

292.   DangDang YANG, Lianwen JIN, Li-Xin Zhen, Jian-Cheng Huang l, Finger-Written Chinese Characters Rcognition using Hierarchical LDA, ICDAR 2007CCF C类会议)

293.   Lianwen Jin, Duanduan Yang, Li-Xin Zhen, Jian-Cheng Huang,  A Novel Vision based Finger-writing Character Recognition System, ICPR 2006CCF C类会议)

294.   Teng LON G, Lianwen Jin, Li-Xin Zheng, Jian-Cheng Huang, ONE STROKE CURSIVE CHARACTER RECOGNITION USING COMBINATION OF DIRECTIONAL AND POSITIONAL FEATURES,  ICASSP 2005. CCF B类会议)

295.   Teng LONG, Lianwen Jin, Hybrid Recognition of One Stroke Style Cursive Handwriting Characters, ICDAR 2005. CCF C类会议)

296.   Xue Gao, Lian-Wen Jin, Jun-Xun Yin, Jian-Cheng HuangA New Stroke-Based Directional Feature Extraction Approach for Handwritten Chinese Character Recognition, ICDAR 2001. CCF C类会议)

 

备注:期刊的影响因子采用最新数据或JCR 2021/2022年的数据.

 

获奖情况

1.   金连文(排名第1),手写人机交互核心技术及云应用,广东省科技进步一等奖,获奖编号:B07-0-1-01-D01 2012.3.27

2.   金连文(排名第2),交互式智慧课堂关键技术及应用,吴文俊人工智能科技进步二等奖,中国人工智能学会,2020年。

3.   金连文(排名第3),数字媒体云服务平台创新及应用,广东省科技进步二等奖,广东省人民政府,2018.2

4.   金连文(排名第5),智慧银行设备安全可控关键技术应用,广东省科技进步二等奖,2017.01.24(获奖编号:B07-2-02-D03)

5.   金连文(排名第4),多模态信号建模、传输及识别新方法,教育部提名国家科技进步奖,2006.1.26.

6.   金连文(排名第5),动力学系统反馈设计与辩识的智能与优化方法,证书编号:A01-1-01-R05 52007.7

7.   2016 CVPR VIVA HAND国际学术比赛第一名(举办地:美国)

8.   2017ICCV HAND Workshop Best Paper Award (地点:意大利)

9.   2017.11.20,  ICDAR 2017 MLT多语言文字检测国际竞赛(ICDAR-MLT Task 1)第一名(举办地:日本)

10.  2017.11.20,  ICDAR 2017 MLT多语言端到端文字检测及语种分类竞赛(ICDAR-MLT Task 3)第一名(举办地:日本)

11.  2018.8.8:  ICFHR 2018 泰国学生签名与姓名识别与认证竞赛(Thai Student Signature and Name Component Recognition and Verification)手写签名竞赛第一名 (举办地:美国)

12.  2019.9.21 ICDAR 2019 古籍文档检索竞赛(ICDAR-HDRC-IR)第一名(举办地:澳大利亚)

13.  2019.9.21ICDAR 2019古籍中文文本行识别竞赛(ICDAR-HDRC-Chinese Task1)第一名 (举办地:澳大利亚)

14.  2019.9.21ICDAR 2019 古籍中文版面分析竞赛(ICDAR-HDRC-Chinese Task2)第一名(举办地:澳大利亚)

15.  2019.9.21ICDAR 2019古籍中文端到端文字检测与识别竞赛(ICDAR-HDRC-Chinese Task3)第一名(举办地:澳大利亚)

16.  2019.9.21ICDAR 2019街景招牌文字检测竞赛 (ICDAR-ReCTS Task2) 第一名(举办地:澳大利亚)

17.  2019.9.21ICDAR 2019街景招牌文字识别竞赛 (ICDAR-ReCTS Task3) 第一名(举办地:澳大利亚)

18.  2019.9.21ICDAR 2019 扫描票据文字检测(ICDAR-SROIE Task 2)第一名(举办地:澳大利亚)

19.  2017.11.20,  ICDAR 2017 MLT多语言语种分类竞赛(ICDAR-MLT Task 2)第二名(举办地:日本)

20.  2019.9.21ICDAR 2019街景招牌文字端到端检测与识别竞赛 (ICDAR-ReCTS Task4) 第二名 (举办地:澳大利亚)

21.  2019.9.21ICDAR 2019 扫描票据文字检测(ICDAR-SROIE Task 1)第二名(举办地:澳大利亚)

22.  2020.9.10ICFHR 2020泰国学生签名、姓名识别与鉴别(SASIGCOM)竞赛签名识别与鉴别任务冠军(举办地:德国)

23.  2020.9.10ICFHR 2020泰国学生签名、姓名识别与鉴别(SASIGCOM)竞赛姓名识别与鉴别任务冠军(举办地:德国)

24.  2020.11.19: 罗灿杰等,“识古通今——文字识别(OCR)技术领航者”, 第六届中国国际“互联网+”大学生创新创业大赛全国金奖。指导老师:金连文。教育部、团中央、国家发改委、工信部等11个部委。

25.  2021.1ICPR-Chart-Infographics竞赛图表类型分类任务(Task12项冠军(Adobe合成数据集、UB PMC真实数据集) (注:ICPR是模式识别领域权威国际会议,下同

26.  2021.1ICPR-Chart-Infographics竞赛图片文字块的检测与识别任务(Task2) 2项冠军(Adobe合成数据集、UB PMC真实数据集)

27.  2021.1ICPR-Chart-Infographics竞赛文字属性的分类任务(Task3) 2项冠军(Adobe合成数据集、UB PMC真实数据集)

28.  2021.1ICPR-Chart-Infographics竞赛坐标轴分析任务(Task4) Adobe合成数据集冠军

29.  2021.1ICPR-Chart-Infographics竞赛图表信息提取任务(Task6) 2项冠军(Adobe合成数据集、UB PMC真实数据集)

30.  2021.1ICPR-Chart-Infographics竞赛端到端任务(End-to-end Task2项冠军(Adobe合成数据集、UB PMC真实数据集)

31.  2021.9 ICDAR 2021 Competition on On-Line Signature Verification (CDAR-2021-SVC) 联机手写签名竞赛Task1/2/3冠军

 

 

授权发明专利

1、 金连文,龙腾,“一种手写文字识别方法”,发明专利,授权号:ZL200510033175.3,申请日期:20050208,授权日期:200759

2、 金连文,陈东明,“一种含书写时序信息的动态汉字字库的处理方法及应用”,发明专利,授权号:ZL200410051504.2,申请日期:20040917,授权日期:20071212.

3、 金连文,倪天龙,龙腾,陈东明,多媒体汉字电子描红本,发明专利,授权号:ZL200410051821.4,申请日期:20050107,授权日期:2008618日。

4、 金连文,高学,张彬,何智杰,一种邮政信封自动识别系统及其识别方法,发明专利,授权号:ZL200610124242.7,申请日期:20061215,授权日期:2008.10.22

5、 金连文,高学,张彬,何智杰,一种邮政信封自动识别系统,发明专利,授权号:ZL200620154802.9,申请日期:20061215,授权日期:2008.04.30

6、 金连文,俎小娜,基于最优全局仿射变换的汉字合成实现方法;发明专利,授权号:ZL20071 0029079.0,申请日期:20070709, 授权日期:2009826日。

7、 金连文,龙腾,“具备认字、写字功能的教育机器人的文字识别方法”,发明专利,授权号:ZL200610124243.1申请日期:20061215, 授权日期:20091111日。

8、 金连文,郭锐,一种基于笔矢量特征的联机手写中文词组切分方法;专利号:ZL2008100294211,申请日期:2008.8.29;授权日期:201023日。

9、 金连文,龙腾,一种中文词组识别方法;专利号:ZL2008100290085,申请日期:2008.6.25;授权日期:201069日。

10、金连文,李旭涛,一种基于视频的人脸美丽评价方法,专利号:ZL2008100294226,申请日期:2008.7.11,授权日期:2010.06.09

11、金连文,朱星华,一种手写汉字美化方法;专利号:ZL2008100289162,申请日期:2008.8.8, 授权日期:2010.9.1

12、金连文,张志毅,丁凯,一种用于手写汉字识别的图像特征提取方法,授权号:ZL200810220334.4,申请日期:2008.12.4,  授权日期:2010.12.29.

13、金连文,丁凯,严汉羽,一种基于可见光检测的虚拟文字识别方法,授权号:ZL200810029420.7,申请日期:2008.7.11,  授权日期:2011.6.15.

14、金连文,邓国强,一种用于联机手写汉字识别的汉字笔画特征串行提取方法,授权号:ZL200910041046.7, 申请日期:2009.07.10,授权日期:2011.08.17

15、金连文,邓国强,一种用于联机手写汉字识别的汉字笔画特征提取方法,授权号:ZL200910041047.1, 申请日期:2009.07.10,授权日期:2011.08.31

16、金连文,邓国强,一种用于联机手写汉字识别的汉字笔画特征并行提取方法,授权号:ZL200910041045.2, 申请日期:2009.07.10,授权日期:2011.09.10

17、金连文,黄志斌,一种用于手写汉字识别的用户书写风格自适应方法,授权号:ZL200910042117.5, 申请日期:2009.08.25,授权日期:2011.09.14

18、金连文,高岩,一种基于置信度的汉字书写质量评价方法,授权号:ZL200910042118.X, 申请日期:2009.08.25,授权日期:2011.09.28

19、金连文,朱星华,毛慧芸,一种手写汉字美化中模拟书法拖笔效果的方法,ZL200910193478.X,授权日期:2011.11.02

20、金连文,朱星华,毛慧芸,一种手写汉字美化的骨架变换方法,申请日期:2009.10.30,授权号:ZL 200910193514.2. 授权日期:2012.02.01

21、金连文,丁凯,“一种旋转无关的手写中文草书词组识别方法”,专利号:ZL200910192675.X,证书号:, 申请日期:2009.09.25,授权日期:2012.08.22.

22、金连文,黄盛明,吕锦,一种旋转方向无关的手写汉字识别方法,专利号:ZL200910192677.9,证书号:第959439号,申请日期:2009.09.25, 授权日期:2012.05.30

23、金连文,朱星华,毛慧芸,一种基于轨迹分析的手写汉字的美化方法,专利号:ZL200910193516.1,证书号:第974577号,申请日期:2009.10.30, 授权日期:2012.06.20.

24、金连文,朱星华,毛慧芸,“一种手写汉字美化的笔画渲染方法”,专利号:ZL200910193515.7,证书号:,申请日期:2009.10.30, 授权日期:2012.09.05.

25、金连文,梁凌宇,刘志斌,何振宇,一种基于加速度传感器的失重特征提取方法,专利号:ZL201019050021.3, 证书号:第2005827号,申请日期:2010.02.02, 授权日期:2012.07.18.

26、金连文,薛洋,一种基于加速度传感器的手势识别的旋转特征提取方法,专利号:ZL201010204591.6, 证书号:第979191号,申请日期:20100618,授权日期:20120627

27、金连文,薛洋,一种基于加速度传感器的手势识别方法,专利号:ZL201010204587.X,证书号:第1028631号。申请日期:20100618,授权日期:20120822

28、金连文,薛洋,“一种应用于手势识别的旋转特征码的距离测度方法”,专利号:ZL201010204595.4,证书号:,申请日期:2010.06.18,授权日期:2012.12.26.

29、郭礼华,金连文,“一种聚类线性鉴别分析特征选择的笑脸表情识别方法”,专利号:ZL201110122941.9,证书号:,申请日期:2011.05.13,授权日期:2013.01.23.

30、金连文,刘岗,丁凯,“一种使手写汉字识别引擎能动态适应用户书写风格的方法”,专利号:ZL201110108782.7,证书号:,申请日期:2011.04.28, 授权日期:2013.03.20

31、金连文,刘岗,丁凯,“一种基于加权鉴别子空间的增量二次鉴别函数的自适应方法”,专利号:ZL201110108770.4,证书号:,申请日期:2011.04.28, 授权日期:2013.07.10.

32、黄庆华,郑硕鹤,金连文,韦岗,“一种医学超声宽景成像中的旋转判断及误差纠正方法”,专利号:ZL 201110139790.8,证书号:,申请日期:2011.05.27, 授权日期:2013.04.17.

33、金连文,刘岗,丁凯,“一种基于鉴别子空间的增量二次鉴别函数书写者自适应方法”,专利号:ZL201110108773.8,证书号:,申请日期:2011.04.28, 授权日期:2014.04.02.

34、黄庆华,郑硕鹤,金连文,韦岗,“一种医学超声宽景成像中的旋转判断及误差纠正方法”,专利号:ZL 201110139790.8,证书号:,申请日期:2011.05.27, 授权日期:2013.04.17.

35、冼启源;金连文;李天豪;麦松涛;梁康楠, 一种强扩展性的嵌入式开发板,申请日期:2011.4.28,授权日期:2014.05.07, 专利号:ZL 201110108771.9

36、丁祖春,金连文,郭礼华,一种分布式无线Ad Hoc网络认证方法,专利号:ZL 201110121144.9, 授权日期:2015.03.11

37、金连文,李磊,一种云计算弹性资源预测及构建方法,专利号:ZL 201310153762.0, 证书号:第1924541号;申请日期:2013.4.27, 授权日期:2016.1.20.

38、金连文,叶植超,张鑫,一种基于Kinect的手写方法,授权公告号:CN103226388B,专利号:ZL201310118074.0。申请日期:2013.4.7,授权公告日:2016.05.04

39、金连文,叶植超,张鑫,基于Kinect的视频手指尖定位方法,授权证书号:第2121465号 ,专利号:ZL 201310118060 .9。申请日期:2013.4.7,授权公告日:2016.06.22      

40、金连文,叶植超,张鑫,基于Kinect的视频手指尖定位方法,授权公告号:第2130659号,专利号:ZL 201310118064.7。申请日期:2013.4.7,授权公告日:2016.06.29 

41、金连文,黎德生,李磊,一种OpenStack云平台异常的处理方法,授权公告号:第2322748号,专利号:ZL 201310153700.X。申请日期:2013.4.27,授权公告日:2016.12.28

42、金连文,陶大鹏,王永飞,一种大数据图像分类方法,授权公告号:第2259246号,专利号:ZL 201310432630.1。申请日期:2013.9.22,授权公告日:2016.10.5

43、陶大鹏,金连文,黎小风,一种基于加速度计的人体行为识别方法,授权公告号:第2327764号,专利号:ZL 201310428353.7。申请日期:2013.9.18,授权公告日:2017.1.4

44、金连文, 毛慧芸; 朱武林; 廖文鑫; 张鑫,人脸特效处理方法以及系统, 申请日期:2012.11.16,专利号:ZL 2012104657672, 授权公告号:CN103824269B,授权公告日:2017.03.29

45、金连文,陶大鹏,王永飞,一种基于云计算的手机图像标注方法,申请日期:2013.09.29,专利号:ZL 201310455285.3, 授权公告日:2017.4.19

46、薛洋; 刘龙坡; 金连文,  一种基于加速度传感器的实时步长估计方法,申请日期:2014.04.29,专利号:ZL 201410179119.X, 授权公告号:CN103983273B,授权公告日:2017.06.06

47、薛洋; 胡耀全; 金连文, 一种用于人体动作识别的三轴特征融合方法,申请日期:2014.04.29,专利号:2014101791166, 授权公告号:CN103984921B,授权公告日:2017.06.06

48、薛洋; 胡耀全; 金连文, 用于运动识别的聚类特征融合方法和装置,申请日期:2014.06.12,专利号:2014102615477, 授权公告号:CN104021295B,授权公告日:2017.06.06

49、金连文; 曾伟铭; 陈露开, 一种复杂曲线的Bezier拟合方法,申请日期:2014.09.19,专利号:ZL 201410484142.X, 授权公告日:2017.08.25

50、金连文; 曾伟铭; 陈露开, 一种手写汉字的实时轮廓美化方法,申请日期:2014.09.19,专利号:ZL 201410484141.5, 授权公告号:CN104268915B,授权公告日:2017.08.25

51、金连文,郭礼华; 薛洋; 李辰成; 吴忠泽,人体运动姿态识别方法和移动终端,申请日期:2013.07.19,专利号:ZL 201310307180.3, 授权公告日:2017.11.28

52、黄双萍; 金连文; 黎小凤,一种基于改进的引导滤波器的人脸图像图层分解方法,申请日期:2015.11.30,专利号:ZL 201510862964.1, 授权公告号:CN105469407B,授权公告日:2018.06.22

53、高学; 金连文,一种基于OCR的票据自动识别与处理系统,申请日期:2016.01.31,专利号:ZL 201610070970.8, 授权公告号:CN105528604B,授权公告日:2018.12.11

 

学术兼职

²  广东省图像图形学会,理事长

²  中国图像图形学学会,常务理事

²  中国图像图形学学会文档图像分析与识别专委会,主任

²  中国计算机学会计算机视觉专委会委员

²  中国计算机学会人机交互专委会委员

²  中国人工智能学会模式识别专委会委员

²  中国图像图形学学会机器视觉专委会常务委员

²  中国自动化学会模式识别与机器智能专委会委员

²  广东省高校“音视频图文智能信息处理”工程研究中心主任