个人简介 李志欣(1971-)，博士/教授，博士生导师，广西师大“独秀学者”。中国计算机学会(China Computer Federation, CCF)杰出会员、中国人工智能学会(Chinese Association for Artificial Intelligence, CAAI)会员、电气电子工程师学会(Institute of Electrical and Electronics Engineers, IEEE)会员、美国计算机学会(Association for Computing Machinery, ACM)会员。 1992年华中理工大学自动控制工程系本科毕业；2004年华中科技大学37000Cm威尼斯硕士研究生毕业；2010年中国科学院计算技术研究所博士研究生毕业，获工学博士学位，导师为史忠植研究员。 2010年至今于广西师范大学计算机科学与工程学院任教，2015年晋升教授，2018年评为博士生导师，2020年评为广西师大“独秀学者”。 博士学位论文“图像语义标注和检索的研究”获2011年度中国人工智能学会优秀博士学位论文奖。 长期从事智能科学的研究，主要研究领域包括图像理解、机器学习、自然语言处理、跨媒体计算等。在工作和学习期间，先后主持国家自然科学基金4项（面上项目1项，地区科学基金项目3项）和广西自然科学基金3项（重点项目1项，面上项目2项），并参与了973计划、863计划及国家自然科学基金重点项目等多个项目的研究。 作为第一作者或通讯作者在国内外重要期刊和会议上发表（录用）学术论文一百余篇（SCI收录46篇、EI收录105篇），其中CCF推荐B类以上的期刊9篇、会议19篇。代表性论文发表于： －重要国际期刊：IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)、ACM Transactions on Multimedia Computing, Communications and Applications (TOMM)、Neural Networks、Machine Learning、Computer Vision and Image Understanding (CVIU)、Information Processing and Management (IPM)、Knowledge-Based Systems (KBS)、Expert Systems With Applications (ESWA)、Engineering Applications of Artificial Intelligence (EAAI)、IEEE Signal Processing Letters (SPL)、Pattern Recognition Letters (PRL)、Neural Computing and Applications (NCA)、Applied Intelligence、Image and Vision Computing (IVC)等； －知名国际会议：ACM-MM、UAI、CIKM、ICDM、SDM、ECML-PKDD、ICMR、ICME、ICASSP、ICIP、ICPR、ACCV、ACML、PRICAI等； －优秀中文期刊：《计算机学报》、《软件学报》、《中国科学：信息科学》、《计算机研究与发展》、《电子学报》、《计算机辅助设计与图形学学报》、《中国图象图形学报》、《中文信息学报》等。 担任国内外重要学术期刊和会议的审稿人，包括： － IEEE Transactions on Image Processing (TIP)、IEEE Transactions on Neural Networks and Learning Systems (TNNLS)、IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)、ACM Transactions on Multimedia Computing, Communications and Applications (TOMM)、Pattern Recognition (PR)、Neural Networks、Information Sciences、Information Processing and Management (IPM)、Knowledge-Based Systems (KBS)、Engineering Applications of Artificial Intelligence (EAAI)、Neurocomputing、IEEE Signal Processing Letters (SPL)、Data and Knowledge Engineering (DKE)、Applied Intelligence、Image and Vision Computing (IVC)、Displays、Future Generation Computer Systems (FGCS)、Signal Processing: Image Communication (SPIC)、Soft Computing、International Journal of Machine Learning and Cybernetics (IJMLC)、Neural Processing Letters (NPL)、Machine Vision and Applications (MVA)、Multimedia Tools and Applications (MTA)等国际期刊； － ACM-MM、EMNLP、ICRA、UAI、ECML-PKDD、ECAI、ICMR、AISTATS、BMVC、ICPR、ACCV、ACML、ICANN、ICONIP、KSEM、ADMA、CCFAI等国际国内会议； －《计算机学报》、《中国科学：信息科学》、《电子学报》、《计算机辅助设计与图形学学报》、《计算机科学》、《小型微型计算机系统》、《计算机工程》等中文期刊。
学习工作经历 1988年9月－1992年6月, 华中理工大学, 自动控制工程系, 自动控制专业, 本科. 1992年7月－1998年5月, 桂林电器科学研究所, 自动化室, 助理工程师. 1998年6月－2001年8月, 伟易达集团, 深圳开发部, 工程师. 2001年9月－2004年6月, 华中科技大学, 计算机科学与技术学院, 计算机应用技术专业, 硕士. 2004年7月－2007年8月, 桂林电子科技大学, 37000Cm威尼斯, 讲师. 2007年9月－2010年6月, 中国科学院计算技术研究所, 计算机软件与理论专业, 博士. 2010年7月－至今, 广西师范大学, 计算机科学与工程学院, 2010年晋升副教授, 2015年晋升教授, 2018年评为博士生导师, 2020年评为广西师大“独秀学者”.
讲授课程 机器学习（研究生） 算法设计与分析（本科生&研究生） 程序设计基础（本科生）
研究兴趣 计算机视觉与图像理解 机器学习与模式识别 自然语言处理 跨媒体智能计算
指导学生 【招生意向】 欢迎优秀的学生加入到我的课题组，一起探索有意义有趣味的研究课题，创造知识，享受知识！希望在课题组的学习经历能够成为你今后的人生财富，祝你拥有锦绣前程！ 专业需求：无特别明确的要求，如果是计算机、信息、数学、自动化、物理等相关专业会有一定优势，如果有较好的数学基础、英语能力、编程动手能力、以及较强的自学能力，无论你是什么专业都没有关系； 招生方向：机器学习、计算机视觉、自然语言处理等。如果以前对这些研究方向接触较少，可以通过网络简单快速了解其在学术和工业界中的理论与应用价值； 对学生的期望：“勤能补拙”，希望学生踏实上进、勤奋努力、做事细致有耐心；“兴趣是最好的老师”，希望学生把探索未知作为一生的兴趣；此外，希望学生性格开朗、有自信心、有较强的意志品质、具有团队合作精神； 学生未来规划：鼓励学生以科研作为追求目标，鼓励博士生毕业后从事科研相关工作，鼓励硕士生毕业后继续读博，也鼓励硕士生毕业后去IT公司从事技术研发或以技术为核心的创业！ 【指导特色】 认真履行导师责任，帮助学生快速成长：关注学生个人成长，因材施教，力所能及地为学生提供帮助。指导学生获批研究生创新项目多次，荣获广西师范大学“学术之星”称号多次，荣获国家奖学金和学业奖学金多次； 精心指导学生，提升学生的论文写作和软件开发能力：重视培养学生独立的科研能力，近年来几乎所有学生都能作为第一作者在CCF推荐的期刊或会议上发表论文； 指导的研究生不断进步，成绩喜人：部分硕士毕业生毕业后进入全国各大重点院校攻读博士学位；部分硕士研究生毕业后进入各大城市IT公司或研究所从事人工智能相关的研发工作；部分硕士研究生毕业后进入高职高专院校任教。 －17级硕士生权宇毕业后进入南京理工大学攻读博士学位； －18级硕士生黄飞成、陈圣嘉、张佳毕业后分别进入厦门大学、电子科技大学、西南交通大学攻读博士学位； －20级硕士生冼添涛、朱强喜毕业后分别进入华南理工大学、西南交通大学攻读博士学位； 【学生名录】 在读博士生：20级－魏家辉；21级－匡文兰；22级－李博；23级－欧利松； 在读硕士生：21级－黄莹、钟欣芳、曹润霖、陈振彬、姚丹、苏强；22级－周凤玲、彭大贺、胡钧博、宁可、吴优、刘鸣琦；23级－邓甫云、庄幸杰、曾琨、顾劲梁、蒋淑妮； 已毕业硕士：12级－曾培龙、王超俊；13级－韦斯婷、李灵芝、严考碧；14级－郑永哲、李艳红；15级－林兰、兰丹媚；16级－周韬、游锋生；17级－魏海洋、权宇、凌锋、孙亚茹、彭智；18级－黄飞成、陈圣嘉、张佳；19级－李伟、陈天宇、朱建伟、侯传文；20级－冼添涛、谢秀敏、杨熹微、曾禹飞、朱强喜；
获奖情况 博士学位论文“图像语义标注和检索的研究”（李志欣）获2011年度中国人工智能学会优秀博士学位论文奖. 获2020年度广西师范大学“优秀研究生指导教师”荣誉称号. 论文“Modeling continuous visual features for semantic image annotation and retrieval”（李志欣, 施智平, 刘曦, 史忠植）获2012年度广西自然科学优秀论文三等奖. 论文“Fusing semantic aspects for image annotation and retrieval”（李志欣, 施智平, 刘曦, 李志清, 史忠植）获2011年度广西自然科学优秀论文三等奖. 指导学生冼添涛、何凯杰等参加2021年中国—东盟数字创新大赛（人工智能赛道）, 获二等奖1项. 指导学生刘璟颢、李芮、李伟参加2018年第11届中国大学生计算机设计大赛, 作品“基于卷积神经网络的人脑海马体医学影像分割”获三等奖1项. 指导学生魏海洋、权宇、凌锋、周韬参加2018年第9届中国大学生服务外包创新创业大赛, 获企业命题类团体三等奖1项. 任教以来指导多名学生参加“蓝桥杯”全国软件和信息技术专业人才大赛, 获全国总决赛三等奖共9项.
科研项目 “融合多模态感知与因果推理的可解释视觉问答”, 国家自然科学基金面上项目, 编号: 62276073, 负责人: 李志欣, 2023.1－2026.12 “集成注意机制与知识推理的图像描述生成”, 国家自然科学基金地区科学基金项目, 编号: 61966004, 负责人: 李志欣, 2020.1－2023.12 “跨媒体语义映射与智能检索关键技术研究”, 国家自然科学基金地区科学基金项目, 编号: 61663004, 负责人: 李志欣, 2017.1－2020.12 “基于主题发现的图像语义理解与识别”, 国家自然科学基金地区科学基金项目, 编号: 61165009, 负责人: 李志欣, 2012.1－2015.12 “融合外部知识与多级注意的图像描述研究”, 广西自然科学基金重点项目, 编号: 2019GXNSFDA245018, 负责人: 李志欣, 2020.1－2023.12 “面向智能检索的跨媒体语义映射研究”, 广西自然科学基金面上项目, 编号: 2016GXNSFAA380146, 负责人: 李志欣, 2016.9－2019.8 “基于概率主题建模的图像语义映射研究”, 广西自然科学基金面上项目, 编号: 2012GXNSFAA053219, 负责人: 李志欣, 2012.4－2015.3 “工科研究生创新能力培养策略的研究”, 广西研究生教育创新计划项目: 学位与研究生教育改革专项课题, 编号: JGY2015031, 负责人: 李志欣, 2015.6－2018.8 “跨媒体语义挖掘关键技术的研究”, 广西信息科学实验中心开放课题, 编号: KF1405, 负责人: 李志欣, 2015.1－2017.12 “联合视觉与自然语言的端到端行人再辨识研究”, 国家自然科学基金地区科学基金项目, 编号: 61866004, 负责人: 张灿龙, 2019.1－2022.12, 排名第二 “多光谱图像目标融合跟踪关键技术研究”, 广西自然科学基金面上项目, 编号: 2017GXNSFAA198365, 负责人: 张灿龙, 2017.9－2020.8, 排名第二 “面向多源数据集成的安全与隐私保护技术及其应用”, 广西科技基地和人才专项, 编号: 桂科AD16380008, 负责人: 李先贤, 2016.9－2019.8, 参与 “基于新一代测序技术的K单体型组装算法研究”, 国家自然科学基金地区科学基金项目, 编号: 61363035, 负责人: 吴璟莉, 2014.1－2017.12, 排名第三 “智能机器人自主行动推理的形式化研究”, 广西自然科学基金面上项目, 编号: 2013GXNSFAA019345, 负责人: 周生明, 2013.4－2016.3, 排名第二 “智能机器人自主知识与自主行动推理研究”, 国家自然科学基金地区科学基金项目, 编号: 61262005, 负责人: 周生明, 2013.1－2016.12, 排名第三 “大规模数据共享的隐私模型与保护技术研究”, 国家重点基础研究发展计划（973计划）专项课题, 编号: 2012CB326403, 负责人: 李先贤, 2013.1－2014.12, 排名第四 “Web搜索与挖掘的新理论与新方法”, 国家自然科学基金重点项目, 编号: 60933004, 负责人: 李晓明/何清, 2010.1－2013.12, 参与 “基于视感知的图像视频语义获取关键技术研究”, 国家自然科学基金青年科学基金项目, 编号: 60903141, 负责人: 施智平, 2010.1－2012.12, 排名第四 “非结构化信息（图像）的内容理解与语义表征”, 国家重点基础研究发展计划（973计划）子课题, 编号: 2007CB311004, 负责人: 史忠植, 2007.1－2011.12, 参与 “基于感知机理的智能信息处理技术”, 国家高技术研究发展计划（863计划）, 编号: 2006AA01Z128, 负责人: 何清, 2007.1－2008.12, 参与 “基于感知学习和语言认知的智能计算模型研究”, 国家自然科学基金重点项目, 编号: 60435010, 负责人: 史忠植, 2005.1－2008.12, 参与
学术论文 在国内外重要学术期刊和会议上发表（录用）的论文主要包括: (按发表时间倒排序, *表示通讯作者, 中科院分区按发表当年标注) 【国际期刊】 Yao Dan, Li Zhixin*, Li Bo, Zhang Canlong, Ma Huifang. Similarity graph-correlation reconstruction network for unsupervised cross-modal hashing [J]. Expert Systems With Applications (ESWA), 2024, 237: Article 121516 (13 pages). (SCI&EI收录, CCF推荐C类/中科院一区Top期刊) Zeng Yufei, Li Zhixin*, Chen Zhenbin, Ma Huifang. A feature-based restoration dynamic interaction network for multimodal sentiment analysis [J]. Engineering Applications of Artificial Intelligence (EAAI), 2024, 127: Article 107335 (12 pages). (SCI&EI收录, CCF推荐C类/中科院二区Top期刊) Zeng Yufei, Li Zhixin*, Chen Zhenbin, Ma Huifang. Aspect-level sentiment analysis based on semantic heterogeneous graph convolutional network [J]. Frontiers of Computer Science (FCS), 2023, 17(6): Article 176340 (13 pages). (SCI&EI收录, CCF推荐B类期刊) Li Wei, Li Zhixin*, Yang Xiwei, Ma Huifang. Causal-ViT: Robust vision Transformer by causal intervention [J]. Engineering Applications of Artificial Intelligence (EAAI), 2023, 126: Article 107123 (14 pages). (SCI&EI收录, CCF推荐C类/中科院二区Top期刊) Yang Xiwei, Li Zhixin*, Zhong Xinfang, Zhang Canlong, Ma Huifang. Mining graph-based dynamic relationships for object detection [J]. Engineering Applications of Artificial Intelligence (EAAI), 2023, 126: Article 106928 (11 pages). (SCI&EI收录, CCF推荐C类/中科院二区Top期刊) Zhu Qiangxi, Li Zhixin*, Kuang Wenlan, Ma Huifang. A multichannel location-aware interaction network for visual classification [J]. Applied Intelligence, 2023, 53(20): 23049-23066. (SCI&EI收录, CCF推荐C类/中科院二区期刊) Chen ShengJia, Yang Xiwei, Li Zhixin*. Improving semantic segmentation with knowledge reasoning network [J]. Journal of Visual Communication and Image Representation (JVCIR), 2023, 96: Article 103923 (15 pages). (SCI&EI收录, CCF推荐C类期刊) Li Bo, Yao Dan, Li Zhixin*. RICH: A rapid method for image-text cross-modal hash retrieval [J]. Displays, 2023, 79: Article 102489 (10 pages). (SCI&EI收录, 中科院二区期刊) Zhu Qiangxi, Kuang Wenlan, Li Zhixin*. A collaborative gated attention network for fine-grained visual classification [J]. Displays, 2023, 79: Article 102468 (11 pages). (SCI&EI收录, 中科院二区期刊) Li Wei, Yang Xiwei, Li Zhixin*. MLCB-Net: A multi-level class balancing network for domain adaptive semantic segmentation [J]. Multimedia Systems (MS), 2023, 29(3): 1405–1416. (SCI&EI收录, CCF推荐C类期刊) Zhu Qiangxi, Kuang Wenlan, Li Zhixin*. Fusing bilinear multi-channel gated vector for fine-grained classification [J]. Machine Vision and Applications (MVA), 2023, 34(2): Article 26 (16 pages). (SCI&EI收录, CCF推荐C类期刊) Zeng Yufei, Li Zhixin*, Tang Zhenjun, Chen Zhenbin, Ma Huifang. Heterogeneous graph convolution based on in-domain self-supervision for multimodal sentiment analysis [J]. Expert Systems With Applications (ESWA), 2023, 213: Article 119240 (15 pages). (SCI&EI收录, CCF推荐C类/中科院一区Top期刊) Wei Jiahui, Li Zhixin*, Zhu Jianwei, Ma Huifang. Enhance understanding and reasoning ability for image captioning [J]. Applied Intelligence, 2023, 53(3): 2706–2722. (SCI&EI收录, CCF推荐C类/中科院二区期刊) Li Zhixin*, Wei Jiahui, Huang Feicheng, Ma Huifang. Modeling graph-structured contexts for image captioning [J]. Image and Vision Computing (IVC), 2023, 129: Article 104591 (10 pages). (SCI&EI收录, CCF推荐C类期刊) Xie Xiumin, Li Zhixin*, Tang Zhenjun, Yao Dan, Ma Huifang. Unifying knowledge iterative dissemination and relational reconstruction network for image-text matching [J]. Information Processing and Management (IPM), 2023, 60(1): Article 103154 (16 pages). (SCI&EI收录, CCF推荐B类/中科院一区Top期刊) Zhu Jianwei, Li Zhixin*, Wei Jiahui, Ma Huifang. PBGN: Phased bidirectional generation network in text-to-image synthesis [J]. Neural Processing Letters (NPL), 2022, 54(6): 5371–5391. (SCI&EI收录, CCF推荐C类期刊) Hou Chuanwen, Li Zhixin*, Tang Zhenjun, Xie Xiumin, Ma Huifang. Multiple instance relation graph reasoning for cross-modal hash retrieval [J]. Knowledge-Based Systems (KBS), 2022, 256: Article 109891 (12 pages). (SCI&EI收录, CCF推荐C类/中科院一区Top期刊) Zhu Qiangxi, Kuang Wenlan, Li Zhixin*. Dual attention interactive fine-grained classification network based on data augmentation [J]. Journal of Visual Communication and Image Representation (JVCIR), 2022, 88: Article 103632 (13 pages). (SCI&EI收录, CCF推荐C类期刊) Xian Tiantao, Li Zhixin*, Tang Zhenjun, Ma Huifang. Adaptive path selection for dynamic image captioning [J]. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022, 32(9): 5762–5775. (SCI&EI收录, CCF推荐B类/中科院一区Top期刊) Zhang Jia, Li Wei, Li Zhixin*. Distinguishing foreground and background alignment for unsupervised domain adaptive semantic segmentation [J]. Image and Vision Computing (IVC), 2022, 124: Article 104513 (9 pages). (SCI&EI收录, CCF推荐C类期刊) Zhu Jianwei, Li Zhixin*, Wei Jiahui, Zeng Yufei, Ma Huifang. Fine-grained bidirectional attentional generation and knowledge-assisted networks for cross-modal retrieval [J]. Image and Vision Computing (IVC), 2022, 124: Article 104507 (11 pages). (SCI&EI收录, CCF推荐C类期刊) Hou Chuanwen, Li Zhixin*, Wu Jingli. Unsupervised hash retrieval based on multiple similarity matrices and text self-attention mechanism [J]. Applied Intelligence, 2022, 52(7): 7670–7685. (SCI&EI收录, CCF推荐C类/中科院二区期刊) Xian Tiantao, Li Zhixin*, Zhang Canlong, Ma Huifang. Dual global enhanced transformer for image captioning [J]. Neural Networks, 2022, 148: 129–141. (SCI&EI收录, CCF推荐B类/中科院一区Top期刊) Chen Tianyu, Li Zhixin*, Wu Jingli, Ma Huifang, Su Bianping. Improving image captioning with pyramid attention and SC-GAN [J]. Image and Vision Computing (IVC), 2022, 117: Article 104340 (12 pages). (SCI&EI收录, CCF推荐C类期刊) Li Zhixin*, Xie Xiumin, Ling Feng, Ma Huifang, Shi Zhiping. Matching images and texts with multi-head attention network for cross-media hashing retrieval [J]. Engineering Applications of Artificial Intelligence (EAAI), 2021, 106: Article 104475 (12 pages). (SCI&EI收录, CCF推荐C类/中科院二区Top期刊) Zhang Jia, Li Zhixin*, Zhang Canlong, Ma Huifang. Stable self-attention adversarial learning for semi-supervised semantic image segmentation [J]. Journal of Visual Communication and Image Representation (JVCIR), 2021, 78: Article 103170 (9 pages). (SCI&EI收录, CCF推荐C类期刊) Quan Yu, Li Zhixin*, Chen Shengjia, Zhang Canlong, Ma Huifang. Joint deep separable convolution network and border regression reinforcement for object detection [J]. Neural Computing and Applications (NCA), 2021, 33(9): 4299–4314. (SCI&EI收录, CCF推荐C类/中科院二区期刊) Wei Haiyang, Li Zhixin*, Huang Feicheng, Zhang Canlong, Ma Huifang, Shi Zhongzhi. Integrating scene semantic knowledge into image captioning [J]. ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 2021, 17(2): Article 52 (22 pages). (SCI&EI收录, CCF推荐B类期刊) Li Zhixin*, Sun Yaru, Zhu Jianwei, Tang Suqin, Zhang Canlong, Ma Huifang. Improve relation extraction with dual attention guided graph convolutional networks [J]. Neural Computing and Applications (NCA), 2021, 33(6): 1773–1784. (SCI&EI收录, CCF推荐C类/中科院二区期刊) Li Zhixin*, Lin Lan, Zhang Canlong, Ma Huifang, Zhao Weizhong, Shi Zhiping. A semi-supervised learning approach based on adaptive weighted fusion for automatic image annotation [J]. ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 2021, 17(1): Article 37 (23 pages). (SCI&EI收录, CCF推荐B类期刊) Wei Haiyang, Li Zhixin*, Zhang Canlong, Ma Huifang. The synergy of double attention: Combine sentence-level and word-level attention for image captioning [J]. Computer Vision and Image Understanding (CVIU), 2020, 201: Article 103068 (10 pages). (SCI&EI收录, CCF推荐B类期刊) Huang Feicheng, Li Zhixin*, Wei Haiyang, Zhang Canlong, Ma Huifang. Boost image captioning with knowledge reasoning [J]. Machine Learning, 2020, 109(12): 2313–2332. (SCI&EI收录, CCF推荐B类期刊) Chen Shengjia, Li Zhixin*, Tang Zhenjun. Relation R-CNN: A graph based relation-aware network for object detection [J]. IEEE Signal Processing Letters (SPL), 2020, 27: 1680–1684. (SCI&EI收录, CCF推荐C类/中科院二区期刊) Zhou Tao, Li Zhixin*, Zhang Canlong, Ma Huifang. Classify multi-label images via improved CNN model with adversarial network [J]. Multimedia Tools and Applications (MTA), 2020, 79(9-10): 6871–6890. (SCI&EI收录, CCF推荐C类期刊) Li Zhixin*, Ling Feng, Zhang Canlong, Ma Huifang. Combining global and local similarity for cross-media retrieval [J]. IEEE Access, 2020, 8: 21847–21856. (SCI&EI收录, 中科院二区期刊) Li Zhixin*, Peng Zhi, Tang Suqin, Zhang Canlong, Ma Huifang. Text summarization method based on double attention pointer network [J]. IEEE Access, 2020, 8: 11279–11288. (SCI&EI收录, 中科院二区期刊) Quan Yu, Li Zhixin*, Zhang Canlong, Ma Huifang. Object detection model based on deep dilated convolutional networks by fusing transfer learning [J]. IEEE Access, 2019, 7: 178699–178709. (SCI&EI收录, 中科院二区期刊) Zhou Tao, Li Zhixin*, Zhang Canlong. Enhance the recognition ability to occlusions and small objects with Robust Faster R-CNN [J]. International Journal of Machine Learning and Cybernetics (IJMLC), 2019, 10(11): 3155–3166. (SCI&EI收录, 中科院二区期刊) Wei Siting, Li Zhixin*, Zhang Canlong. Combined constraint-based with metric-based in semi-supervised clustering ensemble [J]. International Journal of Machine Learning and Cybernetics (IJMLC), 2018, 9(7): 1085–1100. (SCI&EI收录, 中科院二区期刊) Zheng Yongzhe, Li Zhixin*, Zhang Canlong. A hybrid architecture based on CNN for cross-modal semantic instance annotation [J]. Multimedia Tools and Applications (MTA), 2018, 77(7): 8695–8710. (SCI&EI收录, CCF推荐C类期刊) Li Zhixin*, Li Lingzhi, Yan Kaobi, Zhang Canlong. Automatic image annotation using fuzzy association rules and decision tree [J]. Multimedia Systems (MS), 2017, 23(6): 679–690. (SCI&EI收录, CCF推荐C类期刊) Yan Kaobi, Li Zhixin*, Zhang Canlong. A new multi-instance multi-label learning approach for image and text classification [J]. Multimedia Tools and Applications (MTA), 2016, 75(13): 7875–7890. (SCI&EI收录, CCF推荐C类期刊) Li Zhixin*, Shi Zhongzhi, Zhao Weizhong, Li Zhiqing, Tang Zhenjun. Learning semantic concepts from image database with hybrid generative/discriminative approach [J]. Engineering Applications of Artificial Intelligence (EAAI), 2013, 26(9): 2143–2152. (SCI&EI收录, CCF推荐C类期刊) Li Zhixin*, Shi Zhiping, Liu Xi, Shi Zhongzhi. Modeling continuous visual features for semantic image annotation and retrieval [J]. Pattern Recognition Letters (PRL), 2011, 32(3): 516–523. (SCI&EI收录, CCF推荐C类期刊) Li Zhixin*, Shi Zhiping, Liu Xi, Li Zhiqing, Shi Zhongzhi. Fusing semantic aspects for image annotation and retrieval [J]. Journal of Visual Communication and Image Representation (JVCIR), 2010, 21(8): 798–805. (SCI&EI收录, CCF推荐C类期刊)
【国际会议】 Yao Dan, Li Zhixin*. Graph rebasing and joint similarity reconstruction for cross-modal hash retrieval [C]. In: Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD’23), Part II, LNAI 14170, pp. 86–102. Springer, Sep. 18-22, 2023. (EI收录, CCF推荐B类会议) Kuang Wenlan, Zhu Qiangxi, Li Zhixin*. Multi-label image classification with multi-scale global-local semantic graph network [C]. In: Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD’23), Part III, LNAI 14171, pp. 53–69. Springer, Sep. 18-22, 2023. (EI收录, CCF推荐B类会议) Cao Runlin, Li Zhixin*. Overcoming language priors for visual question answering via loss rebalancing label and global context [C]. In: Proceedings of the 39th Conference on Uncertainty in Artificial Intelligence (UAI’23), PMLR 216, pp. 249–259. MIT Press, Jul. 31-Aug. 4, 2023. (EI收录, CCF推荐B类会议) Zhu Qiangxi, Li Zhixin*. A progressive gated attention mechanism model for fine-grained visual classification [C]. In: Proceedings of the 2023 IEEE International Conference on Multimedia and Expo (ICME’23), pp. 2063–2068. IEEE, Jul. 10-14, 2023. (EI收录, CCF推荐B类会议) Li Wei, Li Zhixin*. Causal-SETR: A SEgmentation TRansformer variant based on causal intervention [C]. In: Proceedings of the 16th Asian Conference on Computer Vision (ACCV’22), Part VII, LNCS 13847, pp. 414–430. Springer, Dec. 4-8, 2022. (EI收录, CCF推荐C类会议) Zhu Jianwei, Li Zhixin*, Zeng Yufei, Wei Jiahui, Ma Huifang. Image-text matching with fine-grained relational dependency and bidirectional attention-based generative networks [C]. In: Proceedings of the 30th ACM International Conference on Multimedia (ACM MM’22), pp. 395–403. ACM, Oct. 10-14, 2022. (EI收录, CCF推荐A类会议) Zhu Qiangxi, Li Zhixin*. Data augmented dual-attention interactive image classification network [C]. In: Proceedings of the 31st International Conference on Artificial Neural Networks (ICANN’22), Part III, LNCS 13531, pp. 74–86. Springer, Sep. 6-9, 2022. (EI收录, CCF推荐C类会议) Li Zhixin*, Li Wei, Zhang Jia. Domain adaptative semantic segmentation by fine-grained alignment [C]. In: Proceedings of the 31st International Conference on Artificial Neural Networks (ICANN’22), Part IV, LNCS 13532, pp. 383–394. Springer, Sep. 6-9, 2022. (EI收录, CCF推荐C类会议) Zhu Qiangxi, Kuang Wenlan, Li Zhixin*. Dual-network multi-attention collaborative classification based on fine-grained vision [C]. In: Proceedings of the 26th International Conference on Pattern Recognition (ICPR’22), pp. 513–520. IEEE, Aug. 21-25, 2022. (EI收录, CCF推荐C类会议) Xie Xiumin, Hou Chuanwen, Li Zhixin*. Fine-grained matching with multi-perspective similarity modeling for cross-modal retrieval [C]. In: Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence (UAI’22), PMLR 180, pp. 2148–2158. MIT Press, Aug. 1-5, 2022. (EI收录, CCF推荐B类会议) Yang Xiwei, Zhong Xinfang, Li Zhixin*. GRDN: Graph relation decision network for object detection [C]. In: Proceedings of the 2022 IEEE International Conference on Multimedia and Expo (ICME’22), 6 pages. IEEE, Jul. 18-22, 2022. (EI收录, CCF推荐B类会议) Xian Tiantao, Li Zhixin*, Chen Tianyu, Ma Huifang. Dynamic Transformer for image captioning [C]. In: Proceedings of the 2022 IEEE International Conference on Multimedia and Expo (ICME’22), 6 pages. IEEE, Jul. 18-22, 2022. (EI收录, CCF推荐B类会议) Huang Feicheng, Li Zhixin*. Improve image captioning via relation modeling [C]. In: Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’22), pp. 1945–1949. IEEE, May 22-27, 2022. (EI收录, CCF推荐B类会议) Chen Tianyu, Li Zhixin*, Wei Jiahui, Xian Tiantao. Mixed knowledge relation Transformer for image captioning [C]. In: Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’22), pp. 4403–4407. IEEE, May 22-27, 2022. (EI收录, CCF推荐B类会议) Xian Tiantao, Li Zhixin*, Chen Tianyu, Ma Huifang. Exploring dual stream global information for image captioning [C]. In: Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’22), pp. 4458–4462. IEEE, May 22-27, 2022. (EI收录, CCF推荐B类会议) Wei Jiahui, Li Zhixin*, Zhu Jianwei, Ma Huifang. Flexible image captioning via internal understanding and external reasoning [C]. In: Proceedings of the 2022 SIAM International Conference on Data Mining (SDM’22), pp. 307–315. SIAM, Apr. 28-30, 2022. (EI收录, CCF推荐B类会议) Chen Tianyu, Li Zhixin*, Xian Tiantao, Zhang Canlong, Ma Huifang. Relation also need attention: Integrating relation information into image captioning [C]. In: Proceedings of the 13th Asian Conference on Machine Learning (ACML’21), PMLR 157, pp.1537–1552. MIT Press, Nov. 17-19, 2021. (EI收录, CCF推荐C类会议) Li Wei, Li Zhixin*. Domain adaptative semantic segmentation by alleviating long-tail problem [C]. In: Proceedings of the 2021 International Joint Conference on Neural Network (IJCNN’21), 8 pages. IEEE, Jul. 18-22, 2021. (EI收录, CCF推荐C类会议) Zhu Jianwei, Li Zhixin*, Ma Huifang. TT2INet: Text to photo-realistic image synthesis with transformer as text encoder [C]. In: Proceedings of the 2021 International Joint Conference on Neural Network (IJCNN’21), 8 pages. IEEE, Jul. 18-22, 2021. (EI收录, CCF推荐C类会议) Chen Shengjia, Li Zhixin*, Yang Xiwei. Knowledge reasoning for semantic segmentation [C]. In: Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’21), pp. 2340–2344. IEEE, Jun. 6-11, 2021. (EI收录, CCF推荐B类会议) Li Zhixin*, Sun Yaru, Tang Suqin, Zhang Canlong, Ma Huifang. Reinforcement learning with dual attention guided graph convolution for relation extraction [C]. In: Proceedings of the 25th International Conference on Pattern Recognition (ICPR’20), pp. 946–953. IEEE, Jan. 10-15, 2021. (EI收录, CCF推荐C类会议) Quan Yu, Li Zhixin*, Zhang Canlong, Ma Huifang. Object detection model based on scene-level region proposal self-attention [C]. In: Proceedings of the 25th International Conference on Pattern Recognition (ICPR’20), pp. 954–961. IEEE, Jan. 10-15, 2021. (EI收录, CCF推荐C类会议) Li Zhixin*, Ling Feng, Xu Chuansheng, Zhang Canlong, Ma Huifang. Cross-media hash retrieval using multi-head attention network [C]. In: Proceedings of the 25th International Conference on Pattern Recognition (ICPR’20), pp. 1290–1297. IEEE, Jan. 10-15, 2021. (EI收录, CCF推荐C类会议) Chen Shengjia, Li Zhixin*, Huang Feicheng, Zhang Canlong, Ma Huifang. Improving object detection with relation mining network [C]. In: Proceedings of the 20th IEEE International Conference on Data Mining (ICDM’20), pp. 52–61. IEEE, Nov. 17-20, 2020. (EI收录, CCF推荐B类会议, Full Paper) Zhang Jia, Li Zhixin*, Zhang Canlong, Ma Huifang. Robust adversarial learning for semi-supervised semantic segmentation [C]. In: Proceedings of the 27th IEEE International Conference on Image Processing (ICIP’20), pp. 728–732. IEEE, Oct. 25-28, 2020. (EI收录, CCF推荐C类会议) Huang Feicheng, Li Zhixin*, Chen Shengjia, Zhang Canlong, Ma Huifang. Image captioning with internal and external knowledge [C]. In: Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM’20), pp. 535–544. ACM, Oct. 19-23, 2020. (EI收录, CCF推荐B类会议, Full Paper) Wei Haiyang, Li Zhixin*, Zhang Canlong. Image captioning based on visual and semantic attention [C]. In: Proceedings of the 26th International Conference on MultiMedia Modeling (MMM’20), Part I, LNCS 11961, pp.151–162. Springer, Jan. 5-8, 2020. (EI收录, CCF推荐C类会议) Li Zhixin*, Ling Feng, Zhang Fengqi, Zhang Canlong. Cross-media image-text retrieval based on two-level network [C]. In: Proceedings of the 26th International Conference on Neural Information Processing (ICONIP’19), Part I, LNCS 11953, pp.211–222. Springer, Dec. 12-15, 2019. (EI收录, CCF推荐C类会议) Li Zhixin*, Sun Yaru, Tang Suqin, Zhang Canlong, Ma Huifang. Sentence-level semantic features guided adversarial network for Zhuang language part-of-speech tagging [C]. In: Proceedings of the 31st IEEE International Conference on Tools with Artificial Intelligence (ICTAI’19), pp.265–272. IEEE, Nov. 4-6, 2019. (EI收录, CCF推荐C类会议) Quan Yu, Li Zhixin*, Zhang Fengqi, Zhang Canlong. D_dNet-65 R-CNN: Object detection model fusing deep dilated convolutions and light-weight networks [C]. In: Proceedings of the 16th Pacific Rim International Conference on Artificial Intelligence (PRICAI’19), Part III, LNAI 11672, pp.16–28. Springer, Aug. 26-30, 2019. (EI收录, CCF推荐C类会议) Wei Haiyang, Li Zhixin*, Zhang Canlong, Zhou Tao, Quan Yu. Image captioning based on sentence-level and word-level attention [C]. In: Proceedings of the 2019 International Joint Conference on Neural Network (IJCNN’19), 8 pages. IEEE, Jul. 14-19, 2019. (EI收录, CCF推荐C类会议) Li Zhixin*, Lin Lan, Zhang Canlong, Ma Huifang, Zhao Weizhong. Collaborating CNN and SVM for automatic image annotation [C]. In: Proceedings of the 2019 ACM International Conference on Multimedia Retrieval (ICMR’19), pp. 63–67. ACM, Jun. 10-13, 2019. (EI收录, CCF推荐B类会议) Zhou Tao, Li Zhixin*, Zhang Canlong, Lin Lan. An improved convolutional neural network model with adversarial net for multi-label image classication [C]. In: Proceedings of the 15th Pacific Rim International Conference on Artificial Intelligence (PRICAI’18), Part II, LNAI 11013, pp.38–46. Springer, Aug. 28-31, 2018. (EI收录, CCF推荐C类会议) Li Zhixin*, Shi Zhiping, Liu Xi, Shi Zhongzhi. Automatic image annotation with continuous PLSA [C]. In: Proceedings of the 2010 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’10), pp. 806–809. IEEE, Mar. 14-19, 2010. (EI收录, CCF推荐B类会议) Li Zhixin*, Liu Xi, Shi Zhiping, Shi Zhongzhi. Learning image semantics with latent aspect model [C]. In: Proceedings of the 2009 IEEE International Conference on Multimedia and Expo (ICME’09), pp. 366–369. IEEE, Jun. 28-Jul. 3, 2009. (EI收录, CCF推荐B类会议)
友情链接
最近更新:2021-02-28
|
