沈琳琳,教授,上海交通大学学士、硕士,受英国政府海外研究奖学金资助在诺丁汉大学获得博士学位,博士期间获得“国家优秀自费留学生”奖励。2015-2023连续9年被爱思唯尔出版社评为计算机学科“中国高被引学者”,2020-2023连续入围斯坦福大学“科学影响力全球前2%科学家榜单”。现为深圳市“鹏城学者”特聘教授、英国诺丁汉大学计算机学院荣誉教授、宁波诺丁汉大学计算机系、温州肯恩大学计算机系访问教授、澳门大学杰出访问学者;大数据系统计算技术国家工程实验室副主任、广东省教育厅中英合作视觉信息处理实验室主任、开yun体育官网入口登录苹果计算机视觉研究所所长、开yun体育官网入口登录苹果医学影像智能分析与诊断研究中心主任、华为公司计算机视觉算法顾问。期刊《Cognitive Computation and Systems》常务副主编(Co-Editor-in-Chief)、《Expert Systems with Applications》副编辑(Associate Editor)。研究方向主要为深度学习理论及其在人脸识别/分析以及医学图像分析上的应用,作为负责人连续主持国家自然科学基金重大研究计划、国际合作研究、面上项目等5项,发表学术论文300余篇。2023年5月带领团队开源首个中文百亿参数大模型“伶荔”,被金融等垂直行业广泛使用。
IEEE高级会员,入选江西省“双千计划”创新领军人才(短期)、广东省高校千百十工程培养对象(省级),深圳市高层次“地方领军人才”、深圳市海外高层次“孔雀计划”人才,深圳市十佳青年教师。科研成果先后获得吴文俊人工智能自然科学奖,中国电子学会、广东省和深圳市自然科学奖。基于人脸视频的抑郁分析论文获情感计算顶刊《IEEE Trans. on Affective Computing》最佳论文亚军,人脸识别论文曾获国际期刊《Image and Vision Computing》最多他引论文奖。开发的人脸识别算法曾获ICPR算法测试亚军,开发的细胞荧光图像分类算法连续获得IEEE ICIP 2013、ICPR 2016国际细胞图像分类算法大赛冠军,目标检测算法获得MICCAI 2018细胞核检测比赛季军、2021年科大迅飞遥感影像典型目标提取挑战赛决赛季军。
Google Scholar 引用 12953,H指数 55 https://scholar.google.com/citations?user=AZ_y9HgAAAAJ
所有论文 DBLP 网址: https://dblp.org/pid/88/5607.html
项目和代码网址: http://github.com/cvi-szu
研究领域
(1)通用深度学习理论
百亿参数大规模语言模型,语言-文本跨模态模型预训练、新型网络架构、特征提取模块提升CNN、Transformer性能;提出小波卷积层代替下采样池化及上采样模块,解决高低频信号混叠问题。结合手工特征,引导网络早期的快速收敛。研究最新文本-图像跨模态生成模型及其应用。
(2)弱监督物体检测/语义与实例分割
基于图像类别标签的物体检测网络、语义分割网络,减少通用物体检测/分割网络对标注数据的要求。研究如何利用大规模预训练模型减少网络对训练数据的要求,在零样本开放数据上依然能够取得良好性能。
(3)人脸识别/分析与合成
基于深度卷积网络的人脸识别、表情、年龄等属性识别方法及系统,基于GAN、StyleGAN和Diffusion Model的人脸编辑、文本驱动的人脸生成,以及基于人脸视频的个体性格、抑郁等心理情绪预测。开发的人脸识别系统在深圳高交会、双创周、杭州G20和新疆安防广泛使用。
(4)医学图像智能分析
大脑MRI图像肿瘤区域分割、牙齿CT图像种牙位置预测、多尺度卷积网络的X光图像肺结节识别,眼底图像/视网膜OCT图像疾病检测;
B超图像甲状腺结节分割与良恶性分类、鼻内窥镜图像腺样体肥大检测、消化道内窥镜图像息肉检测与分析;
胃肠组织病理全切片WSI图像肿瘤判读,宫颈TCT细胞病理全切片WSI图像判读
常年招聘博士后、博士/硕士研究生,联系邮件 LLShen@szu.edu.cn,要求:
(1)踏实、勤奋、努力、上进、肯干
(2)编程能力强,良好的数学功底
(3)具有团队协作精神
宁波诺丁汉大学-开yun体育官网入口登录苹果联合培养博士 全奖项目(生活费4500/月),授予英国诺丁汉大学博士学位!! 2024.09入学申请链接
深大招生专业:计算机科学与技术 学术博士,电子信息“计算机技术”专业博士
计算机科学与技术学硕,计算机技术、人工智能专硕;
医学影像智能分析与诊断研究中心交叉学科学硕(授计算机科学与技术学硕学位):与医学部、医院医生联合培养,详见 2023入学申请链接
提供的科研环境:
(1)优良的计算机硬件环境,含100块Tesla A100、V100、P100,12块 Titan X GPU 深度学习工作站多台;
(2)有1000万人脸数据库,百万级肺部X光、CT、万级细胞病理图像、以及十万级服饰图像供使用训练;
(3)和高通、华为、大华、唯品会、雄帝等上市公司深入的企业合作,项目需求来自于企业,具有广泛应用前景,高薪工作offer;
(4)充足研究经费,提供有竞争力的生活补助。
博士后出站去向:
培养出站10名,其中助理教授6名(美国Lehigh大学、开yun体育官网入口登录苹果、西交利物浦、深圳技术大学)、副研究员1名(开yun体育官网入口登录苹果)、算法科学家3名(腾讯天衍实验室、鹏行智能、之江实验室)
Dr. Weicheng Xie (解为成) 开yun体育官网入口登录苹果计算机学院 副教授(人脸情感分析)
Dr. Lifang He (何丽芳) 美国Lehigh大学 助理教授(大数据分析)
Dr. Xiaole Shen (沈小乐) 深圳技术大学 大数据学院 助理教授(遥感图像分析)
Dr. Xuechen Li (李雪晨) 五邑大学 副教授(医学图像分析)
Dr. Yang Zhang (张洋) 开yun体育官网入口登录苹果 计算机学院 助理教授(基于忆阻的深度学习)
Dr. Qiufu Li (李秋富) 开yun体育官网入口登录苹果 大数据国家工程实验室 助理教授(计算机视觉)
Dr. Xianxu Hou (侯贤旭) 西交利物浦大学 助理教授(人脸图像生成)
Dr. Renwu Gao (高仁武) 鹏行智能 算法科学家(机器人视觉)
Dr. Syed Furqan Qadri 之江实验室 副研究员(医学图像分析)
博士生毕业去向:
培养1名,在读10名
Dr. Siyang Song (宋思阳) 英国Leicester大学讲师(人脸情感分析)
硕士生毕业去向:
累计培养70余名,继续攻读博士10名(美国Rochester理工学院(RIT)、新加坡国立、英国诺丁汉、伯明翰、宁波诺丁汉、澳大利亚莫纳什、荷兰格罗宁根、瑞典卡罗林斯卡医学院、香港城大、香港理工、中山大学),腾讯9名,华为9名,字节跳动6名、大疆2名、招商银行2名,其他就业单位包括 百度、Oracle、小米 AI Lab、美团、寒武纪、金山 AI Lab、地平线、奥比中光、超参数、飞思卡尔、中国人民银行、中国证券、深圳证券、绿米、华付信息以及广东司法警官学校、深圳龙岗中学等。
代表会议论文
- Qiufu Li, Xi Jia, Jiancan Zhou,Linlin Shen* and Jinming Duan. UniTSFace: Unifined threshold integrated sample-to-sample loss for face recognition. NeurIPS 2023, New Orleans, USA, Dec. 2023 (神经网络顶会)
- Jinheng Xie, Kai Ye, Yudong Li, Yuexiang Li, Kevin Qinghong Lin, Yefeng Zheng, Linlin Shen and Mike Zheng Shou. Learning Visual Pior via Geerative Pre-Training. NeurIPS 2023, New Orleans, USA, Dec. 2023 (神经网络顶会)
- Jiancan Zhou, Xi Jia, Qiufu Li, Linlin Shen* and Jinming Duan. UniFace: Unified Cross-Entropy Loss for Deep Face Recognition. ICCV 2023, Pairs, France (计算机视觉顶会)
- Hao Li, Xianxu Hou, Zepeng Huang and Linlin Shen*. StyleGene: Crossover and Mutation of Region-level Facial Genes for Kinship Face Synthesis. CVPR 2023, Vancouver, Canada (计算机视觉顶会, 入选Highlight Paper, 比例2.5%)
- Songhe Deng, Wei Zhuo, Jinheng Xie and Linlin Shen*. QA-CLIMS: Question-Answer Cross Language Image Matching for Weakly Supervised Semantic Segmentation. ACM Multimedia 2023, Vancuver, Canada (多媒体顶会)
- Xinquan Yang, Jinheng Xie, Xuechen Li, Xuguang Li, Xin Li, Linlin Shen* and Yongqiang Deng. Text Condition Embedded Regression Network for Dental Implant Position Prediction, Vancouver, Canada, MICCAI 2023, Oct. (医学图像顶会)
- Jianfeng Xiang, Junliang Chen, Wenshuang Liu, Xianxu Hou and Linlin Shen*. RamGAN: Region Attentive Morphing GAN for Region-Level Makeup Transfer, ECCV 2022, Oct. Tel-Aviv, Israel. (计算机视觉顶会)
- Wenshuang Liu, Wenting Chen, Zhanjia Yang and Linlin Shen*. Translate the Facial Regions You Like Using Self-Adaptive Region Translation, AAAI 2021 , Feb. (人工智能顶会)
- Yudong Li, Xianxu Hou, Zhe Zhao, Linlin Shen*, Xuefeng Yang and Kimmo Yan. Talk2Face: A Unified Sequence-based Framework for Diverse Face Generation and Analysis Tasks, ACM Multimedia 2022 Oct. Portugal. (多媒体顶会)
- Ya-Nan Zhang, Linlin Shen* and Qiufu Li. Content and Gradient Model-driven Deep Network for Single Image Reflection Removal. ACM Multimedia 2022 Oct. Portugal. (多媒体顶会)
- Minmin Liu, Xuechen Li, Xiangbo Gao, Junliang Chen, Linlin Shen* and Huisi Wu. Sample hardness based gradient loss for long-tailed cervical cell detection. MICCAI 2022, Oct. (医学图像顶会)
- Haoqin Ji, Haozhe Liu, Yuexiang Li, Jinheng Xie, Nanjun He, Dong Wei, Xinrong Chen, Linlin Shen* and Yefeng Zheng. Point Beyond Class: A Benchmark for Weakly Semi-Supervised Abnormality Localization in Chest X-Rays. MICCAI 2022, Oct. (医学图像顶会)
- Cheng Luo, Siyang Song, Weicheng Xie, Linlin Shen and Hatice Guns. Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition. IJCAI 2022, USA (人工智能顶会,接受率15%)
- Jinheng Xie, Xianxu Hou, Kai Ye and Linlin Shen*. CLIMS: Cross Language Image Matching for Weakly Supervised Semantic Segmentation, CVPR 2022, USA (计算机视觉顶会)
- Jinheng Xie, Jianfeng Xiang, Junliang Chen, Xiaodong Zhao and Linlin Shen*. C2AM: Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation, CVPR 2022, USA (计算机视觉顶会)
- Jinheng Xie, Cheng Luo, Xiangping Zhu, Ziqi Jin, Weizeng Lu and Linlin Shen*. Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization, ICCV 2021, Oct. Online (计算机视觉顶会)
- Hanbang Liang, Xianxu Hou and Linlin Shen*. SSFlow: Style-guided neural Spline Flows for Face Image Manipulation, ACM Multimedia 2021 Oct. Chengdu, China (多媒体顶会)
- Zilong Shao, Siyang Song, Shashank Jaiswal, Linlin Shen*, Michel Valstar and Hatice Gunes, Personality Recognition by Modelling Person-specific Cognitive Processes using Graph Representation, ACM Multimedia 2021 Oct. Chengdu, China,(多媒体顶会)
- Qi Wan, Haoqing Ji and Linlin Shen*. Self-attention based Text Knowledge Mining for Text Detection, CVPR 2021, June, USA. (计算机视觉顶会)
- Weizeng Lu, Xi Jia, Weicheng Xie, Linlin Shen*, Yicong Zhou and Jinming Duan. Geometry constrained weakly supervised object localization, ECCV 2020, Aug. Germeny, (计算机视觉顶会)
- Qiufu Li, Linlin Shen*, Sheng Guo and Zhihui Lai. Wavelet Integrated CNNs for Noise-Robust Image Classification, CVPR 2020, Seattle, USA, (计算机视觉顶会)
-
代表期刊论文
- Yang Zhang and Linlin Shen*. Automatic Learning Rate Adaption for Memristive Deep Learning Systems. IEEE Transactions on Neural Networks and Learning Systems, online, Jan. 2023. (IF 14.2)
- Weicheng Xie, Linlin Shen* and Jinming Duan. Adaptive Weighting of Hand-crafted Feature Losses for Facial Expression Recognition. IEEE Transactions on Cybernetics, Vol. 51(5), pp.2787-2800, May, 2021. (IF 19.1)
- Yang Zhang, Menglin Cui, Linlin Shen* and Zhigang Zeng. Memristive Quantized Neural Networks A Novel Approach to Accelerate Deep Learning On-Chip. IEEE Transactions on Cybernetics, Vol.51(4), pp.1875-1887, Apr. 2021. (IF 19.1)
- Yang Zhang, Menglin Cui, Linlin Shen* and Zhigang Zeng. Memristive Fuzzy Deep Learning Systems, IEEE Transactions on Fuzzy Systems, Vol.29(8), pp.2224-2238, Aug. 2021 (IF 12.2)
- Yuwu Lu, Wenjing Wang, Biqing Zeng, Zhihui Lai, Linlin Shen* and Xuelong Li. Canonical Correlation Analysis With Low-Rank Learning for Image Representation. IEEE Transactions on Image Processing, Vol. 31, pp. 7048-7062, Nov. 2022 ( IF 11.0)
- Qiufu Li, Linlin Shen*, Sheng Guo and Zhihui Lai. WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification. IEEE Transactions on Image Processing, Vol. 30, pp. 7074-7089, Aug. 2021 ( IF 11.0)
- Feng Liu, Haozhe Liu, Wentian Zhang, Guojie Liu and Linlin Shen*. One-Class Fingerprint Presentation Attack Detection Using Auto-Encoder Network. IEEE Transactions on Image Processing, Vol. 30, pp. 2394-2407, Jan. 2021 ( IF 11.0)
- Siyang Song, Zilong Shao, Shashank Jaiswal, Linlin Shen*, Michel Valstar and Hatice Gunes. Learning Person-specific Cognition from Facial Reactions for Automatic Personality Recognition, IEEE Transactions on Affective Computing, Vol. 14(4), pp.3048-3065, March. 2023. (IF 14.0)
- Siyang Song, Shashank Jaiswal, Enrique Sanchez, Georgios Tzimiropoulos, Linlin Shen* and Michel Valstar. Self-supervised Learning of Person-specific Facial Dynamics for Automatic Personality Recognition, IEEE Transactions on Affective Computing, Vol. 14(1), pp.178-195, March. 2023. (IF 14.0)
- Siyang Song, Shashank Jaiswal, Linlin Shen* and Michel Valstar. Spectral Representation of Behaviour Primitives for Depression Analysis. IEEE Transactions on Affective Computing. Vol. 13(2), pp.829-844, Jun. 2022 (2022 Best Paper Award Runner-up, IF 14.0)
- Qiufu Li, Linlin Shen*. 3D Neuron Reconstruction in Tangled Neuronal Image with Deep Networks.IEEE Transactions on Medical Imaging,Vol.39 (2), pp. 425-435, Feb. 2020. (IF 10.0)
- Weicheng Xie, Wenya Lu, Zhibin Peng and Linlin Shen*. Consistency preservation and feature regularization for GAN based face editing, IEEE Transactions on Multimedia, Vol.25, pp.8892-8905, Dec. 2023. (IF 8.2)
- Xianxun Hou, Xiaokang Zhang, Yudong Li and Linlin Shen*. TextFace: Text-to-Style Mapping based Face Generation and Manipulation, IEEE Transactions on Multimedia, Vol. 25, pp.3409-3419, Aug. 2023. (IF 8.2)
- Xianxu Hou, Xiaokang Zhang, Hanbang Liang, Linlin Shen* and Zhong Ming. Lifelong Age Transformation with a Deep Generative Prior, IEEE Transactions on Multimedia, Vol. 25, pp.3125-3139, Aug. 2023. (IF 8.2)
- Bing Li, Yuanlue Zhu, Yitong Wang, Chia-Wen Lin, Bernard Ghanem and Linlin Shen*, AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation, IEEE Transactions on Multimedia, Vol. 24, pp. 4077-4091, Aug. 2022. (IF 8.2)
- Xiaokang Zhang, Yuanlue Zhu, Wenting Chen, Wenshuang Liu and Linlin Shen*. Gated SwitchGAN for multi-domain facial image translation, IEEE Transactions on Multimedia, Vol. 24, pp.1990-2003, Apr. 2022. (IF 8.2)
- Shisong Lin, Mengchao Bai, Feng Liu, Linlin Shen* and Yicong Zhou. Orthogonalization-Guided Feature Fusion Network for Multimodal 2D+3D Facial Expression Recognition, IEEE Transactions on Multimedia, Vol.23, pp. 1581-1591, Jun. 2021.(IF 8.2)
- Junliang Chen, Weizeng Lu, Yuexiang Li, Linlin Shen* and Jinming Duan. Adversarial learning of Object-aware activation map for weakly-supervised semantic segmentation. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 30(8), pp. 3935-3946, Aug. 2023. (IF 8.4)
- Ziqi Jin, Bizhu Wu, Jinheng Xie and Linlin Shen*. Weakly Supervised Pedestrian Segmentation for Person Re-Identification. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 33 (3), pp. 1349-1362, March. 2023. (IF 8.4)
- Weicheng Xie, Haoqian Wu, Yi Tian, Mengchao Bai and Linlin Shen*. Triplet loss with multistage outlier suppression and class-pair margins for facial expression recognition. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 32 (2), pp. 690-703, Feb. 2022. (IF 8.4)
- Yuexiang Li, Linlin Shen*, Shiqi Yu. HEp-2 Specimen Image Segmentation and Classification Using Very Deep Fully Convolutional Network. IEEE Transactions on Medical Imaging. Vol. 36 (7), pp.1561-1572,July, 2017. (IF 6.1)
-
个人主页:/pages/user/index?id=594