-
概况
本人主要从Open FIESTA IID和数信院的人工智能、大数据三个方向招生
教育经历
2008中国科学院自动化所模式识别与智能系统博士
2002中国矿业大学控制工程硕士
1995中国矿业大学应用地球物理专业学士
工作经历
2023.12–至今 清华大学深圳国际研究生院,教授
2016.12–2023.11 清华大学深圳国际研究生院,副教授
2010.10–2016.12 清华大学深圳研究生院讲师,副教授
2008.07-2010.09 清华大学博士后
2002.07-2008.07 中国科学院自动化研究所助理研究员
学术兼职
2011.05 - 现在 Association for Computing Machinery(ACM)Member
2009.07 - 现在 Institute of Electrical and Electronics Engineers(IEEE)Member
2009.09 - 现在 中国计算机学会(CCF) 会员
2010.09 - 现在 CCF-YOCSEF深圳 AC委员
2010.04 - 现在 深圳市科技专家委员会 评审专家,
为下列期刊和国际会议担任程序委员会委员或审稿人:NeurIPS、ICML、ACL、EMNLP、NAACL、SIGKDD、CVPR、ECCV、AAAI
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
IEEE Transactions on Multimedia ( TMM )
IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
SCIENCE CHINA Information Sciences
IEEE Transactions on Knowledge and Data Engineering (TKDE)
IEEE Internet of Things Journal
IEEE Transactions on Parallel and Distributed Systems (TPDS)
IEEE Internet Computing
IEEE Computing in Science \& Engineering
IEEE Computer
International Journal of Machine Learning and Cybernetics
《计算机学报》
《自动化学报》
《电子与信息学报》
社会兼职
-
教学课程
开设课程:
《智能信息处理专题》
《统计学习理论导论》
《分布式机器学习》
主讲课程:
《大数据的采集与智能处理》(合讲)
Open FIESTA轮转课程
研究生指导
-
研究领域
课题组以机器学习、模式识别基本理论为基础,开展相应算法理论研究,并围绕智能交互的需求,探索AI在自然语言处理、视觉图像理解和分析等领域应用。课题组长期同腾讯AI Lab和华为诺亚方舟实验室开展合作。非常欢迎有志于人工智能方向的同学报考。
主要项目
国家自然科学基金委员会,重大项目,61991451,海洋散射光学图像重构理论、算法及评估方法研究,2020-1至2024-12,在研,任务负责人。
国家自然科学基金委员会,联合基金重点项目,U1903213,音视频多模态协同的异常事件鲁棒性检测关键技术研究,2020-1至2023-12,在研,课题负责人。
科技部,国家重点研发计划,2018YFB1601102,超大规模的广域时空交通知识聚合,2019-1至2022-12,在研,任务负责人。
科技部,国家重点研发计划,2020YFB1708200,基于多源异构信息的领域知识图谱及产品设计方法,2020-1至2023-12,在研,课题负责人。
广东省科技厅,基础研究项目,基于深度神经网络的聊天机器人内容生成技术,2019-10至2022-10,在研,主持。
企业横向,基础研究项目,图神经网络项目,2021-10至2023-10,在研,主持。
-
代表性论文
[1] Weihao Xia, Yulun Zhang, Yujiu Yang, Jing-Hao Xue, Bolei Zhou, Ming-Hsuan Yang:GAN Inversion: A Survey, in IEEE Transactions on Pattern Analysis and Machine Intelligence,. 45(3): 3121-3138 (2023) (CCF-A) (IF:24.314)
[2] Fei Yin, Yong Zhang, Baoyuan Wu, Yan Feng, Jingyi Zhang, Yanbo Fan, Yujiu Yang: Generalizable Black-Box Adversarial Attack With Meta Learning, in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 doi: 10.1109/TPAMI.2022.3194988. (CCF-A) (IF:24.314)
[3] Mingdeng Cao, Yanbo Fan, Yong Zhang, Jue Wang, Yujiu Yang: VDTR: Video Deblurring With Transformer. IEEE Trans. Circuits Syst. Video Technol. 33(1): 160-171 (2023) (IF:5.859)
[4] Shengjie Chen, Gang Wu, Yujiu Yang, Zhenhua Guo: A simple and effective patch-Based method for frame-level face anti-spoofing. Pattern Recognit. Lett. 171: 1-7 (2023) (IF:4.757)
[5] Lei Shi, Sheng Lan, Hao Gui, Yujiu Yang, Zhenhua Guo: A novel 2D contactless fingerprint matching method. Neurocomputing 500: 547-555 (2022) (IF:5.779)
[6] Ran Yu, Chenyu Tian, Weihao Xia, Xinyuan Zhao, Liejun Wang, Yujiu Yang: Real-time human-centric segmentation for complex video scenes. Image Vis. Comput. 126: 104552 (2022) (IF:3.86)
[7] Yiru Wang, Pengda Si, Zeyang Lei, Guangxu Xun, Yujiu Yang: HSCJN: A holistic semantic constraint joint network for diverse response generation. Comput. Speech Lang. 65: 101135 (2021) (IF:3.252)
[8] Weihao Xia, Yujiu Yang, Jing-Hao Xue: Cali-sketch: Stroke calibration and completion for high-quality face image generation from human-like sketches. Neurocomputing 460: 256-265 (2021) (IF:5.779)
[9] Weihao Xia, Yujiu Yang, Jing-Hao Xue, Jing Xiao: Domain Fingerprints for No-Reference Image Quality Assessment. IEEE Trans. Circuits Syst. Video Technol. 31(4): 1332-1341 (2021) (IF:5.859)
[10] Weihao Xia, Yujiu Yang, Jing-Hao Xue: Unsupervised multi-domain multimodal image-to-image translation with explicit domain-constrained disentanglement. Neural Networks 131: 50-63 (2020) (IF:9.657)
[11] Lifang Ding, Zeyang Lei, Guangxu Xun, Yujiu Yang: FAT-RE: A faster dependency-free model for relation extraction. J. Web Semant. 65: 100598 (2020) (IF:2.77)
会议论文:【更新文章】
[1] Xinyu Zhu, Junjie Wang, Lin Zhang, Yuxiang Zhang, Yongfeng Huang, ruyi gan, Jiaxing Zhang and Yujiu Yang:Solving Math Word Problems via Cooperative Reasoning induced Language Models;ACL2023.(CCF-A)
[2] Siheng Li, Yichun Yin, Cheng Yang, Wangjie Jiang, Yiwei Li, Zesen Cheng, Lifeng Shang, Xin Jiang, Qun Liu and Yujiu Yang:NewsDialogues: Towards Proactive News Grounded Conversation;ACL2023.(CCF-A)
[3] Siheng Li, Cheng Yang, Yichun Yin, Xinyu Zhu, Zesen Cheng, Lifeng Shang, Xin Jiang, Qun Liu and Yujiu Yang: AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models;ACL2023.(CCF-A)
[4] Zhibin Gou, qingyan guo and Yujiu Yang;Multi-view Prompting Improves Aspect Sentiment Tuple Prediction;ACL2023.(CCF-A)
[5] Jiaqi Sun, Lin Zhang, Guangyi Chen, Peng XU, Kun Zhang, Yujiu Yang: Feature Expansion for Graph Neural Networks; ICML23. (CCF-A)
[6] Xuanzhou Liu, Lin Zhang, Jiaqi Sun, Yujiu Yang, Haiqin Yang: D2Match: Leveraging Deep Learning and Degeneracy for Subgraph Matching; ICML23. (CCF-A)
[7] Fei Yin, Yong Zhang, Xuan Wang, Tengfei Wang, Xiaoyu Li, Yuan Gong, Yanbo Fan, Xiaodong Cun, Ying Shan, Cengiz Oztireli, Yujiu Yang:3D GAN Inversion with Facial Symmetry Prior;CVPR23 (CCF-A)
[8] Yatai Ji, Rong-Cheng Tu, jie jiang, Weijie Kong, Chengfei Cai, Wenzhe Zhao, WANG HongFa, Yujiu Yang, Wei Liu:Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning;CVPR23(CCF-A)
[9] Yatai Ji, Junjie Wang, Yuan Gong, Lin Zhang, yanru Zhu, WANG HongFa, Jiaxing Zhang, Tetsuya Sakai, Yujiu Yang:MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model;CVPR23(CCF-A)
[10] Qingyan Bai, Ceyuan Yang, Yinghao Xu, Xihui Liu, Yujiu Yang, Yujun Shen: GLeaD: Improving GANs with A Generator-Leading Task;CVPR23(CCF-A)
[11] Jiahao Wang, Songyang Zhang, Yong Liu, Taiqiang Wu, Yujiu Yang, Xihui Liu, Kai Chen, Ping Luo, Dahua Lin: RIFormer: Keep Your Vision Backbone Effective But Removing Token Mixer;CVPR23(CCF-A)
[12] Taiqiang Wu, Xingyu Bai, Weigang Guo, Weijie Liu, Siheng Li, Yujiu Yang: Modeling Fine-grained Information via Knowledge-aware Hierarchical Graph for Zero-shot Entity Retrieval. WSDM 2023: 1021-1029. (CCF-B)
[13] Shuwei Shi, Jinjin Gu, Liangbin Xie, Xintao Wang, Yujiu Yang, Chao Dong, Rethinking Alignment in Video Super-Resolution Transformers. Advances in Neural Information Processing Systems (NeurIPS), 2022. (CCF-A)
[14] Wangjie Jiang, Zhihao Ye, Zijing Ou, Ruihui Zhao, Jianguang Zheng, Yi Liu, Bang Liu, Siheng Li, Yujiu Yang, Yefeng Zheng: MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction. CIKM 2022: 4084-4088(CCF-B)
[15] Mingdeng Cao, Zhihang Zhong, Jiahao Wang, Yinqiang Zheng, Yujiu Yang: Learning Adaptive Warping for RealWorld Rolling Shutter Correction. CVPR 2022: 17764-17772 (CCF-A)
[16] Shanshan Lao, Yuan Gong, Shuwei Shi, Sidi Yang, Tianhe Wu, Jiahao Wang, Weihao Xia, Yujiu Yang: Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network. CVPR Workshops 2022: 1139-1148 (The track champion)
[17] Sidi Yang, Tianhe Wu, Shuwei Shi, Shanshan Lao, Yuan Gong, Mingdeng Cao, Jiahao Wang, Yujiu Yang: MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment. CVPR Workshops 2022: 1190-1199 (The track champion)
[18] Yong Liu, Ran Yu, Fei Yin, Xinyuan Zhao, Wei Zhao, Weihao Xia, and Yujiu Yang:Learning Quality-aware Dynamic Memory for Video Object Segmentation;ECCV (29) 2022: 468-486 (CCF-B)
[19] Yong Liu, Ran Yu, Jiahao Wang, Xinyuan Zhao, Yitong Wang, Yansong Tang, and Yujiu Yang:Global Spectral Filter Memory Network for Video Object Segmentation;ECCV (29) 2022: 648-665 (CCF-B)
[20] Qingyan Bai, Yinghao Xu, Jiapeng Zhu, Weihao Xia, Yujiu Yang, Yujun Shen: High-fidelity GAN Inversion with Padding Space;ECCV (15) 2022: 36-53(CCF-B)
[21] Fei Yin, Yong Zhang, Xiaodong Cun, Mingdeng Cao, Yanbo Fan, Xuan Wang, Qingyan Bai, Baoyuan Wu, Jue Wang, Yujiu Yang: StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN;ECCV (17) 2022: 85-101 (CCF-B)
[22] Xiaopei Wan , Guoqiu Li , Yujiu Yang and Zhenhua Guo: Augmenting Anchors by the Detector Itself;IJCAI 22: 1371-1377 (CCF-A)
[23] Mao Yan Chen and Siheng Li and Yujiu Yang: EmpHi: Generating Empathetic Responses with Human-like Intents, NAACL2022: 1063-1074 (CCF-B)
[24] Jiahao Wang, Mingdeng Cao, Shuwei Shi, Baoyuan Wu, Yujiu Yang: Attention Probe: Vision Transformer Distillation in the Wild;ICASSP22, 2220-2224. (CCF-B)
[25] Wangjie Jiang∗, Siheng Li∗, Jiayi Li, Yujiu Yang: Multi-Turn incomplete Utterance Restoration as Object Detection;ICASSP22, 8052-8056. (CCF-B)
[26] Han Shu,Jiahao Wang,Hanting Chen, Lin Li,Yujiu Yang,Yunhe Wang:Adder Attention for Vision Transformer,(NeurIPS2021) Advances in Neural Information Processing Systems 34, 19899-19909 (CCF-A)
[27] Junjie Wang, Yatai Ji, Jiaqi Sun, Yujiu Yang and Tetsuya Sakai:MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering,EMNLP (Findings) 2021: 2280-2292. (CCF-B)
[28] Gengcong Yang, Jingyi Zhang, Yong Zhang, Baoyuan Wu, Yujiu Yang: Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation. Virtual June19-25, CVPR2021: 12527-12536. (CCF-A)
[29] Weihao Xia, Yujiu Yang, Jing-Hao Xue, Baoyuan Wu: TediGAN: Text-Guided Diverse Image Generation and Manipulation. Virtual June19-25, CVPR2021: 2256-2265. (CCF-A)
[30] Yutong Wang, Renze Lou, Kai Zhang, Mao Yan Chen, Yujiu Yang: More: A Metric Learning Based Framework for Open-Domain Relation Extraction. ICASSP 2021: 7698-7702. (CCF-B)
[31] Yiru Wang; Shen Huang; Gongfu Li; Qiang Deng; Dongliang Liao; Pengda Si; Yujiu Yang; Jin Xu. Cognitive Representation Learning of Self-Media Online Article Quality,ACM Multimedia,12-16 October 2020 Seattle, United States. (CCF-A)
[32] Weihao Xia*; Yujiu Yang; Jing-Hao Xue: Controllable Continuous Gaze Redirection. ACM Multimedia,12-16 October 2020 Seattle, United States. (CCF-A)
[33] Shuwei Shi, Qingyan Bai, Mingdeng Cao, Weihao Xia, Jiahao Wang, Yifan Chen, Yujiu Yang: Region-Adaptive Deformable Network for Image Quality Assessment. CVPR Workshops 2021: 324-333
[34] Yue Wu, Yui Lo, Yujiu Yang: STCN: A Lightweight Sleep Staging Model with Multiple Channels. BIBM 2020: 1180-1183 (CCF-B)
[35] Sijin Wu, Yujiu Yang, Nicholas Yung, Zhengchen Shen, Zeyang Lei: DT-QDC: A Dataset for Question Comprehension in Online Test. COLING 2020: 6470-6480 (CCF-B)
[36] Yanbo Fan, Baoyuan Wu, Tuanhui Li, Yong Zhang, Mingyang Li, Zhifeng Li, Yujiu Yang: Sparse Adversarial Attack via Perturbation Factorization,16th European Conference on Computer Vision (ECCV), 23-28 August, 2020. (CCF-B)
[37] Yunzhou Shi, Zhiling Luo, Pengcheng Zhu, Feng Ji, Wei Zhou, Haiqing Chen and Yujiu Yang. G2T: Generating Fluent Descriptions for Knowledge Graph [C] ACM SIGIR 2020, July 25-30, 2020 (Xi'an, China), pages 1861-1864. (CCF-A)
[38] Miaomiao Yu, Yujiu Yang, Chenhui Li: HGCN4MeSH: Hybrid Graph Convolution Network for MeSH Indexing. ACL (student) 2020: 20-26; (CCF-A)
[39] Yiru Wang, Pengda Si, Zeyang Lei, Yujiu Yang: Topic Enhanced Controllable CVAE for Dialogue Generation (Student Abstract). AAAI 2020: 13955-13956; (CCF-A)
[40] Tuanhui Li, Baoyuan Wu, Yujiu Yang, Yanbo Fan, Yong Zhang, Wei Liu; Compressing Convolutional Neural Networks via Factorized Convolutional Filters The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 3977-3986;(CCF-A)
[41] Xinrui Zhuang, Yuexiang Li, Yifan Hu, Kai Ma, Yujiu Yang, Yefeng Zheng: Self-supervised Feature Learning for 3D Medical Images by Playing a Rubik's Cube. MICCAI (4) 2019: 420-428 (学生旅行奖)
[42] Guanqun Hou, Yujiu Yang, Jing-Hao Xue: Residual Dilated Network with Attention for Image Blind Denoising. ICME 2019: 248-253 (CCF-B)
[43] Weihao Xia, Yujiu Yang, Xianyu Bao: ECGAN: Image Translation with Multi-scale Relativistic Average Discriminator. AIMS 2019: 28-38 (Best student paper)
[44] Zeyang Lei, Yujiu Yang, Min Yang, Wei Zhao, Jun Guo, Yi Liu: A Human-Like Semantic Cognition Network for Aspect-Level Sentiment Classification. AAAI 2019: 6650-6657 (CCF-A)
[45] Zeyang Lei, Yujiu Yang, Min Yang, Yi Liu; A Multi-sentiment-resource Enhanced Attention Network for Sentiment Classification. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL (2) 2018: 758-763; (CCF-A)
[46] Zeyang Lei, Yujiu Yang, Yi Liu; LAAN: A Linguistic-Aware Attention Network for Sentiment Analysis, WWW ’18 Companion, April 23–27, 2018, Lyon, France; (CCF-A)
[47] Zeyang Lei, Yujiu Yang, Min Yang; SAAN: A Sentiment-Aware Attention Network for Sentiment Analysis. SIGIR 2018: 1197-1200 (CCF-A)
[48] Zeyang Lei, Yujiu Yang, Min Yang; Sentiment Lexicon Enhanced Attention-based LSTM for Sentiment Classification, The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) , 2018.2.2-2018.2.7 (CCF-A)
代表性著作
主要专利成果
[1] 杨余久,张如意,邵航,黄旭; 一种无人机救援系统及其搜救方法,中国,ZL 2016 1 0047601.7。授权时间:2018.12.21
[2] 杨余久,黄旭; 一种层次化商品信息过滤推荐方法,中国,ZL 2016 1 0112904.2 授权时间:2018.10.30
[3] 杨余久,袁威强; 商品属性特征词聚类方法,中国,ZL 2015 1 0638459.9 授权时间:2020.11.17
[4] 杨余久,胡源航, 邵航,金舟. 一种基于协同过滤的在线打车推荐方法,中国, ZL 2016 1 0643458.8 授权时间:2019.12.03
[5] 杨余久,金舟,邵航,黄旭. 一种社交网络用户情绪判别方法, 中国, ZL 2016 1 0204531.1 授权时间:2019.06.28
[6] 杨余久, 庄新瑞, 杨芳,一种基于多注意力机制的端到端的脑部肿瘤分割方法, 中国, ZL 2019 1 0002630.5 授权时间:2020.9.1
[7] 杨余久,王艺如,杨芳, 对话机器人的回复内容生成方法和终端设备, ZL 2019 1 0244935.7 授权时间:2020.11.24
[8] 杨余久,胡晓翔; 一种基于目标和相机运动建模的目标跟踪方法, ZL 2018 1 1307972.X 授权时间:2020.7.28
[9] 杨余久、庄新瑞、杨芳:一种基于公私钥对的深度学习模型水印的嵌入和提取方法,ZL 2020 1 0197449.7 授权时间:2022.9.16
[10] 龚德政、杨余久、杨芳:一种基于动态标签调整的弱监督目标检测算法,ZL 2021 1 0548236.9 授权时间:2022.9.6
其他成果
软件著作权:
(1)杨余久,尹宾,胡源航,吴过,MovieRecommended软件V1.0,中国, 2014/12/30
标准:
(1)云制造 服务分类 GB/T 35586-2017 (国家标准);
(2)跨境电子商务产品质量信息数据规范 SN/T 4900-2017 (行业标准)
(3)检验检疫信息系统分析建模规范 SN/T 4901-2017 (行业标准)
(4)信息化系统监控管理规范 SN/T 5025-2017 (行业标准)
-
荣誉奖项
[1] 肖京,杨余久,汪伟,徐冰,王好谦,王磊,徐亮,王健宗,陈又新,郭振华,刘懿祺,谭韬,雷泽阳,张宇辰: 基于时序知识图谱的金融风控与经济量化决策平台产业化, 第十届吴文俊人工智能科技进步奖一等奖,2020
[2] 杨余久; 方炎林; 赵宏田; 郭振华; 王好谦; 董海鸥; 李秀; 冯传宏;移动健康管理采集终端设备关键技术研发及产业化,2017年广东省科技进步三等奖(第一完成人)
[3] 戴琼海; 王好谦; 范静涛; 张永兵; 张 磊; 金欣; 黄道权; 申优桦; 杨余久; 郭振华; 李秀; 王兴政; 韦建端; 黄建兴;动态立体视觉系统关键技术及应用,2015年广东省科技进步一等奖
[4] 杨余久; 方炎林; 赵宏田; 郭振华; 王好谦; 董海鸥; 李秀; 冯传宏;移动健康管理采集终端设备关键技术研发及产业化,2015年深圳市科技进步二等奖(第一完成人)