基本信息

陈盈盈  女    中国科学院自动化研究所
电子邮件：yingying.chen@nlpr.ia.ac.cn
通信地址：中关村东路95号
邮政编码：100190

个人介绍

陈盈盈，中国科学院自动化研究所项目研究员。专注于视觉语义理解、多模态大模型，科学智能方面的研究。主持和参与国家级重大科研项目十余项（包括国家科技部新一代人工智能国家科技重大专项课题、国家自然科学基金、中国科学院战略性先导科技专项课题等）。在相关领域取得多项突破性进展，已发表高水平国际学术论文50余篇，包括在IEEE TIP、CVPR、ICCV、AAAI、IJCAI等顶级国际期刊和会议（CCF-A类）论文20余篇。已授权国家发明专利20余项，参与制定行业/团体标准多项。

研究成果获得了学术界和产业界的广泛认可，荣获吴文俊人工智能科技进步二等奖、世界人工智能大会最高奖SAIL奖（最高奖）、中国科学院科苑名匠团队、中国科学院北京分院科技成果转化二等奖、首届中国西部巾帼科技创新大赛银奖等10余项荣誉。

指导学生参与国内外高水平学术竞赛，累计获得冠军10余项，代表性成果包括：全球人工智能挑战赛第一名、CVPR 2024视觉异常和创新性检测国际竞赛(VAND2.0 Challenge) 第一名等。

作为项目负责人或实际完成人将核心技术赋能人工智能应用场景，完成企业委托项目20余项。

最新动态

2025年要闻：

[2025-05]科学传播|天文耀发预测大模型FLARE被新华社报道。[链接]
[2025-05]学术进展|智能体交互协议 (Agent Interaction Protocol, AIP) 发布。[代码]
[2025-04]学术进展|FLARE: A Framework for Stellar Flare Forecasting using Stellar Physical Properties and Historical Records被IJCAI2025接收。[论文]
[2025-03]学术进展|UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection被CVPR 2025接收。[论文|代码]
[2025-01]科学传播|受科技日报《科技π》栏目邀请录制“科技有AI 智能向善”系列访谈第二期。[链接]

更早：已折叠

招生信息

招生方向：视觉语义理解，目标运动与行为分析，AI for Science

招生专业：081104-模式识别与智能系统

招生状态：长期招收对人工智能、AI4S交叉领域研究充满热情的研究生、实习生。

专业背景要求：计算机科学、生物科学、电气信息、自动化、神经科学、心理学、应用数学等相关专业背景。

基础素质要求：具备强烈的科研兴趣、自主学习能力、批判性思维、良好的沟通能力和团队协作精神。

申请方式： 有意申请者请将您的简历（含成绩单、研究经历、已发表论文等）发送至我的邮箱：yingying.chen@nlpr.ia.ac.cn，邮件主题请注明“[博士/硕士/实习生申请]-姓名-毕业院校”。

课题组情况：https://nlpr.ia.ac.cn/iva/homepage/jqwang/index.htm。课题组长期与国内外高水平大学、AI研究机构保持密切合作，包括新加坡国立大学、澳大利亚悉尼科技大学、清华大学、中国科学技术大学、东南大学、鹏城实验室、武汉人工智能研究院等。

工作经历

工作简历：
2025-02~现在, 中国科学院自动化研究所, 项目研究员
2022-04~2025-02,中国科学院自动化研究所, 副研究员
2018-07~2022-04,中国科学院自动化研究所, 助理研究员
社会兼职：
中国图像图形学学会多媒体专业委员会委员
中国技术创业协会技术创新工作委员会委员
中国技术创业协会，技术创新工作委员会委员

论文发表

  1. Bingke Zhu, Zhaopeng Gu, Guibo Zhu, Yingying Chen, Ming Tang, Jinqiao Wang:ADFormer: Generalizable Few-Shot Anomaly Detection With Dual CNN-Transformer Architecture. IEEE Trans. Instrum. Meas. 74: 1-16 (2025)

  2. Zhaopeng Gu, Bingke Zhu, Guibo Zhu, Yingying Chen, Ming Tang, Jinqiao Wang:UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection. CVPR (2025)

  3. Bingke Zhu, Xiaoxiao Wang, Minghui Jia, Yihan Tao, Xiao Kong, Ali Luo, Yingying Chen, Ming Tang, Jinqiao Wang:FLARE: A Framework for Stellar Flare Forecasting using Stellar Physical Properties and Historical Records. IJCAI (2025)

  4. Zhaopeng Gu, Bingke Zhu, Guibo Zhu, Yingying Chen, Ming Tang, Jinqiao Wang:FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization. Arxiv (2025)

  5. Yingtao Tan, Yingying Chen, Jinqiao Wang: DSTA: Reinforcing Vision-Language Understanding for Scene-Text VQA With Dual-Stream Training Approach. IEEE Signal Process. Lett. 32: 6-10 (2025)

  6. Lu Zhou, Yingying Chen, Jinqiao Wang:Dual-Path Transformer for 3D Human Pose Estimation. IEEE Trans. Circuits Syst. Video Technol. 34(5): 3260-3270 (2024)

  7. Haixin Wang, Lu Zhou, Yingying Chen, Zhiyang Chen, Ming Tang, Jinqiao Wang:EFCPose: End-to-End Multi-Person Pose Estimation With Fully Convolutional Heads. IEEE Trans. Circuits Syst. Video Technol. 34(7): 6039-6050 (2024)

  8. Zhaopeng Gu, Bingke Zhu, Guibo Zhu, Yingying Chen, Ming Tang, Jinqiao Wang:AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models. AAAI 2024: 1932-1940

  9. Zhaopeng Gu, Bingke Zhu, Guibo Zhu, Yingying Chen, Hao Li, Ming Tang, Jinqiao Wang:FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization. ACM Multimedia 2024: 2041-2049

  10. Lu Zhou, Yingying Chen, Jinqiao Wang:SlowFastFormer for 3D human pose estimation. Comput. Vis. Image Underst. 243: 103992 (2024)

  11. Bingke Zhu, Yingying Chen, Ming Tang, Jinqiao Wang:Pixel-Level Contrastive Pretrainer for Industrial Image Representation. IEEE Trans. Instrum. Meas. 73: 1-13 (2024)

  12. Lu Zhou, Yingying Chen, Jinqiao Wang:Progressive Direction-Aware Pose Grammar for Human Pose Estimation. IEEE Trans. Biom. Behav. Identity Sci. 5(4): 593-605 (2023)

  13. Xiaomei Zhang, Yingying Chen, Ming Tang, Jinqiao Wang, Xiangyu Zhu, Zhen Lei:Human Parsing With Part-Aware Relation Modeling. IEEE Trans. Multim. 25: 2601-2612 (2023)

  14. Jinyi Fang, Bingke Zhu, Yingying Chen, Jinqiao Wang, Ming Tang:Explicit Attention Modeling for Pedestrian Attribute Recognition. ICME 2023: 2075-2080

  15. Yuanbing Zhu, Bingke Zhu, Yingying Chen, Jinqiao Wang:Uncertainty-Aware Boundary Attention Network for Real-Time Semantic Segmentation. PRCV (3) 2023: 388-400

  16. Xiaomei Zhang, Yingying Chen, Ming Tang, Zhen Lei, Jinqiao Wang:Grammar-Induced Wavelet Network for Human Parsing. IEEE Trans. Image Process. 31: 4502-4514 (2022)

  17. Zhaowen Li, Yousong Zhu, Fan Yang, Wei Li, Chaoyang Zhao, Yingying Chen, Zhiyang Chen, Jiahao Xie, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang:UniVIP: A Unified Framework for Self-Supervised Visual Pre-training. CVPR 2022: 14607-14616

  18. Tong Wang, Yousong Zhu, Yingying Chen, Chaoyang Zhao, Bin Yu, Jinqiao Wang, Ming Tang: C2AM Loss: Chasing a Better Decision Boundary for Long-Tail Object Detection. CVPR 2022: 6970-6979

  19. Haixin Wang, Lu Zhou, Yingying Chen, Ming Tang, Jinqiao Wang: Regularizing Vector Embedding in Bottom-Up Human Pose Estimation. ECCV (6) 2022: 107-122

  20. Suqin Wang, Lu Zhou, Yingying Chen, Jiangtao Huo, Jinqiao Wang: When Skeleton Meets Appearance: Adaptive Appearance Information Enhancement for Skeleton Based Action Recognition. ICME 2022: 1-6

  21. Lu Zhou, Yingying Chen, Congqi Cao, Yakui Chu, Jinqiao Wang, Hanqing Lu: Macro-micro mutual learning inside compositional model for human pose estimation. Neurocomputing 449: 176-188 (2021)

  22. Lu Zhou, Yingying Chen, Congqi Cao, Jinqiao Wang, Hanqing Lu: STN-enhanced message passing guided by adversarial learning for human pose estimation. Neurocomputing 453: 60-72 (2021)

  23. Linyu Zheng, Ming Tang, Yingying Chen, Guibo Zhu, Jinqiao Wang, Hanqing Lu: Improving Multiple Object Tracking With Single Object Tracking. CVPR 2021: 2453-2462

  24. Yunze Gao, Yingying Chen, Jinqiao Wang, Hanqing Lu: Progressive rectification network for irregular text recognition. Sci. China Inf. Sci. 63(2): 120101 (2020)

  25. Xiaomei Zhang, Yingying Chen, Bingke Zhu, Jinqiao Wang, Ming Tang: Semantic-spatial fusion network for human parsing. Neurocomputing 402: 375-383 (2020)

  26. Linyu Zheng, Yingying Chen, Ming Tang, Jinqiao Wang, Hanqing Lu: Siamese Deformable Cross-Correlation Network for Real-Time Visual Tracking. Neurocomputing 401: 36-47 (2020)

  27. Lu Zhou, Yingying Chen, Jinqiao Wang, Hanqing Lu: Progressive Bi-C3D Pose Grammar for Human Pose Estimation. AAAI 2020: 13033-13040

  28. Xiaomei Zhang, Yingying Chen, Bingke Zhu, Jinqiao Wang, Ming Tang: Part-Aware Context Network for Human Parsing. CVPR 2020: 8968-8977

  29. Xiaomei Zhang, Yingying Chen, Bingke Zhu, Jinqiao Wang, Ming Tang: Blended Grammar Network for Human Parsing. ECCV (24) 2020: 189-205

  30. Linyu Zheng, Ming Tang, Yingying Chen, Jinqiao Wang, Hanqing Lu: Learning Feature Embeddings for Discriminant Model Based Tracking. ECCV (15) 2020: 759-775

  31. Lu Zhou, Yingying Chen, Yunze Gao, Jinqiao Wang, Hanqing Lu: Occlusion-Aware Siamese Network for Human Pose Estimation. ECCV (20) 2020: 396-412

  32. Linyu Zheng, Ming Tang, Yingying Chen, Jinqiao Wang, Hanqing Lu: High-Speed And Accurate Scale Estimation For Visual Tracking With Gaussian Process Regression. ICME 2020: 1-6

  33. Yunze Gao, Yingying Chen, Jinqiao Wang, Ming Tang, Hanqing Lu: Reading scene text with fully convolutional sequence modeling. Neurocomputing 339: 161-170 (2019)

  34. Yingying Chen, Jinqiao Wang, Bingke Zhu, Ming Tang, Hanqing Lu: Pixelwise Deep Sequence Learning for Moving Object Detection. IEEE Trans. Circuits Syst. Video Technol. 29(9): 2567-2579 (2019)

  35. Yunze Gao, Yingying Chen, Jinqiao Wang, Hanqing Lu: Gate-based Bidirectional Interactive Decoding Network for Scene Text Recognition. CIKM 2019: 2273-2276

  36. Linyu Zheng, Ming Tang, Yingying Chen, Jinqiao Wang, Hanqing Lu: Fast-deepKCF Without Boundary Effect. ICCV 2019: 4019-4028

  37. Sufang Zhang, Qinghai Miao, Min Huang, Xiangyu Zhu, Yingying Chen, Zhen Lei, Jinqiao Wang: Pose-Weighted Gan for Photorealistic Face Frontalization. ICIP 2019: 2384-2388

  38. Lu Zhou, Yingying Chen, Jinqiao Wang, Ming Tang, Hanqing Lu: Bi-Directional Message Passing Based Scanet for Human Pose Estimation. ICME 2019: 1048-1053

  39. Quan Liu, Yingying Chen, Jinqiao Wang, Sijiong Zhang: Multi-view pedestrian captioning with an attention topic CNN model. Comput. Ind. 97: 47-53 (2018)

  40. Bingke Zhu, Yingying Chen, Ming Tang, Jinqiao Wang: Progressive Cognitive Human Parsing. AAAI 2018: 7607-7614

  41. Yunze Gao, Yingying Chen, Jinqiao Wang, Ming Tang, Hanqing Lu: Dense Chained Attention Network for Scene Text Recognition. ICIP 2018: 679-683

  42. Xiaomei Zhang, Yingying Chen, Bingke Zhu, Jinqiao Wang, Ming Tang, Hanqing Lu: Tree Hierarchical CNNs for Object Parsing. ICIP 2018: 1588-1592

  43. Quan Liu, Yingying Chen, Jinqiao Wang, Sijiong Zhang: Joint Visual Context for Pedestrian Captioning. ICIMCS 2017: 45-53

  44. Xu Zhao, Yingying Chen, Ming Tang, Jinqiao Wang: Joint background reconstruction and foreground segmentation via a two-stage convolutional neural network. ICME 2017: 343-348

  45. Bingke Zhu, Yingying Chen, Jinqiao Wang, Si Liu, Bo Zhang, Ming Tang: Fast Deep Matting for Portrait Animation on Mobile Phone. ACM Multimedia 2017: 297-305

  46. Yingying Chen, Jinqiao Wang, Min Xu, Xiangjian He, Hanqing Lu: A unified model sharing framework for moving object detection. Signal Process. 124: 72-80 (2016)

  47. Jinqiao Wang, Zhan Qu, Yingying Chen, Tao Mei, Min Xu, La Zhang, Hanqing Lu: Adaptive Content Condensation Based on Grid Optimization for Thumbnail Image Generation. IEEE Trans. Circuits Syst. Video Technol. 26(11): 2079-2092 (2016)

  48. Yingying Chen, La Zhang, Jinqiao Wang, Hanqing Lu: Piecewise Video Condensation for Complex Scenes. ACCV Workshops (3) 2016: 286-300

  49. Jun Luo, Jinqiao Wang, La Zhang, Yingying Chen, Huazhong Xu, Hanqing Lu: 60 Hz self-tuning background modeling. ICIMCS 2015: 78:1-78:4

  50. Yingying Chen, Jinqiao Wang, Jianqiang Li, Hanqing Lu: Multiple features based shared models for background subtraction. ICIP 2015: 3946-3950

  51. Yingying Chen, Jinqiao Wang, Hanqing Lu: Learning sharable models for robust background subtraction. ICME 2015: 1-6

  52. Yingying Chen, Jinqiao Wang, Jing Liu, Hanqing Lu: Mobile Media Thumbnailing. ICMR 2015: 665-666

       ...


学生指导

2016.9-2021.6，朱炳科，博士研究生，模式识别与智能系统，发表论文7篇（包括顶会ACM MM, AAAI等）。获自动化研究所攀登二等奖学金，获得发明专利授权3项，学术。

2016.9-2021.6，周鲁，博士研究生，模式识别与智能系统，指导发表论文5篇（包括AAAI,ECCV等），获得发明专利授权2项。

2016.9-2021.6，张小梅，博士研究生，模式识别与智能系统，指导发表论文6篇（包括TIP, TMM,CVPR等），获得发明专利授权1项，中科院自动化研究所攀登二等奖学金。

2020.9-2024.6，王海鑫，博士研究生，模式识别与智能系统，指导发表论文3篇（包括TCSVT,ECCV,MIR），获得发明专利授权1项，

2020-至今，谭颖韬，博士研究生，模式识别与智能系统，指导发表论文2篇。

2022-至今，古兆鹏，博士研究生，模式识别与智能系统，指导发表论文3篇（AAAI, ACM MM），

2023-至今，王林歌，博士研究生，模式识别与智能系统

2024-至今，高涓茹，硕士研究生，人工智能