刘宏

职称:教授
电话:
办公室:A329
Email:liuh@pkusz.edu.cn
实验室网站:http://robotics.pkusz.edu.cn
研究方向:1、计算机视觉与智能机器人; 2、机器学习与智能人机交互。
职称 教授 电话
办公室 A329 Email liuh@pkusz.edu.cn
研究方向 1、计算机视觉与智能机器人; 2、机器学习与智能人机交互。 实验室网站 http://robotics.pkusz.edu.cn

导师与研究领域、方向:

刘宏,工学博士,北京大学教授,博士生导师。国家首批科技创新领军人才,科技部国家重点研发计划“智能机器人”总体专家组专家,中国人工智能学会副理事长,深圳市第六届政协委员。

长期从事计算机视觉与智能机器人、机器学习与智能人机交互等领域的教学和科研工作。曾师从蔡鹤皋院士、王选院士、石青云院士等知名专家。多次赴美国、加拿大、日本和新加坡等国家的多所著名大学和研究机构访问交流。

先后承担 20余项国家级重要科研项目,包括863课题、 973课题、国家重点研发计划项目、新一代人工智能重大项目和国家自然科学基金重点项目等。已发表学术论文200多篇,近年的研究成果被国内外同行研究机构引用5000余次,相关成果申报/获得国家发明专利40余项。获国家航天科技进步奖、吴文俊人工智能科学技术奖、日内瓦国际发明博览会奖、北京大学教学优秀奖、安泰奖和北京大学“十佳教师” 候选人等荣誉。

作为深圳教育界首位国家科技创新领军人才,二十多年来刘宏教授专注于所热爱的人工智能和机器人事业,先后培养了100多名硕士博士研究生和博士后,是我国“智能科学与技术”新学科建设的积极倡导者、智能机器人领域科技创新的潜心实践者。“十四五”期间刘宏教授的研究特色将聚焦在“机器人视觉感知与自主学习”等领域。

近年承担的主要科研项目:

  • 国家新一代人工智能重大项目:基于数字孪生的室内服务机器人自主学习与进化关键技术 (在研)

  • 国家重点研发计划项目:面向智能手机制造的柔性机器人自动化生产线研制及示范应用 (在研、 指导)

  • 国家自然科学基金项目:面向混合增强智能运动规划的机器人位姿空间建模方法(在研)

  • 深圳市基础研究重点项目:基于情感计算人和机器人交互模型研究 (在研)

  • 深圳市高等院校稳定支持计划重点项目:面向复杂场景机器人高效作业的混合增强智能 (在研)

  • 国家自然科学基金(联合基金)重点项目:面向服务机器人的视听感知融合与多模态人机交互关键技术 (已完成)

  • 国家自然科学基金项目:基于麦克风阵列的移动机器人实时声源定位方法研究(已完成)

  • 国家自然科学基金项目:人机互动环境下机器人实时运动规划研究(已完成)

  • 国家自然科学基金项目:面向人体目标实时跟踪的视觉注意转移机制研究(已完成)

  • 国家863课题:面向HRI的机器人视听觉注意机制及运动规划技术(已完成)

  • 国家863课题:基于多源信息融合的交通事件自动检测技术(已完成)

  • 科技部创新人才推进计划:面向复杂场景人机交互的嵌入式仿生视觉技术(已完成)

  • 教育部博士点基金课题:面向显著事件主动感知的仿生立体视觉研究(已完成)

  • 广东省重大产业攻关项目:新一代家用服务机器人关键技术突破及集成应用示范(已完成)

  • 深圳市“创新链-产业链”双链融合重大产业化项目:智能电视生产流水线的视觉检测和定位方法 (已完成)

  • 深圳市战略新兴产业项目:网络环境下智能监控系统公共技术平台(已完成)

  • 深圳市战略新兴产业项目:物联网智能感知技术工程实验室(已完成)

  • 深圳市基础研究重点项目:面向复杂场景人机交互的仿生视觉技术与系统(已完成)


近年发表的主要学术论文:

[1] Wenhao Li, Hong Liu(刘宏), Runwei Ding, Mengyuan Liu, Pichao Wang and Wenming Yang. Exploiting temporal contexts with strided transformer for 3d human pose estimation. IEEE Transactions on Multimedia(TMM). Accepted in 2022.(多媒体领域顶级国际学术期刊)

[2] Wei Shi, Hong Liu(刘宏), and Mengyuan Liu. Image-to-video person re-identification using three-dimensional semantic appearance alignment and cross-modal interactive learning. Pattern Recognition(PR), 2022, 122: 108314.(模式识别领域顶级国际学术期刊)

[3] Weibo Huang and Hong Liu(刘宏). A robust pixel-aware gyro-aided KLT feature tracker for large camera motions. IEEE Transactions on Instrumentation and Measurement(TIM), 2022, 71: 1-14. (机器智能领域重要国际学术期刊)

[4] Bing Yang, Hong Liu(刘宏), and Xiaofei Li. Learning deep direct-path relative transfer function for binaural sound source localization. IEEE/ACM Transactions on Audio, Speech, and Language Processing(TASLP), 2021, 29: 3491-3503.(机器听觉领域顶级国际学术期刊)

[5] Meijia Song, Hong Liu(刘宏), Wei Shi, and Xia Li. PCLoss: Fashion Landmark Estimation with Position Constraint Loss. Pattern Recognition(PR), 2021, 118: 108028.(模式识别领域顶级国际学术期刊)

[6] Hao Tang, Hong Liu(刘宏), Dan Xu, Philip HS Torr, and Nicu Sebe. Attentiongan: Unpaired image-to-image translation using attention-guided generative adversarial networks. IEEE Transactions on Neural Networks and Learning Systems(TNNLS), 2021, 1-16.(人工智能领域顶级国际学术期刊)

[7] Hanrong Ye, Hong Liu(刘宏), Fanyang Meng, and Xia Li. Bi-Directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification. IEEE Transactions on Image Processing(TIP), 2021, 30:1583-1595. (人工智能领域顶级国际学术期刊)

[8] Hao Tang, Hong Liu(刘宏), Wei Xiao, and Nicu Sebe. When Dictionary Learning Meets Deep Learning: Deep Dictionary Learning and Coding Network for Image Recognition With Limited Data. IEEE Transactions on Neural Networks and Learning Systems(TNNLS), 2021, 32(5): 2129-2141.(人工智能领域顶级国际学术期刊)

[9] Weibo Huang, Hong Liu(刘宏), and Weiwei Wan. An Online Initialization and Self-Calibration Method for Stereo Visual-Inertial Odometry. IEEE Transactions on Robotics(TRO), 2020, 36(4): 1153-1170.(机器人领域顶级国际学术期刊)

[10] Jie Wen, Yong Xu, and Hong Liu(刘宏). Incomplete Multiview Spectral Clustering With Adaptive Graph Learning. IEEE Transactions on Cybernetics(TCYB), 2020, 50(4): 1418-1429.(人工智能领域顶级国际学术期刊)

[11] Hao Tang, Hong Liu(刘宏), and Nicu Sebe. Unified Generative Adversarial Networks for Controllable Image-to-Image Translation. IEEE Transactions on Image Processing(TIP), 2020, 29: 8916-8929.(人工智能领域顶级国际学术期刊)

[12] Hanrong Ye, Hong Liu(刘宏), Fanyang Meng and Xia Li. Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification. IEEE Transactions on Image Processing(TIP), 2020, 30: 1583-1595.(人工智能领域顶级国际学术期刊)

[13] Jiayao Ma, Weiwei Wan, Kensuke Harada, Qiuguo Zhu, and Hong Liu(刘宏). Regrasp Planning Using Stable Object Poses Supported by Complex Structures. IEEE Transactions on Cognitive and Developmental Systems(TCDS), 2019, 11(2): 257-269.(人工智能领域重要国际学术期刊)

[14] Bing Yang, Hong Liu(刘宏), Cheng Pang and Xiaofei Li. Multiple Sound Source Counting and Localization Based on TF-Wise Spatial Spectrum Clustering. IEEE/ACM Transactions on Audio, Speech and Language Processing(TASLP), 2019, 27(8):1241-1255.(机器听觉领域顶级国际学术期刊)

[15] Fanyang Meng, Hong Liu(刘宏), Yongsheng Liang, Juanhui Tu and Mengyuan Liu. Sample Fusion Network: An End-to-End Data Augmentation Network for Skeleton-based Human Action Recognition. IEEE Transactions on Image Processing(TIP), 2019, 28(11): 5281-5295.(人工智能领域顶级国际学术期刊)

[16] Mengyuan Liu, Hong Liu(刘宏), and Chen Chen, 3D action recognition using multi-scale energy-based global ternary image, Accepted by IEEE Transactions on Circuits and Systems for Video Technology(TCSVT), 28(8): 1824-1838 (2018) (多媒体领域顶级国际学术期刊)

[17] Mengyuan Liu, Hong Liu(刘宏), Chen Chen, Robust 3D Action Recognition Through Sampling Local Appearances and Global Distributions. IEEE Transaction on Multimedia(TMM) 20(8): 1932-1947 (2018) (多媒体领域顶级国际学术期刊)

[18] Chen Pang, Hong Liu(刘宏), Jie Zhang, Binaural Sound Localization Based on Reverberation Weighting and Generalized Parametric Mapping, Accepted by IEEE Transaction on Audio, Speech and Language Processing(TASLP) VOL.25:1618-1632, 2017(机器听觉领域顶级国际学术期刊)

[19] Pingping Wu, Hong Liu, Chao Xu, Yuan Gao, Zheyuan Li, Xuewu Zhang, How do you smile? Towards a comprehensive smile analysis system. Neurocomputing 235: 245-254 (2017) (人工智能领域重要国际学术期刊)

[20] Mengyuan Liu, Hong Liu(刘宏), and Chen Chen, Enhanced skeleton visualization for view invariant human action recognition, Pattern Recognition(PR) 68: 346-362 (2017)(模式识别领域顶级国际学术期刊)

[21] Qianru Su, Hong Liu(刘宏), Tatsuya Harada, Online Growing Neural Gas for Anomaly Detection in Changing Surveillance Scenes, Pattern Recognition(PR) 64: 187-201, 2017.(模式识别领域顶级国际学术期刊)

[22] Pingping Wu, Hong Liu (刘宏), Xiaofei Li, A Novel Lip Descriptor for Audio-Visual Keyword Spotting Based on Adaptive Decision Fusion, IEEE Transactions on Multimedia (TMM). vol.18(3): 326-338, 2016. (多媒体领域顶级国际学术期刊)

[23] Qianru Sun, Hong Liu, Liqian Ma, Tianwei Zhang, A novel hierarchical Bag-of-Words model for compact action representation. Neurocomputing 174: 722-732, 2016. (人工智能领域重要国际学术期刊)

[24] Yuan Gao, Hong Liu(刘宏), Pingping Wu P. A new descriptor of gradients Self-Similarity for smile detection in unconstrained scenarios. Neurocomputing. vol.174: 1077-1086, 2016. (人工智能领域重要国际学术期刊)

[25] Mengyuan Liu, Hong Liu(刘宏), Depth Context: a new descriptor for human activity recognition by using sole depth sequences. Neurocomputing. vol.175: 747-758, 2016. (人工智能领域重要国际学术期刊)

[26] Qianru Sun Q, Hong Liu(刘宏), Liqian Ma, A novel hierarchical Bag-of-Words model for compact action representation. Neurocomputing. vol.174: 722-732, 2016. (人工智能领域重要国际学术期刊)

[27] Jie Zhang, Hong Liu (刘宏), Robust Acoustic Localization Via Time-Delay Compensation and Interaural Matching Filter, IEEE Transactions on Signal Processing(TSP), vol.63, no.18, pp. 4771-4783, 2015. (多媒体信号处理领域顶级国际学术期刊)

[28] Qianru Sun, Hong Liu(刘宏), Mengyuan Liu, Human activity prediction by mapping grouplets to recurrent Self-Organizing Map. Neurocomputing, vol.177: 427-440, 2015. (人工智能领域重要国际学术期刊)

[29] Wenhao Li, Hong Liu, Hao Tang, Pichao Wang, and Luc Van Gool. MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation. Accepted by IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (计算机视觉领域顶级国际学术会议)

[30] Tianyu Guo, Hong Liu(刘宏), Zhan Chen, Mengyuan Liu, Tao Wang, Runwei Ding. Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition. Accepted by Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2022. (人工智能领域顶级国际学术会议)

[31] Tao Wang, Hong Liu(刘宏), Pinhao Song, Tianyu Guo, Wei Shi. Pose-guided Feature Disentangling for Occluded Person Re-identification based on Transformer. Accepted by Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2022.(人工智能领域顶级国际学术会议)

[32] Yidi Li, Hong Liu(刘宏), Hao Tang. Multi-Modal Perception Attention Network with Self-Supervised Learning for Audio-Visual Speaker Tracking. Accepted by Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2022.(人工智能领域顶级国际学术会议)

[33] Zhan Chen, Sicheng Li, Bing Yang, Qinghan Li, and Hong Liu(刘宏). Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021, 35(2): 1113-1122.(人工智能领域顶级国际学术会议)

[34] Wanlu Xu, Hong Liu(刘宏), Wei Shi, Ziling Miao, Zhisheng Lu, and Feihu Chen, Adversarial Feature Disentanglement for Long-Term Person Re-identification, International Joint Conference on Artificial Intelligence (IJCAI), 2021.(人工智能领域顶级国际学术会议)

[35] Ziling Miao, Hong Liu(刘宏), Wei Shi, Wanlu Xu, and Hanrong Ye, Modality-aware Style Adaptation for RGB-Infrared Person Re-Identification, International Joint Conference on Artificial Intelligence (IJCAI), 2021: 19-27.(人工智能领域顶级国际学术会议)

[36] Peng Wei, Guoliang Hua, Weibo Huang, Hong Liu(刘宏). Unsupervised Monocular Visual-inertial Odometry Network, International Joint Conferences on Artificial Intelligence Organization (IJCAI), 2020: 2347-2354.(人工智能领域顶级国际学术会议)

[37] Jie Wen, Zheng Zhang, Yong Xu, Bob Zhang, Lunke Fei, and Hong Liu(刘宏). Unified Embedding Alignment with Missing Views Inferring for Incomplete Multi-View Clustering. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2019, 33(01): 5393-5400.(人工智能领域顶级国际学术会议)

[38] Xia Li, Zhisheng Zhong, Jianlong Wu, Yibo Yang, Zhouchen Lin, Hong Liu(刘宏). Expectation-maximization attention networks for semantic segmentation, International Conference in Computer Vision (ICCV), 2019: 9167-9176.(计算机视觉领域顶级国际学术会议)

[39] Xia Li, Jianlong Wu, Zhouchen Lin, Hong Liu(刘宏), Hongbin Zha. Recurrent squeeze-and-excitation context aggregation net for single image deraining, European Conference on Computer Vision (ECCV), 2018: 254-269.(计算机视觉领域顶级国际学术会议)

[40] Weibo Huang, Hong Liu(刘宏). Online initialization and automatic camera-IMU extrinsic calibration for monocular visual-inertial SLAM, International Conference on Robotics and Automation (ICRA), 2018: 5182-5189.(智能机器人领域顶级国际学术会议)

[41] Dan Xu, Wei Wang, Hao Tang, Hong Liu(刘宏), Nicu Sebe, Elisa Ricci. Structured attention guided convolutional neural fields for monocular depth estimation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018: 3917-3925.(计算机视觉领域顶级国际学术会议)

[42] Hao Tang, Hong Liu(刘宏), Wei Xiao, A Novel Feature Matching Strategy for Large Scale Image Retrieval, International Joint Conference on Artificial Intelligence (IJCAI), 2016: 2053-2059. (人工智能领域顶级国际学术会议)

[43] Chen Chen, Mengyuan Liu, Baochang Zhang, Jungong Han, Junjun Jiang, and Hong Liu(刘宏). 3D Action Recognition Using Multi-temporal Depth Motion Maps and Fisher Vector, International Joint Conference on Artificial Intelligence (IJCAI), 2016: 3331-3337(人工智能领域顶级国际学术会议)

[44] Hong Liu(刘宏), Mengdi Yue, and Jie Zhang. Probabilistic Binaural Multiple Sources Localization Based on Time-delay Compensation Estimator Clustering Analysis, IEEE International Conference on Intelligent Robots and Systems (IROS), 2016: 4537-4544. (智能机器人领域重要国际学术会议)

[45] Hong Liu(刘宏), Fang Xiao and Can Wang. A predictive model for narrow passage path planner by using Support Vector Machine in changing environments, IEEE International Conference on Robotics and Automation (ICRA), 2015: 2991-2996.(智能机器人领域顶级国际学术会议)

[46] Hong Liu(刘宏), Cheng Pang and Jie Zhang. Binaural sound source localization based on generalized parametric model and two-layer matching strategy in complex environments, IEEE International Conference on Robotics and Automation (ICRA), 2015: 4496-4503.(智能机器人领域顶级国际学术会议)


对计划招收研究生的基本要求:

1)专业范围:计算机科学技术、自动化、机器人等相关学科

2)外语/数学能力:一般应通过六级;数学(高数、线代、概率、组合等)基础好。

3)研究/开发能力:探索能力、创新精神、动手能力强,愿意按高标准严格要求自己。


智能机器人开放实验室(点击进入)