王敬宇,男,北京邮电大学长聘教授,博士生导师,网络与交换技术全国重点实验室-网络智能研究中心,万物有灵IE战队负责人。英文主页:https://jericwang.github.io/
具有工业界和学术界的双重背景,长期关注通信网络与人工智能交叉领域,聚焦人机交互的理解与控制决策问题,推进了自智网络的理论研究与工程实践,取得了包括算力网络、知识定义网络、智能运维、意图转译、裸手交互、大模型加速、多路径传输等一系列代表性成果。入选江苏省高层次人才计划,北京市青年英才计划,全球前2%顶尖科学家,华为智库专家。IEEE Senior Member,中国通信学会高级会员,担任6GANA TSC委员/TG5主席,算力网专委会委员、数字孪生与系统仿真专委会委员、中国运筹学会智能工业数据解析与优化专业委员会理事等,国家自然科学基金委项目评议专家,国家科技部/教育部/中国科协评审专家,国家互联网应急中心/国家电网技术专家等。
作为项目负责人,主持国家自然科学基金重点项目、国家973计划课题、连续五个国家自然科学基金面上项目、北京市自然科学基金,教育部科研基金等国家及省部级项目,主持完成华为公司、中国移动、国家互联网应急中心、国家电网、美团等企业产业化项目二十余项,作为骨干协助完成“创新团队”、“创新群体”、国家重点研发计划、973和863等多个国家级重大项目。所研发的网络智能管控系统已在中国移动、中国联通、国家电网、国家互联网应急中心等15个省级单位实现规模化工程应用,荣获国家科技进步奖二等奖1项、中国通信学会科技进步奖一等奖2项和教育部科技进步奖二等奖2项。
目前,发表学术论文200余篇,包括IEEE ToN、JSAC、TPDS、TKDE、TDSC等CCF推荐A类期刊以及USENIX NSDI、ACM ASPLOS、NeurIPS、CVPR、ACL等CCF推荐A类会议论文,荣获人工智能顶级会议AAAI 2023年杰出论文奖(Distinguished Papers Award),信息系统顶级期刊IEEE System Journal 2021年最佳论文奖(Best Papers Award),ESI高被引论文多篇,已授权美国专利5项、已授权中国专利50余项,获批3GPP、IETF、ETSI、CCSA等标准化文稿十余篇,出版《智慧服务云网络》、《6G网络按需服务关键技术》和《网络智能化中的深度强化学习技术》专著,在Openstack社区贡献OPNFV Compass开源代码,在机器学习编译器TVM项目贡献开源代码,牵头主持发布《网络管控大模型》、《知识定义的编排与管控》和《知识定义的意图网络》白皮书,担任多个国际学术会议的TPC成员,IEEE ICDCS、IEEE GIIS、IEEE VTC会议的Session Chair。带队参加国际知名赛事AITrans、ACM MM、ACM MMSys、SemEval、ICCV Hands、Apollo等获得多项总冠军。
科研获奖,喜欢解决工程中实际疑难问题,发挥产学研用一体化的优势,工程与研究并重。
2023年,荣获国家科技进步奖二等奖(第2完成人);
2023年,入选江苏省高层次人才计划;
2023年,荣获AAAI 2023杰出论文奖(Distinguished Papers Award);
2021年,荣获中国通信学会科技进步一等奖;
2021年,入选南京市“紫金山英才”计划;
2021年,荣获IEEE System Journal 2021年最佳论文奖(Best Papers Award);
2018年,荣获中国通信学会科技进步奖二等奖;
2016年,荣获教育部科技进步奖二等奖;
2016年,荣获中国通信学会科技进步二等奖;
2014年,荣获中国通信学会科技进步一等奖;
2013年,荣获教育部科技进步奖二等奖;
2013年,入选北京市青年英才计划;
实现了多项新理论成果的规模应用,取得了显著的经济效益和社会效益,其中
2014年研发的业务用户行为大数据分析系统,在中国移动手机阅读商业智能、彩铃深度运营等系统中实现了大规模应用;
2015年研发的基于深度学习的菜品图像精细化识别系统,在美食达人小黄圈APP中实现了菜品识别的业界首例商用;
2016年研发的云数据中心的裸机自动发现与部署系统,与华为公司合作突破大规模服务器的操作系统/云管理平台的安装与生命周期管理;
2017年研发的基于机器视觉的仪表识别系统,在中国移动物联网公司和国家电网的机房实现了规模化部署应用;
2018年研发的国际诈骗行为识别与防控系统,在中国移动信息安全中心和国家互联网应急中心实现了应用;
2019年研发的基于知识图谱的生成文本多轮对话系统,与汽车之家合作实现了购车意向导购机器人的业界首例商用;
2020年研发的基于时序指标和日志的智能运维与监控系统,在中国移动和国家电网实现了故障定位与智能派单的首例商用;
2021年研发的知识定义意图网络系统KIN,在中国移动完成了从意图到网络路由、切片多场景任务执行及故障自愈突破;
2022年研发的网络通用日志大模型LogGPT,在华为和中国移动的网络系统中实现了安全、运维等垂类日志任务上的跨领域应用;
2023年研发的神经网络模型推理加速器RACE,在美团的搜索/广告/推荐等场景下实现了对稀疏模型的优化编译部署;
2024年研发的云原生智能运维实验评估平台MicroOps,为微服务场景下的智能运维算法开发提供全流程支持(欢迎体验:https://aiops-nirc.bupt.site)。
从教十余年,一线培养博士生30余人/硕士生100余人,主讲"智慧交通与自动驾驶"前沿交叉课程,“软件定义网络技术”和“下一代Internet技术与协议”等计算机专业课。
2016年和2019年两次荣获学院/学校“师德标兵”称号,2018~2023年未来学院科研导师/叶培大学院实验班导师;
2017~2023年指导学生获得北京邮电大学研究生“创新创业展”一等奖8项、二等奖6项,指导硕士/博士研究生先后获得十余次国家奖学金;
付霄元博士荣获2019年北京邮电大学优秀博士学位论文,入选2020年博士后创新人才支持计划(博新计划);
任鹏飞博士荣获2023年中国电子教育学会优秀博士论文、北京邮电大学优秀博士学位论文,入选2023年博士后基金特别资助(站前);
何波博士荣获2020年和2022年两次国家奖学金,入选2023年博士后创新人才支持计划(博新计划);
多次荣获北京邮电大学优秀硕士学位论文指导教师称号,2024年郭岳彬,2023年徐佳庆,2022年黄伟亭,2020年靖宇涵,2020年李家仕;
多次荣获北京市或北京邮电大学优秀本科学位论文指导教师称号,2024年孙俊哲,2023年刘俊杰,2022年徐逸辰,2020年李松洋,2016年戈策;
作为指导教师,组队参加国际/全国知名赛事与技术挑战赛,多次获得优异成绩,其中
2019年AITrans全球智能网络传输竞赛荣获总决赛总冠军、最佳实战算法奖,全球138支参赛队伍,实际环境下的视频传输PK;
2019年FGVC | Kaggle iMaterialist @IEEE CVPR细粒度视觉识别全球顶级挑战赛荣获季军,全球202支参赛队伍,规模最大的商品识别竞赛;
2019年AIOps国际智能运维挑战赛荣获季军,多维检测指标异常定位和根因分析,吸引了全球457名选手组成的141支队伍;
2019年“雅典娜杯”数据挖掘大赛获高校创新奖,线上贷款违约预测,邀请赛共70余家单位,361支队伍和870人参赛;
2019~2021年“vGesture:精细化3D手势与VR系统”获北邮“创新创业展”一等奖3项,“互联网+”大赛北京赛区一等奖2项,全球ICCV Hands榜单第一名;
2021年“MindCamera:所思即所得的图像视频生成工具"和“Insight:电信诈骗和恶意行为识别系统”等项目荣获北邮“创新创业展”一等奖;
2022年“i360:沉浸式全景虚拟交互系统”项目荣获2022年“互联网+”腾讯企业赛道一等奖,首次实现面向元宇宙的VR/AR虚拟增强现实场景系统。
2022年第二十四届中国机器人及人工智能大赛全国总决赛“百度Apollo城市道路自动驾驶虚拟仿真赛”荣获全国一等奖。
2023年ITU AI/ML in 5G Challenge图神经网络挑战赛Graph Neural Networking challenge第二名,构建数字孪生网络预测网络QoS性能。
2024年ACM多媒体系统年会(MMSys) 360° 全景视频挑战赛第一名,部署自定义运动预测算法优化流媒体传输,用户端取得最佳指标。
回归科学技术本源,坚持系统级创新,欢迎关注团队最新的学术进展,开源了部分成果的代码,希望对本领域技术进步有所推动,欢迎多多引用我们的论文。
一、泛在智联网络 (AI4Net&DCN)
[1]Tianjian Dong,Qi Qi, Jingyu Wang*, Zirui Zhuang, Haifeng Sun, Jianxin Liao, Zhu Han, "Standing on the Shoulders of Giants: Cross-Slice Federated Meta Learning for Resource Orchestration to Cold-Start Slice", IEEE/ACM Transactions on Networking (ToN) [CCF A], 31(2): 828-845, Apr. 2023. [Paper], 算力网络编排
[2]Bo He, Jingyu Wang*, Qi Qi, Haifeng Sun, Jianxi Liao,"RTHop: Real-Time Hop-by-hop Mobile Network Routing by Decentralized Learning with Semantic Attention," IEEE Transactions on Mobile Computing (TMC)[CCF A], vol. 22, no. 3, Mar. 2023. [Paper], 网络边缘路由
[3]Rongxin Han, Dezhi Chen, Song Guo, Qi Qi, Jingyu Wang*, Lu Lu, Zhu Han, "Multi-SP Network Slicing Parallel Relieving Edge Network Conflict," IEEE Transactions on Parallel and Distributed Systems (TPDS) [CCF A], vol. 34, no. 11, pp: 2860-2875, Nov. 2023.. 边缘网络切片
[4]Chenyang Zhao, Yuebin Guo, Jingyu Wang*, Qi Qi, Zirui Zhuang, Haifeng Sun, Lingqi Guo, Yuming Xie, Jianxin Liao, "EPVerifier: Accelerating Update Storms Verification with Edge-Predicate," USENIX Symposium on Networked Systems Design and Implementation (NSDI) [CCF A], Santa Clara, CA, USA, April 2024. 网络策略验证
[5]Rongxin Han, Jingyu Wang#, Qi Qi, Haifeng Sun, Chaowei Xu, Zhaoyang Wan, Zirui Zhuang, Yichuan Yu, Jianxin Liao, "NetRen: Service Migration-Driven Network Renascence with Synthesizing Updated Configuration," ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) [CCF A], San Diego, USA, April 2024. 重构配置自动生成
[6]Yu Liu, Zirui Zhuang, Qi Qi, Jingyu Wang*, Dezhi Chen, Lu Lu, Hongwei Yang, Jianxin Liao, Zhu Han, "Slice Sandwich: Jagged Slicing Multi-tier Dynamic Resources for Diversified V2X Services," IEEE Transactions on Mobile Computing (TMC) [CCF A], vol. 23, no. 5, pp. 4285-4302, May 2024. [Paper], 动态细粒度切片
[7]Bo He, Jingyu Wang*, Qi Qi, Qiang Ye, Qihao Li, Jianxin Liao, Xuemin Shen, "ShuttleBus: Dense Packet Assembling with QUIC Stream Multiplexing for Massive IoT," IEEE Transactions on Mobile Computing (TMC) [CCF A], vol. 23, no. 8, pp. 8307-8322, Aug. 2024. [Paper], 海量物联包汇聚
[8]Rongxin Han, Jingyu Wang#, Qi Qi, Dezhi Chen, Zirui Zhuang, Haifeng Sun, Xiaoyuan Fu, Jianxin Liao, Song Guo, "Dynamic Network Slice for Bursty Edge Traffic," IEEE/ACM Transactions on Networking (ToN) [CCF A], vol. 32, no. 4, pp. 3142-3157, Aug. 2024. [Paper], 按需动态切片
[9]Haifeng Sun, Xingjian Liao, Jingyu Wang*, Qi Qi, Zirui Zhuang, Jianxin Liao, Dapeng Wu, "Fast and Scalable ACL Policy Solving under Complex Constraints with Graph Neural Networks," IEEE/ACM Transactions on Networking (ToN) [CCF A], DOI:10.1109/TNET.2024.3409529, online May 2024. [Paper], 访问控制配置生成
[10]Haoran Zhao, Bo He, Jingyu Wang*, Qi Qi, Haifeng Sun, Zirui Zhuang, Jianxin Liao, "QUIC-Enabled Framework for Alleviating Transient Congestion in Time-Critical IoT," ACM Annual International Conference On Mobile Computing And Networking (MobiCom) [CCF A], Demo, Washington D.C., DC, USA, Nov. 2024. 缓解暂态突发
二、多模态数据分析 (DM&IR)
[1]Guojun Chu, Jingyu Wang*, Qi Qi, Haifeng Sun, Shimin Tao, Jianxin Liao, “Prefix-Graph: A Versatile Log Parsing Approach Merging Prefix Tree with Probabilistic Graph,” The annual IEEE International Conference on Data Engineering (ICDE) [CCF A], Chania, Crete, Greece, Apr. 2021. [Paper], 通用日志解析
[2]Jinming Wu,Qi Qi,Jingyu Wang*,Haifeng Sun,Zhikang Wu,Zirui Zhuang,Jianxin Liao, "Not Only Pairwise Relationships: Fine-Grained Relational Modeling for Multivariate Time Series Forecasting," International Joint Conference on Artificial Intelligence (IJCAI) [CCF A], Macao, Aug. 2023. [Paper], 图关系时间序列预测
[3]Wei Tang, Haifeng Sun, Jingyu Wang*, Qi Qi, Wang Jing, Hao Yang and Shimin Tao, "Multi-order Matched Neighborhood Consistent Graph Alignment in a Union Vector Space," ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) [CCF A], Taipei Taiwan, July 2023. [Paper], [Code], 邻域一致性图对齐
[4]Wei Tang, Haifeng Sun, Jingyu Wang*, Cong Liu, Qi Qi, Jing Wang, Jianxin Liao, "Identifying Users across Social Media Networks for Interpretable Fine-grained Neighborhood Matching by Adaptive GAT," IEEE Transactions on Services Computing (TSC) [CCF A], vol.16, no.5, pp: 3453-3466, Oct. 2023. 跨平台用户匹配
[5]Wei Tang, Haifeng Sun, Jingyu Wang*, Qi Qi, Chunning Du, Li Chen, "Cross-graph Embedding with Trainable Proximity for Graph Alignment," IEEE Transactions on Knowledge and Data Engineering (TKDE) [CCF A], vol.35, no. 12, pp: 12556-12570, Dec. 2023. [Paper], [Code], 跨图随机游走
[6]Chengsen Wang, Qi Qi, Jingyu Wang*, Haifeng Sun, Xingyu Wang, Zirui Zhuang, Jianxin Liao "Drift doesn't Matter: Dynamic Decomposition with Diffusion Reconstruction for Unstable Multivariate Time Series Anomaly Detection," Annual Conference on Neural Information Processing Systems (NeurIPS) [CCF A], New Orleans, Louisiana, USA, Dec. 2023. [Code], 多维时间序列检测
[7]Guojun Chu, Jingyu Wang*, Qi Qi, Haifeng Sun, Shimin Tao, Hao Yang, Jianxin Liao, “Exploiting Spatial-Temporal Behavior Patterns for Fraud Detection in Telecom Networks,” IEEE Transactions on Dependable and Secure Computing (TDSC)[CCF A], vol.20, no. 6, pp:4564-4577, Nov. 2023. [Paper], 时空诈骗识别
[8]Jiabo Wang, Guojun Chu, Jingyu Wang*, Haifeng Sun, Qi Qi, Yuanyi Wang, Ji Qi, Jianxin Liao, "LogExpert: Log-based Recommended Resolutions Generation using Large Language Model," IEEE/ACM International Conference on Software Engineering (ICSE) [CCF A]: New Ideas and Emerging Results, Lisbon, Portugal, April, 2024. [Code], 大模型日志专家
[9]Yuanyi Wang, Haifeng Sun, Jiabo Wang, Jingyu Wang*, Wei Tang, Qi Q, Shaoling Sun, Jianxin Liao, "Towards Semantic Consistency: Dirichlet Energy Driven Robust Multi-Modal Entity Alignment," IEEE International Conference on Data Engineering (ICDE) [CCF A], Utrecht, Netherlands, May 2024. [Code], 多模态实体对齐
[10]Yuhan Jing, Jingyu Wang#, Ji Qi, Qi Qi, Bo He, Zirui Zhuang, Nanxing Wu, Jianxin Liao, "Diner: Interpretable Anomaly Detection for Seasonal Time Series in Web Services," IEEE Transactions on Services Computing (TSC) [CCF A], DOI: 10.1109/TSC.2024.3422894, online June 2024. 可解释异常检测
[11]Chengsen Wang, Qi Qi, Jingyu Wang*, Haifeng Sun, Zirui Zhuang, Jinming Wu, Jianxin Liao, "Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective," Annual Conference on Neural Information Processing Systems (NeurIPS) [CCF A], Vancouver Canada, Dec. 2024. [Code], 时间戳时间序列预测
三、服务与模型加速 (MLSys&Net4AI)
[1]Jiashi Li, Qi Qi, Jingyu Wang*, Ce Ge, Zhangzhang Yue, Haifeng Sun, “OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural Networks,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [CCF A], Long Beach, USA, Jun. 2019. [Paper], [Code], 神经网络压缩
[2]Wanyi Ning, Haifeng Sun, Xiaoyuan Fu, Xiang Yang, Qi Qi, Jingyu Wang*, Jianxin Liao, Zhu Han, "Following the Correct Direction: Renovating Sparsified SGD towards Global Optimization in Distributed Edge Learning", IEEE Journal on Selected Areas in Communications (JSAC) [CCF A], 40(2): 499-514, Feb. 2022. [Paper], [Code], 分布式边缘智能
[3]Ruilong Ma, Jingyu Wang#, Qi Qi, Xiang Yang, Haifeng Sun, Zirui Zhuang, Jianxin Liao, "PipeLLM: Pipeline LLM Inference on Heterogeneous Devices with Sequence Slicing," ACM Special Interest Group on Data Communication (SIGCOMM) [CCF A], Demo, New York City, US, Sep. 2023. [Paper], 流水线大模型
[4]Xiang Yang, Zikang Xu, Qi Qi, Jingyu Wang*, Haifeng Sun, Jianxin Liao, Song Guo, "PICO: Pipeline Inference Framework for Versatile CNNs on Diverse Mobile Devices," IEEE Transactions on Mobile Computing (TMC) [CCF A], vol. 23, no. 4, pp. 2712-2730, Apr. 2024. [Paper], 模型分布式边缘推理
[5]Baoqi Gao, Daoxu Sheng, Lei Zhang, Qi Qi, Bo He, Zirui Zhuang, Jingyu Wang*, "STAR-VP: Improving Long-term Viewport Prediction in 360° Videos via Space-aligned and Time-varying Fusion," ACM Multimedia (MM) [CCF A], Melbourne, Australia, Oct. 2024. 长期视角预测
[6]Daoxu Sheng, Qi Qi, Jingyu Wang*, Lianyuan Li, Wei Yu, Jianxin Liao, "PsyQoE: Improving Quality-of-Experience Assessment with Psychological Effects in Video Streaming," IEEE Transactions on Services Computing (TSC) [CCF A], DOI: 10.1109/TSC.2024.3422894, online Aug. 2024. 视频流QoE评估
[7]Wanyi Ning, Qi Qi, Jingyu Wang*, Mengde Zhu, Shaolong Li, Guang Yang, Jianxin Liao, "One Teacher is Enough: A Server-Clueless Federated Learning with Knowledge Distillation," IEEE Transactions on Services Computing (TSC) [CCF A], DOI: 10.1109/TSC.2024.3414372, online June 2024. 无线索知识蒸馏
[8]Wanyi Ning, Jingyu Wang*, Qi Qi, Mengde Zhu, Haifeng Sun, Daixuan Cheng, Jianxin Liao, Ce Zhang, "FM-Delta: Lossless Compression for Storing Massive Fine-tuned Foundation Models," Annual Conference on Neural Information Processing Systems (NeurIPS) [CCF A], Vancouver Canada, Dec. 2024. [Code], 微调大模型无损压缩
[9]Jingyu Wang, Ruilong Ma, Xiang Yang, Qi Qi, Zirui Zhuang, Jing Wang, Jianxin Liao, and Song Guo, "DeepZoning: Re-accelerate CNN Inference with Zoning Graph for Heterogeneous Edge Cluster," ACM Transactions on Architecture and Code Optimization (TACO) [CCF A], online Sep. 2024. 异构资源模型加速
四、机器视觉与意图理解 (CV&NLP)
[1]Chunning Du, Haifeng Sun, Jingyu Wang*, Qi Qi and Jianxin Liao, “Adversarial and Domain-Aware BERT for Cross-Domain Sentiment Analysis,” Annual Meeting of the Association for Computational Linguistics (ACL) [CCF A], Seattle, USA, Jul. 2020. [Paper], 语义情感识别
[2]Gao Lei, Wang Yulong, Liu Tongcun, Wang Jingyu, Zhang Lei, Liao Jianxin. "Question-driven span labeling model for aspect–opinion pair extraction," AAAI Conference on Artificial Intelligence (AAAI)[CCF A], Virtual Event, 2021. [Paper], 问答机器理解
[3]Bing Ma, Cao Liu, Jingyu Wang∗, Shujie Hu, Fan Yang, Xunliang Cai, Guanglu Wan, Jiansong Chen, Jianxin Liao: "Distant Supervision based Machine Reading Comprehension for Extractive Summarization in Customer Service." ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) [CCF A], 2021: 1895-1899. [Paper], [Code], 机器阅读理解
[4]Jiaqing Xu, Haifeng Sun, Qi Qi, Jingyu Wang∗,Ce Ge, Lejian Zhang, Jianxin Liao, "DLA-Net for FG-SBIR: Dynamic Local Aligned Network for Fine-Grained Sketch-Based Image Retrieval," ACM Multimedia (MM) [CCF A], Chengdu, China, Oct. 2021. [Paper], 精细草图检索
[5]Ce Ge, Jingyu Wang∗, Qi Qi, Haifeng Sun, Tong Xu, Jianxin Liao, "Scene-Level Sketch-Based Image Retrieval with Minimal Pairwise Supervision," AAAI Conference on Artificial Intelligence (AAAI)[CCF A], Booz Allen Hamilton, USA, Feb. 2023. 场景草图检索
[6]Ce Ge, Jingyu Wang#, Qi Qi, Haifeng Sun, Tong Xu, Jianxin Liao, "Semi-Transductive Learning for Generalized Zero-Shot Sketch-Based Image Retrieval," AAAI Conference on Artificial Intelligence (AAAI)[CCF A], Booz Allen Hamilton, USA, Feb. 2023. 实例草图检索
[7]Menghao Zhang, Jingyu Wang*, Qi Qi, Haifeng Sun, Zirui Zhuang, Pengfei Ren, Ruilong Ma, Jianxin Liao, "Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [CCF A], Seattle WA, USA, Jun. 2024. 多粒度时空表征学习
[8]Menghao Zhang, Jingyu Wang#, Qi Qi, Pengfei Ren, Haifeng Sun, Zirui Zhuang, Lei Zhang, Jianxin Liao, "Safeguarding Sustainable Cities: Unsupervised Video Anomaly Detection through Diffusion-based Latent Pattern Learning," International Joint Conference on Artificial Intelligence (IJCAI)[CCF A], Jeju Island, South Korea, August 2024. 扩散学习异常检测
[9]Huazheng Wang, Haifeng Sun, Jingyu Wang*, Qi Qi, Zixuan Xia, Menghao Zhang, Jianxin Liao, "SSS: Editing Factual Knowledge in Language Models towards Semantic Sparse Space," Annual Meeting of the Association for Computational Linguistics (ACL) [CCF A], Bangkok, Thailand, August 2024. 语义稀疏程度评估
[10]Menghao Zhang, Jingyu Wang*, Qi Qi, Pengfei Ren, Haifeng Sun, Zirui Zhuang, Huazheng Wang, Lei Zhang, Jianxin Liao, "Video Anomaly Detection via Progressive Learning of Multiple Proxy Tasks," ACM Multimedia (MM) [CCF A], Melbourne, Australia, Oct. 2024. 渐进式学习异常检测
[11]Menghao Zhang, Jingyu Wang#, Qi Qi, Zirui Zhuang, Haifeng Sun, Jianxin Liao, "Cognition Guided Video Anomaly Detection Framework for Surveillance Services," IEEE Transactions on Services Computing (TSC) [CCF A], DOI: 10.1109/TSC.2024.3407588, online May 2024. [Paper], [Code], 认知异常检测
五、人机交互与姿态估计 (CHI&PR)
[1]Weiting Huang, Pengfei Ren, Jingyu Wang*, Qi Qi, Haifeng Sun, “AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation,” AAAI Conference on Artificial Intelligence (AAAI) [CCF A], New York, USA. Feb. 2020. [Paper], [Code], 手势姿态估计
[2]Pengfei Ren, Haifeng Sun, Jiachang Hao, Jingyu Wang∗, Qi Qi, Jianxin Liao: "Mining Multi-View Information: A Strong Self-Supervised Framework for Depth-based 3D Hand Pose and Mesh Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)[CCF A] 2022: 20523-20533, [Paper], [Video], [Code], 自监督姿态估计
[3]Pengfei Ren, Haifeng Sun, Jiachang Hao, Qi Qi, Jingyu Wang*, Jianxin Liao, "A Dual-Branch Self-Boosting Framework for Self-Supervised 3D Hand Pose Estimation", IEEE Transactions on Image Processing (TIP) [CCF A], 31: 5052-5066, July 2022. [Paper], [Code], 自监督手势估计
[4]Pengfei Ren, Yuchen Chen, Jiachang Hao, Haifeng Sun, Qi Qi, Jingyu Wang∗, Jianxin Liao, “Two Heads are Better than One: Image-Point Cloud Network for Depth-Based 3D Hand Pose Estimation,” AAAI Conference on Artificial Intelligence (AAAI)[CCF A], Booz Allen Hamilton, USA, Feb. 2023. [Paper], [Code], 图像点云网络, Distinguished Papers Reward
[5]Xingyu Liu, Pengfei Ren, Yuchen Chen, Cong Liu, Jing Wang, Haifeng Sun, Qi Qi and Jingyu Wang*, "SA-Fusion: Multimodal Fusion Approach for Web-based Human-Computer Interaction in the Wild," ACM Web Conference (WWW)[CCF A], Austin, TX, USA, May 2023. [Paper], 多模态人机交互
[6]Xiaozheng Zheng, Chao Wen, Zhou Xue, Pengfei Ren, Jingyu Wang*, "HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learning," International Conference on Computer Vision (ICCV) [CCF A], Paris, France, Oct. 2023. [Code], [Homepage], 多视角自监督学习
[7]Pengfei Ren, Chao Wen, Xiaozheng Zheng, Zhou Xue, Haifeng Sun, Qi Qi, Jingyu Wang*, Jianxin Liao, "Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image," International Conference on Computer Vision (ICCV) [CCF A], Paris, France, Oct. 2023. [Code], [Homepage], 交互手势重建
[8]Xingyu Liu, Pengfei Ren, Yuanyuan Gao, Jingyu Wang*, Haifeng Sun, Qi Qi, Zirui Zhuang, Jianxin Liao, "Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation," AAAI Conference on Artificial Intelligence (AAAI) [CCF A], Vancouver, Canada, Feb. 2024. [Code], 多模态融合估计
[9]Pengfei Ren, Yuanyuan Gao, Haifeng Sun, Qi Qi, Jingyu Wang*, Jianxin Liao, "Dynamic Support Information Mining for Category-Agnostic Pose Estimation," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [CCF A], Seattle WA, USA, Jun. 2024. 类别不可知姿态估计
网络智能研究中心NIRC公众号(每周更新),开源平台 https://github.com/OpenNetAI
欢迎您了解和加入我们实验室,同学们口中的“大智能”中心,万物有灵IE战队,Intelligence of Everything(IE),
也欢迎大家保送和考取本中心硕士/博士/博士后,精诚合作共创美好未来。
有意者请将简历等相关材料发至wangjingyu@bupt.edu.cn
[1]网络智能化(算力智联网络、知识定义网络、自智网络、智能运维、物联网与车联网)
[2]深度学习系统(模型编译、加速与分布化、模型压缩)
[3]人机交互(手势控制、语义理解、视频异常检测、自然语言处理、对话机器人)
网络与交换技术国家重点实验室网络智能研究中心,创建于1999年,是国内较早开展通信网络智能业务理论研究的著名实验室。学术带头人两院院士陈俊亮先生,国重实验室主任张平院士,中心主任廖建新教授,所在团队入选教育部“创新团队”以及国家自然科学基金委“创新研究群体”。
团队长期从事智能网络、云计算、机器视觉、自然语言处理、数据挖掘等方面的研究,取得了多项国际领先的创新成果。在国际顶级期刊以及顶级会议发表论文200余篇,获得网络领域顶级会议SIGCOMM 2022唯一最佳论文奖(中国首次),人工智能领域顶级会议AAAI 2023杰出论文奖(北邮首次),参加知名国际挑战赛AITrans、SemEval、ICCV Hands、FGVC、AIOps等也多次获得全球总冠军和优异成绩。
主持国家重点研发计划6G重点专项、973计划课题、自然科学基金重大课题等国家级科研项目二十余项,通过产学研一体化转化实现了多项科技成果的大规模应用,获得国家科技进步二等奖2项、省部级科技进步奖一等奖4项及信息产业部重大技术发明1项。