刘武
近期热点
资料介绍
个人简历
个人介绍2015年博士毕业于中国科学院计算技术研究所。研究方向为多媒体、机器学习与计算机视觉,在IEEECVPR、ACMMM、IJCAI、ECCV、IEEET-MM、IEEET-CYB等一流国际会议和期刊上发表文章20余篇。曾获得中国科学院优秀博士学位论文奖、中国科学院院长特别奖、国际会议IEEEICME2016BestStudentPaper、BIGCOM2016RunnerUpforBestPaper、2016CCF腾讯-犀牛鸟科研基金等。曾担任SCI期刊MVA客邀编辑,国际会议PCM2016、ICIMCS2016、CCIS2016、BIGMM2017、ICIP2017、GlobalSIP2017的分会或专题研讨会主席,以及多个IEEE/ACMTransaction期刊和CCF推荐A、B类国际会议的审稿人。承担课题1.国家自然科学基金青年科学基金项目,61602049,有限语义标注的视频场景自动理解技术研究,2017/01-2019/12,在研,主持2.CCF-腾讯“犀牛鸟”科研基金项目,AGR20160113,移动视频检索关键技术研究,2016/11-2017/11,在研,主持3.国家自然科学基金面上项目,61572472,基于稀疏表示和深度学习的大规模目标检测,2016/01-2019/12,在研,科研骨干4.国家高技术研究发展计划(863计划)项目,2014AA015101,基于深度学习的大数据语义分析技术,2014/07-2016/12,结题,科研骨干获奖和成果1.中国科学院优秀博士学位论文奖,20162.中国科学院院长特别奖,20153.CCF-腾讯犀牛鸟科研基金奖,20164.国际会议IEEEICME2016最佳学生论文,20165.国际会议BIGCOM2016最佳论文亚军奖,20166.中科院计算所“夏培肃”奖,2014研究领域
多媒体计算、机器学习、计算机视觉近期论文
[1]WuLiu,XinchengLiu,HuadongMa,PengCheng:BeyondHuman-levelLicensePlateSuper-resolutionwithProgressiveVehicleSearchandDomainPrioriGAN.ACMMM2017[2]WuLiu,HuadongMa,HengQi,DongZhao,ZhinengChen:Deeplearninghashingformobilevisualsearch.EURASIPJ.ImageandVideoProcessing2017:17(2017)[3]WuLiu,JiangyuLiu,XiaoyanGu,KunLiu,XiaoweiDai,HuadongMa:DeepLearningBasedIntelligentBasketballArenawithEnergyImage.MMM(1)2017:601-613[4]WuLiu,TaoMei,YongdongZhang,CherryChe,JieboLuo:Multi-taskdeepvisual-semanticembeddingforvideothumbnailselection.CVPR2015:3707-3715[5]WuLiu,TaoMei,YongdongZhang:InstantMobileVideoSearchWithLayeredAudio-VideoIndexingandProgressiveTransmission.IEEETrans.Multimedia16(8):2242-2255(2014)[6]WuLiu,YongdongZhang,ShengTang,JinhuiTang,RichangHong,JintaoLi:AccurateEstimationofHumanBodyOrientationFromRGB-DSensors.IEEETrans.Cybernetics43(5):1442-1452(2013)[7]WuLiu,FeibinYang,YongdongZhang,QinghuaHuang,TaoMei:LAVES:aninstantmobilevideosearchsystembasedonlayeredaudio-videoindexing.ACMMultimedia2013:409-410[8]WuLiu,TaoMei,YongdongZhang,JintaoLi,ShipengLi:Listen,look,andgotcha:instantvideosearchwithmobilephonesbylayeredaudio-videoindexing.ACMMultimedia2013:887-896[9]WuLiu,TianXia,JiWan,YongdongZhang,JintaoLi:RGB-DBasedMulti-attributePeopleSearchinIntelligentVisualSurveillance.MMM2012:750-760[10]WuLiu,YihongGao,HuadongMa,ShuiYu,andJieNie,“CostOptimalResourceProvisioningforLiveVideoForwardingacrossVideoDataCenters,”JournalofVisualCommunicationandImageRepresentation,2017,DOI:10.1016/j.jvcir.2017.01.010[11]YihongGao,HuadongMa,WuLiu:MinimizingResourceCostforCameraStreamSchedulinginVideoDataCenter.J.Comput.Sci.Technol.32(3):555-570(2017)[12]PeiyeLiu,WuLiu,HuadongMa,“Weightedsequencelossbasedspatial-temporaldeeplearningframeworkforhumanbodyorientationestimation,”IEEEICME2017[13]LinghengZhu,WuLiu,LingyangChu,PeiyeLiu,XiaoyanGu,“QueryFromSketch:ACommonSubgraphCorrespondenceMiningFramework,”IEEEBIGMMWorkshop2017[14]JingkuanSong,ZhaoGuo,WuLiu,DongxiangZhang,HengtaoTShen,LianliGao,“HierarchicalLSTMwithAdjustedTemporalAttentionforVideoCaptioning,”IJCAI2017[15]ZhengZhang,WuLiu,HuadongMa,ChuangGan,XinchenLiu,“GoingClearfromMistyRaininDarkChannelguidedNetwork”,IJCAIWorkshop,2017[16]XinchenLiu,WuLiu,TaoMei,HuadongMa:ADeepLearning-BasedApproachtoProgressiveVehicleRe-identificationforUrbanSurveillance.ECCV(2)2016:869-884[17]ChengZhang,WuLiu,HuadongMa,HuiyuanFu:Siameseneuralnetworkbasedgaitrecognitionforhumanidentification.ICASSP2016:2832-2836[18]XinchenLiu,WuLiu,HuadongMa,HuiyuanFu:Large-scalevehiclere-identificationinurbansurveillancevideos.ICME2016:1-6[19]ShuangqunLi,WuLiu,HuadongMa,HuiyuanFu:Multi-attributeBasedFireDetectioninDiverseSurveillanceVideos.MMM(1)2017:238-250[20]YihongGao,HuadongMa,WuLiu,ShuiYu:CostOptimalResourceProvisioningforLiveVideoForwardingAcrossVideoDataCenters.BigCom2016:27-38[21]ShuangqunLi,XinchenLiu,WuLiu,HuadongMa,HaitaoZhang:Adiscriminativenullspacebaseddeeplearningapproachforpersonre-identification.CCIS2016:480-484[22]RuiZhang,ShengTang,WuLiu,YongdongZhang,JintaoLi,”Multi-modalTagLocalizationforMobileVideoSearch,”MultimediaSystems,2016,DOI:10.1007/s00530-016-0506-9[23]RuiZhang,ShengTang,WuLiu,JintaoLi:Multimodaltaglocalizationbasedondeeplearning.ICIMCS2015:50:1-50:4[24]BinWang,ShengTang,RuizhenZhao,WuLiu,YigangCen:PedestriandetectionbasedonRegionProposalFusion.MMSP2015:1-6[25]YichengSong,Yong-DongZhang,JuanCao,TianXia,WuLiu,Jin-TaoLi:WebVideoGeolocationbyGeotaggedSocialResources.IEEETrans.Multimedia14(2):456-470(2012)ACMFCA创始会员MachineVisionandApplications客邀编辑ICIP2017,GlobalSIP2017,BIGMM2017,PCM2016,ICIMCS2016分会/专题研讨会主席 相关热点