计算机科学

计算机科学 ›› 2022, Vol. 49 ›› Issue (3): 152-162.doi: 10.11896/jsjkx.210200048

• 计算机图形学&多媒体 • 上一篇    下一篇

多目标跟踪的对象初始化综述

文成宇1, 房卫东2, 陈伟1,2   

  1. 1 中国矿业大学计算机科学与技术学院 江苏 徐州221116
    2 中国科学院上海微系统与信息技术研究所无线传感网与通信重点实验室 上海200050
  • 收稿日期:2021-02-04 修回日期:2021-06-03 出版日期:2022-03-15 发布日期:2022-03-15
  • 通讯作者: 陈伟(chenwdavior@163.com)
  • 作者简介:(cumtwency@163.com)
  • 基金资助:
    国家自然科学基金(51874300);国家自然科学基金委员会-山西省人民政府煤基低碳联合基金(U1510115);中国科学院上海微系统与信息技术研究所无线传感网与通信重点实验室开放基金(20190902,20190913)

Object Initialization in Multiple Object Tracking:A Review

WEN Cheng-yu1, FANG Wei-dong2, CHEN Wei1,2   

  1. 1 School of Computer Science and Technology,China University of Mining and Technology,Xuzhou,Jiangsu 221116,China
    2 Key Laboratory of Wireless Sensor Network & Communication,Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences,Shanghai 200050,China
  • Received:2021-02-04 Revised:2021-06-03 Online:2022-03-15 Published:2022-03-15
  • About author:WEN Cheng-yu,born in 1995,postgra-duate.His main research interests include machine learning and image processing.
    CHEN Wei,born in 1978,Ph.D,professor,is a member of IEEE.His main research interests include machine lear-ning,image processing,and computer networks.
  • Supported by:
    National Natural Science Foundation of China(51874300),National Natural Science Foundation of China and Shanxi Provincial People’s Government Jointly Funded Project of China for Coal Base and Low Carbon(U1510115) and Open Research Fund of Key Laboratory of Wireless Sensor Network & Communication,Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences(20190902,20190913).

PDF (PC)

625

摘要： 对象初始化方法决定了如何对待多目标跟踪问题,与后续的多目标跟踪效果直接相关。不同的对象初始化方法能够确定不同的多目标跟踪框架,每一种框架都提供一种解决问题的思路,使得多目标跟踪的对象初始化问题具有巨大的研究前景。目前关于多目标跟踪中的对象初始化方法的综述性文献较少或缺乏系统性的对象初始化概述,因此文中从多假设跟踪方法、网络流方法、深度学习方法和主题发现方法4个方面对多目标跟踪的对象初始化方法进行分析。系统地阐述了不同多目标跟踪框架下的任务转换和对象映射问题,汇总了多目标跟踪的对象初始化方法。

关键词: 对象初始化, 多假设跟踪, 多目标跟踪, 深度学习, 网络流, 主题发现

Abstract: Object initialization method determines how to treat the multi-object tracking problem,being directly related to the subsequent tracking result.Different object initialization methods confirm different multi-object tracking frameworks and each framework provides a way to solve the problem,which makes the object initialization of multi-object tracking a huge research prospect.Currently there are few literature on object initialization methods of multi-target tracking,or lacks a systematic overview of object initialization.Therefore,we analyze the object initialization methods on four aspects:multi-hypothesis tracking,network flow,deep learning and topic discovery.We systematically expound the task conversion and object mapping problems under diffe-rent multi-object tracking frameworks,and summarize the object initialization methods for the multi-object tracking.

Key words: Deep learning, Multiple hypothesis tracking, Multiple target tracking, Network flow, Object initialization, Topic discovery

中图分类号: 

  • TP391
[1]LEAL-TAIXÉ L,MILAN A,REID I,et al.MOT Challenge2015:Towards a Benchmark for Multi-Target Tracking[EB/OL].(2015-04-01)[2020-11-27].https://ui.adsabs.harvard.edu/abs/2015arXiv150401942L.
[2]KHALKHALI M B,VAHEDIAN A,YAZDI H S.Multi-Target State Estimation Using Interactive Kalman Filter for Multi-Vehicle Tracking[J].IEEE Transactions on Intelligent Transportation Systems,2020,21(3):1131-1144.
[3]LUO Z Z,ATTARI M,HABIBI S,et al.Online Multiple Maneuvering Vehicle Tracking System Based on Multi-Model Smooth Variable Structure Filter[J].IEEE Transactions on Intelligent Transportation Systems,2020,21(2):603-616.
[4]DU Y,WEI S G,CHAI L G.Particle Filter Based Object Trac-king of 3D Sparse Point Clouds for Autopilot[C]//2018 Chinese Automation Congress.2018:1102-1107.
[5]LIU Y,ZHANG W X,YANG Y,et al.RAMTEL:RobustAcoustic Motion Tracking Using Extreme Learning Machine for Smart Cities[J].IEEE Internet Things,2019,6(5):7555-7569.
[6]BLOISI D,IOCCHI L.Argos-a Video Surveillance System forBoat Traffic Monitoring in Venice[J].International Journal of Pattern Recognition and Artificial Intelligence,2009,23(7):1477-1502.
[7]NANAWARE V S,NERKAR M H,PATIL C M.A Review of the Detection Methodologies of Multiple Human Tracking & Action Recognition in a Real Time Video Surveillance[C]//2017 IEEE International Conference on Power,Control,Signals and Instrumentation Engineering.2017:2484-2489.
[8]ZHOU L F,TOKEKAR P.Active Target Tracking With Self-Triggered Communications in Multi-Robot Teams[J].IEEE Transactions on Automation Science and Engineering,2019,16(3):1085-1096.
[9]VALDIVIA-GRANDA W A.Biosurveillance enterprise foroperational awareness,a genomic-based approach for tracking pathogen virulence[J].Virulence,2013,4(8):745-751.
[10]SHAH P,FAZA A,NIMMALA R,et al.Infrared and InertialTracking in the Immersive Audio Environment for Enhanced Military Training[C]//2012 IEEE International Conference on Multimedia and Expo Workshops.2012:181-186.
[11]SENG K Y,CHEN Y,CHAI K M A,et al.Tracking Body Core Temperature in Military Thermal Environments:An Extended Kalman Filter Approach[C]//IEEE International Conference on Wearable and Implantable Body Sensor Networks.2016:296-299.
[12]ZHANG J M,PRESTI L L,SCLAROFF S.Online Multi-Person Tracking by Tracker Hierarchy[C]//2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance.2012:379-385.
[13]RISTANI E,TOMASI C.Tracking Multiple People Online and in Real Time[J].Lecture Notes in Computer Science,2015,9007:444-459.
[14]QIN Z,SHELTON C R.Improving Multi-target Tracking viaSocial Grouping[C]//IEEE Conference on Computer Vision and Pattern Recognition.2012:1972-1978.
[15]BOSE B,WANG X,GRIMSON E.Multi-class object trackingalgorithm that handles fragmentation and grouping[C]//IEEE Conference on Computer Vision and Pattern Recognition.2007:1567-1574.
[16]CHOI W G.Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor[C]//IEEE Conference on Computer Vision.2015:3029-3037.
[17]SONG J,CHO H,YOON S M.Target Object Tracking-Based 3D Object Reconstruction in a Multiple Camera Environment in Real Time[C]//Asian Conference on Intelligent Information and Database Systems.2017.
[18]TESFAYE Y T,ZEMENE E,PRATI A,et al.Multi-targetTracking in Multiple Non-overlapping Cameras Using Fast-Constrained Dominant Sets[J].International Journal of Computer Vision,2019,127(9):1303-1320.
[19]WU B,NEVATIA R.Detection and tracking of multiple,par-tially occluded humans by Bayesian combination of edgelet based part detectors[J].International Journal of Computer Vision,2007,75(2):247-266.
[20]SVENSSON D,ULMKE M,DANIELSSON L.Joint probabilistic data association filter for partially unresolved target groups[C]//Information Fusion.2011.
[21]LEAL-TAIXÉ L,MILAN A,SCHINDLER K,et al.Tracking the Trackers:An Analysis of the State of the Art in Multiple Object Tracking[EB/OL].(2017-04-01)[2020-11-27].https://ui.adsabs.harvard.edu/abs/2017arXiv170402781L.
[22]DENDORFER P,REZATOFIGHI H,MILAN A,et al.CVPR19 Tracking and Detection Challenge:How crowded can it get[EB/OL].(2019-06-01)[2020-11-27].https://ui.adsabs.harvard.edu/abs/2019arXiv190604567D.
[23]SUGIMURA D,KITANI K M,OKABE T,et al.Using Indivi-duality to Track Individuals:Clustering Individual Trajectories in Crowds using Local Appearance and Frequency Trait[C]//IEEE International Conference on Computer Vision.2009:1467-1474.
[24]YOON J H,LEE C R,YANG M H,et al.Structural Constraint Data Association for Online Multi-object Tracking[J].International Journal of Computer Vision,2019,127(1):1-21.
[25]KUO C H,HUANG C,NEVATIA R.Inter-camera Association of Multi-target Tracks by On-Line Learned Appearance Affinity Models[J].Lecture Notes in Computer Science,2010,6311:383-396.
[26]NITTI D,CHLIVEROS G,PATERAKI M,et al.Application of Dynamic Distributional Clauses for Multi-hypothesis Initialization in Model-based Object Tracking[C]//Proceedings of the 2014 9th International Conference on Computer Vision,Theory and Applications.2014:256-261.
[27]LUO W,XING J,ZHANG X,et al.Multiple Object Tracking:A Literature Review[EB/OL].(2017-05-22)[2020-11-27].https://arxiv.org/abs/1409.7618.
[28]XU Y K,ZHOU X L,CHEN S Y,et al.Deep learning for multiple object tracking:a survey[J].IET Computer Vision,2019,13(4):355-368.
[29]OH S,RUSSELL S,SASTRY S.Markov Chain Monte CarloData Association for Multi-Target Tracking[J].IEEE Transactions on Automatic Control,2009,54(3):481-497.
[30]FAN L T,WANG Z L,CAI B G,et al.A Survey on Multiple Object Tracking Algorithm[C]//2016 IEEE International Conference on Information and Automation.2016:1855-1862.
[31]BAE S H.Survey of amplitude-aided multi-target tracking met-hods[J].IET Radar Sonar and Navigation,2019,13(2):243-253.
[32]FENG X Y,MEI W,HU D S.A Review of Visual Tracking with Deep Learning[C]//International Conference on Artificial Intelligence and Industrial Engineering.2016.
[33]CIAPARRONE G,SÁNCHEZ F L,TABIK S,et al.DeepLearning in Video Multi-Object Tracking:A Survey2019[EB/OL].(2019-06-01)[2020-11-27].https://ui.adsabs.harvard.edu/abs/2019arXiv190712740C.
[34]CAMPLANI M,PAIEMENT A,MIRMEHDI M,et al.Multiple human tracking in RGB-depth data:a survey[J].IET Computer Vision,2017,11(4):265-285.
[35]ATH G D,EVERSON R.Visual Object Tracking:The Initia-lisation Problem[C]//2018 15th Conference on Computer and Robot Vision.2018:142-149.
[36]ULLAH M,CHEIKH F A.A Directed Sparse Graphical Model for Multi-Target Tracking[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.2018:1897-1904.
[37]KIERITZ H,HUBNER W,ARENS M.Joint detection and online multi-object tracking[C]//IEEE Computer Society Confe-rence.2018:1540-1548.
[38]YU F W,LI W B,LI Q Q,et al.POI:Multiple Object Tracking with High Performance Detection and Appearance Feature[J].Lecture Notes in Computer Science,2016,9914:36-42.
[39]WOJKE N,BEWLEY A,PAULUS D.Simple Online and Realtime Tracking with a Deep Association Metric[J].IEEE Tran-sactions on Image Processing,2017:3645-3649.
[40]MAHMOUDI N,AHADI S M,RAHMATI M.Multi-targettracking using CNN-based features:CNNMTT[J].Multimed Tools Application,2019,78(6):7077-7096.
[41]ZHANG Y,WANG C,WANG X,et al.FairMOT:On the Fairness of Detection and Re-Identification in Multiple Object Tracking2020[EB/OL].(2020-04-01)[2020-11-27].https://ui.adsabs.harvard.edu/abs/2020arXiv200401888Z.
[42]WANG Y,WENG X,KITANI K.Joint Detection and Multi-Object Tracking with Graph Neural Networks[EB/OL].(2020-06-23)[2020-11-27].https://arxiv.org/abs/2006.13164v2.
[43]WAN X,CAO J,ZHOU S,et al.End-to-End Multi-ObjectTracking with Global Response Map2020[EB/OL].(2020-07-01)[2020-11-27].https://ui.adsabs.harvard.edu/abs/2020arXiv200706344W.
[44]FANG K,XIANG Y,LI X C,et al.Recurrent AutoregressiveNetworks for Online Multi-Object Tracking[C]//2018 IEEE Winter Conference on Applications of Computer Vision.2018:466-475.
[45]REID D.An Algorithm for Tracking Multiple Targets[J].IEEE Transaction on Automatics Control,1979,24(6):1202-1211.
[46]HAN M,XU W,TAO H,et al.An algorithm for multiple object trajectory tracking[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2004:864-871.
[47]PAPAGEORGIOU D J,SAPUKAS M R.The MaximumWeight Independent Set Problem for Data Association in Multiple Hypothesis Tracking[J].Lecture Notes in Control and Information Sciences,2009,381:235-255.
[48]BRENDEL W,AMER M,TODOROVIC S.Multiobject Trac-king as Maximum Weight Independent Set[C]//2011 IEEE Conference on Computer Vision and Pattern Recognition.2011:1273-1280.
[49]SHENG H,CHEN J H,ZHANG Y,et al.Iterative MultipleHypothesis Tracking With Tracklet-Level Association[J].IEEE Transactions on Circuits and Systems for Video Technology,2019,29(12):3660-3672.
[50]KIM C,LI F X,CIPTADI A,et al.Multiple Hypothesis Trac-king Revisited[C]//IEEE International Conference on Computer Vision.2015:4696-4704.
[51]KOJIMA M,KAMEDA H,TSUJIMICHI S,et al.A study of target tracking using track-oriented multiple hypothesis tracking[C]//Sice '98-Proceedings of the 37th Sice Annual Conference.1998:933-938.
[52]YOO H,KIM K,BYEON M,et al.Online Scheme for Multiple Camera Multiple Target Tracking Based on Multiple Hypothesis Tracking[J].IEEE Transactions on Circuits and Systems for Video Technology,2017,27(3):454-469.
[53]AHMADI K,SALARI E.A novel Multiple Hypothesis Testing (MHT) scheme for tracking of dim objects[C]//IEEE International Conference on Electro/information Technology.2015.
[54]WANG X C,TURETKEN E,FLEURET F,et al.Tracking Interacting Objects Using Intertwined Flows[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(11):2312-2326.
[55]PIRSIAVASH H,RAMANAN D,FOWLKES C C.Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects[C]//2011 IEEE Conference on Computer Vision and Pattern Recognition.2011:1201-1208.
[56]TANG S Y,ANDRES B,ANDRILUKA M,et al.Subgraph Decomposition for Multi-Target Tracking[C]//2015 IEEE Confe-rence on Computer Vision and Pattern Recognition.2015:5033-5041.
[57]DEHGHAN A,ASSARI S M,SHAH M.GMMCP Tracker:Globally Optimal Generalized Maximum Multi Clique Problem for Multiple Object Tracking[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition.2015:4091-4099.
[58]XU Y K,QIN L,HUANG Q M.Coupling Reranking and Structured Output SVM Co-Train for Multitarget Tracking[J].IEEE Transactions on Circuits and Systems for Video Technology,2016,26(6):1084-1098.
[59]KUMAR R,CHARPIAT G,THONNAT M.Multiple ObjectTracking by Efficient Graph Partitioning[C]//Asian Confe-rence on Computer Vision.2014.
[60]ZHANG L,LI Y,NEVATIA R.Global data association formulti-object tracking using network flows[C]//2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2008:1881-1888.
[61]BERCLAZ J,FLEURET F,TURETKEN E,et al.Multiple Object Tracking Using K-Shortest Paths Optimization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(9):1806-1819.
[62]UZUN C,DEMIREKLER M.Stochastic Dynamic Programming Based Resource Allocation for Multi Target Tracking for Electronically Steered Antenna Radar[C]//2015 23rd Signal Processing and Communications Applications Conference.2015:867-870.
[63]HUANG C,WU B,NEVATIA R.Robust Object Tracking byHierarchical Association of Detection Responses[C]//European Conference on Computer Vision.2008:788-801.
[64]KUO C H,HUANG C,NEVATIA R.Multi-Target Tracking by On-Line Learned Discriminative Appearance Models[C]//2010 IEEE Conference on Computer Vision and Pattern Recognition.2010:685-692.
[65]BUTT A A,COLLINS R T.Multi-target Tracking by Lagran-gian Relaxation to Min-Cost Network Flow[C]//IEEE Confe-rence on Computer Vision and Pattern Recognition.2013:1846-1853.
[66]WANG B,WANG G,CHAN K L,et al.Tracklet Association by Online Target-Specific Metric Learning and Coherent Dynamics Estimation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(3):589-602.
[67]MILAN A,ROTH S,SCHINDLER K.Continuous Energy Mi-nimization for Multitarget Tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(1):58-72.
[68]MILAN A,SCHINDLER K,ROTH S.Detection and Trajectory-Level Exclusion in Multiple Object Tracking[C]//Computer Vision and Pattern Recognition.2013.
[69]CHARI V,LACOSTE-JULIEN S,LAPTEV I,et al.On Pair-wise Costs for Network Flow Multi-Object Tracking[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition.2015:5537-5545.
[70]LENZ P,GEIGER A,URTASUN R.FollowMe:Efficient On-line Min-Cost Flow Tracking with Bounded Memory and Computation[C]//IEEE International Conference on Computer Vision.2015:4364-4372.
[71]BAE S H,YOON K J.Confidence-Based Data Association andDiscriminative Deep Appearance Learning for Robust Online Multi-Object Tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(3):595-610.
[72]SADEGHIAN A,ALAHI A,SAVARESE S.Tracking The Untrackable:Learning to Track Multiple Cues with Long-Term Dependencies[C]//2017 IEEE International Conference on Computer Vision.2017:300-311.
[73]LI H X,LI Y,PORIKLI F.DeepTrack:Learning Discriminative Feature Representations Online for Robust Visual Tracking[J].IEEE Transactions on Image Processing,2016,25(4):1834-1848.
[74]FAN J L,XU W,WU Y,et al.Human Tracking Using Convolutional Neural Networks[J].IEEE Transactions on Neural Networks,2010,21(10):1610-1623.
[75]ZHOU Z W,XING J L,ZHANG M D,et al.Online Multi-Target Tracking with Tensor-Based High-Order Graph Matching[C]//2018 24th International Conference on Pattern Recognition (ICPR).2018:1809-1814.
[76]ZENG X Y,OUYANG W L,WANG M,et al.Deep Learning of Scene-Specific Classifier for Pedestrian Detection[J].Lecture Notes in Computer Science,2014,8691:472-487.
[77]BAE S H,YOON K J.Robust Online Multi-Object Trackingbased on Tracklet Confidence and Online Discriminative Appea-rance Learning[C]//IEEE Conference on Computer Vision and Pattern Recognition.2014:1218-1225.
[78]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition.2014:580-587.
[79]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[80]HE K M,GKIOXARI G,DOLLAR P,et al.Mask R-CNN[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017:2980-2988.
[81]REDMON J,FARHADI A.YOLO9000:Better,Faster,Stronger[C]//IEEE Conference on Computer Vision and Pattern Recognition.2017:6517-6525.
[82]REDMON J,FARHADI A.YOLOv3:An Incremental Improvement[EB/OL].(2018-04-08)[2020-11-27].https://arxiv.org/abs/1804.02767.
[83]BODLA N,SINGH B,CHELLAPPA R,et al.Soft-NMS-Improving Object Detection With One Line of Code[C]//IEEE International Conference on Computer Vision.2017:5562-5570.
[84]LAW H,DENG J.CornerNet:Detecting Objects as Paired Keypoints[J].International Journal of Computer Vision,2020:642-656.
[85]ZHOU X,WANG D,KRHENBÜHlP. Objects as Points[EB/OL].(2019-04-16)[2020-11-27].https://arxiv.org/abs/1904.07850.
[86]LAW H,TENG Y,RUSSAKOVSKY O,et al.CornerNet-Lite:Efficient Keypoint Based Object Detection[EB/OL].(2019-04-18)[2020-11-27].https://arxiv.org/abs/1904.08900v2.
[87]MILAN A,REZATOFIGHI S H,DICK A,et al.Online Multi-Target Tracking Using Recurrent Neural Networks[C]//Thirty-First Aaai Conference on Artificial Intelligence.2017:4225-4232.
[88]QI C,OUYANG W L,LI H S,et al.Online Multi-ObjectTracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism[C]//IEEE International Conference on Computer Vision.2017:4846-4855.
[89]LEAL-TAIXE L,CANTON-FERRER C,SCHINDLER K.Learning by tracking:Siamese CNN for robust target association[C]//IEEE Computer Society Conference.2016:418-425.
[90]WANG B,WANG L,SHUAI B,et al.Joint Learning of Convolutional Neural Networks and Temporally Constrained Metrics for Tracklet Association[C]//IEEE Computer Society Confe-rence.2016:386-393.
[91]SON J,BAEK M,CHO M,et al.Multi-Object Tracking withQuadruplet Convolutional Neural Networks[C]//30th IEEE Conference on Computer Vision and Pattern Recognition.2017:3786-3795.
[92]TANG S Y,ANDRES B,ANDRILUKA M,et al.Multi-person Tracking by Multicut and Deep Matching[C]//2016 European Conference on Computer Vision Workshops.2016:100-111.
[93]TANG S Y,ANDRILUKA M,ANDRES B,et al.Multiple People Tracking by Lifted Multicut and Person Re-identification[C]//30th IEEE Conference on Computer Vision and Pattern Recognition.2017:3701-3710.
[94]SCHULTER S,VERNAZA P,CHOI W,et al.Deep Network Flow for Multi-Object Tracking[C]//30th IEEE Conference on Computer Vision and Pattern Recognition.2017:2730-2739.
[95]CHEN L,AI H Z,SHANG C,et al.Online Multi-Object Trac-king with Convolutional Neural Networks[C]//IEEE International Conference on Image Processing.2017:645-649.
[96]TIAN Y C,DEHGHAN A,SHAH M.On Detection,Data Association and Segmentation for Multi-Target Tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,41(9):2146-2160.
[97]CHU P,FAN H,TAN C C,et al.Online Multi-Object Tracking With Instance-Aware Tracker and Dynamic Model Refreshment[C]//IEEE Winter Conference on Applications of Computer Vision.2019.
[98]DAI J F,QI H Z,XIONG Y W,et al.Deformable Convolutional Networks[C]//IEEE International Conference on Computer Vision.2017:764-773.
[99]ZHU X Z,HU H,LIN S,et al.Deformable ConvNets v2:More Deformable,Better Results[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (Cvpr 2019).2019:9300-9308.
[100]HAN K,WANG Y,TIAN Q,et al.GhostNet:More Features From Cheap Operations[C]//CVF Conference on Computer Vision and Pattern Recognition.2020.
[101]HAN R,FENG W,ZHAO J,et al.Complementary-View Multiple Human Tracking[C]//Thirty-Fourth AAAI Conference on Artificial Intelligence.2020.
[102]LUO W H,STENGER B,ZHAO X W,et al.Trajectories asTopics:Multi-Object Tracking by Topic Discovery[J].IEEE Transactions on Image Processing,2019,28(1):240-252.
[103]PAPADIMITRIOU C H,RAGHAVAN P,TAMAKI H,et al.Latent semantic indexing:A probabilistic analysis[J].Journal of Computer and System Sciences,1998,61(2):217-235.
[104]BLEI D M,NG A Y,JORDAN M I.Latent Dirichlet allocation[C]//Advances in Neural Information Processing Systems.2001.
[105]JBABDI S,WOOLRICH M W,BEHRENS T E J.Multiple-subjects connectivity-based parcellation using hierarchical Dirichlet process mixture models[J].Neuroimage,2009,44(2):373-384.
[106]TOPKAYA I S,ERDOGAN H,PORIKLI F.Detecting andTracking Unknown Number of Objects with Dirichlet Process Mixture Models and Markov Random Fields[J].Advances in Visual Computing,2013,8034:178-188.
[107]NEISWANGER W,WOOD F,XING E.The DependentDirichlet Process Mixture of Objects for Detection-free Trac-king and Object Modeling[J].Journal of Machine Learning Research,2014,33:660-668.
[108]FOX E,SUDDERTH E B,WILLSKY A S.HierarchicalDirichlet processes for tracking maneuvering targets[C]//2007 Proceedings of the 10th International Conference on Information Fusion.2007.
[109]TOPKAYA I S,ERDOGAN H,PORIKLI F.Tracklet clustering for robust multiple object tracking using distance dependent Chinese restaurant processes[J].Signal Image and Video Processing,2015,10(5):795-802.
[110]CAO L L,LI F F.Spatially coherent latent topic model for concurrent segmentation and classification of objects and scenes[C]//2007 IEEE 11th International Conference on Computer Vision.2007:1080-1087.
[111]WANG X,GRIMSON E.Spatial Latent Dirichlet Allocation[C]//Conference on Advances in Neural Information Processing Systems.2007.
[112]VERBEEK J,TRIGGS W.Region Classification with MarkovField Aspect Models[C]//2007 IEEE Computer Society Confe-rence on Computer Vision and Pattern Recognition.2007.
[113]WANG X G,MA K T,NG G W,et al.Trajectory Analysis and Semantic Region Modeling Using Nonparametric Hierarchical Bayesian Models[J].International Journal of Computer Vision,2011,95(3):287-312.
[114]WANG C,BLEI D,LI F F.Simultaneous Image Classification and Annotation[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition.2009.
[115]FEI-FEI L,PERONA P.A Bayesian hierarchical model forlearning natural scene categories[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2005:524-531.
[1] 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺.
时序知识图谱表示学习
Temporal Knowledge Graph Representation Learning
计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[2] 饶志双, 贾真, 张凡, 李天瑞.
基于Key-Value关联记忆网络的知识图谱问答方法
Key-Value Relational Memory Networks for Question Answering over Knowledge Graph
计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[3] 汤凌韬, 王迪, 张鲁飞, 刘盛云.
基于安全多方计算和差分隐私的联邦学习方案
Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy
计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[4] 孙奇, 吉根林, 张杰.
基于非局部注意力生成对抗网络的视频异常事件检测方法
Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection
计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[5] 沈祥培, 丁彦蕊.
多检测器融合的深度相关滤波视频多目标跟踪算法
Multi-detector Fusion-based Depth Correlation Filtering Video Multi-target Tracking Algorithm
计算机科学, 2022, 49(8): 184-190. https://doi.org/10.11896/jsjkx.210600004
[6] 王剑, 彭雨琦, 赵宇斐, 杨健.
基于深度学习的社交网络舆情信息抽取方法综述
Survey of Social Network Public Opinion Information Extraction Based on Deep Learning
计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[7] 王馨彤, 王璇, 孙知信.
基于多尺度记忆残差网络的网络流量异常检测模型
Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network
计算机科学, 2022, 49(8): 314-322. https://doi.org/10.11896/jsjkx.220200011
[8] 郝志荣, 陈龙, 黄嘉成.
面向文本分类的类别区分式通用对抗攻击方法
Class Discriminative Universal Adversarial Attack for Text Classification
计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[9] 姜梦函, 李邵梅, 郑洪浩, 张建朋.
基于改进位置编码的谣言检测模型
Rumor Detection Model Based on Improved Position Embedding
计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[10] 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木.
中文预训练模型研究进展
Advances in Chinese Pre-training Models
计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018
[11] 周慧, 施皓晨, 屠要峰, 黄圣君.
基于主动采样的深度鲁棒神经网络学习
Robust Deep Neural Network Learning Based on Active Sampling
计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
[12] 苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫.
小样本雷达辐射源识别的深度学习方法综述
Survey of Deep Learning for Radar Emitter Identification Based on Small Sample
计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138
[13] 胡艳羽, 赵龙, 董祥军.
一种用于癌症分类的两阶段深度特征选择提取算法
Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification
计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[14] 程成, 降爱莲.
基于多路径特征提取的实时语义分割方法
Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction
计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[15] 刘伟业, 鲁慧民, 李玉鹏, 马宁.
指静脉识别技术研究综述
Survey on Finger Vein Recognition Research
计算机科学, 2022, 49(6A): 1-11. https://doi.org/10.11896/jsjkx.210400056
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发