{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T02:10:03Z","timestamp":1751681403170,"version":"3.41.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,6,8]],"date-time":"2018-06-08T00:00:00Z","timestamp":1528416000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Key Laboratory of Forensic Marks, Ministry of Public Security"},{"DOI":"10.13039\/501100001809","name":"Chinese National Natural Science Foundation","doi-asserted-by":"crossref","award":["61532018, 61372169, 61471049"],"award-info":[{"award-number":["61532018, 61372169, 61471049"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,1]]},"DOI":"10.1007\/s11042-018-6163-6","type":"journal-article","created":{"date-parts":[[2018,6,8]],"date-time":"2018-06-08T17:59:24Z","timestamp":1528480764000},"page":"817-838","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["A comprehensive solution for detecting events in complex surveillance videos"],"prefix":"10.1007","volume":"78","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7234-1694","authenticated-orcid":false,"given":"Yandong","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaihui","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Menglai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhicheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,8]]},"reference":[{"issue":"1","key":"6163_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2015.2439257","volume":"38","author":"BB Amor","year":"2016","unstructured":"Amor BB, Jingyong S, Srivastava A (2016) Action recognition using rate-invariant analysis of skeletal shape trajectories. IEEE Trans Pattern Anal Mach Intell 38(1):1\u201313","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6163_CR2","unstructured":"S Bell, CL Zitnick, K Bala, R Girshick (2015) Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks. arXiv 1\u201324"},{"key":"6163_CR3","doi-asserted-by":"crossref","unstructured":"Cai Z, et al. (2016) A unified multi-scale deep convolutional neural network for fast object detection. European Conference on Computer Vision. Springer International Publishing","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"6163_CR4","doi-asserted-by":"crossref","unstructured":"Chang BW, R Nevatia (2008) Robust object tracking by hierarchical association of detection responses.\" European Conference on Computer Vision. Springer Berlin Heidelberg","DOI":"10.1007\/978-3-540-88688-4_58"},{"key":"6163_CR5","doi-asserted-by":"crossref","unstructured":"X Chang et al. (2016) Semantic pooling for complex event analysis in untrimmed videos. IEEE Trans Patt Anal Mach Intel","DOI":"10.1109\/TPAMI.2016.2608901"},{"key":"6163_CR6","unstructured":"X Chang et al. (2016) Bi-level semantic representation analysis for multimedia event detection. IEEE Trans Cybernet"},{"key":"6163_CR7","doi-asserted-by":"crossref","unstructured":"Chen Q et al. (2015) Part-based deep network for pedestrian detection in surveillance videos.\" Visual Communications and Image Processing (VCIP), 2015. IEEE","DOI":"10.1109\/VCIP.2015.7457855"},{"key":"6163_CR8","doi-asserted-by":"crossref","unstructured":"Dalal N, B Triggs (2005) Histograms of oriented gradients for human detection.\" Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. Vol. 1. IEEE","DOI":"10.1109\/CVPR.2005.177"},{"issue":"9","key":"6163_CR9","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb PF et al (2010) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627\u20131645","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6163_CR10","doi-asserted-by":"crossref","unstructured":"Gidaris, Spyros, and Nikos Komodakis (2015) Object detection via a multi-region and semantic segmentation-aware cnn model. Proc IEEE Int Conf Comput Vis","DOI":"10.1109\/ICCV.2015.135"},{"key":"6163_CR11","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. Proc IEEE Int Conf Comput Vis","DOI":"10.1109\/ICCV.2015.169"},{"key":"6163_CR12","doi-asserted-by":"crossref","unstructured":"Girshick R et al. (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. Proc IEEE Conf Comput Vis Patt Recog","DOI":"10.1109\/CVPR.2014.81"},{"issue":"1\u20133","key":"6163_CR13","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","volume":"17","author":"BKP Horn","year":"1981","unstructured":"Horn BKP, Schunck BG (1981) Determining optical flow. Artif Intell 17(1\u20133):185\u2013203","journal-title":"Artif Intell"},{"key":"6163_CR14","unstructured":"http:\/\/crcv.ucf.edu\/data\/UCF101.php"},{"key":"6163_CR15","unstructured":"https:\/\/www.nist.gov\/itl\/iad\/mig\/trecvid-multimedia-event-detection-evaluation-track"},{"key":"6163_CR16","unstructured":"Karen, A Zisserman (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"6163_CR17","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn HW (1955) The Hungarian method for the assignment problem. Naval Res Logist Quart 2:83\u201397 Kuhn's original publication","journal-title":"Naval Res Logist Quart"},{"key":"6163_CR18","doi-asserted-by":"crossref","unstructured":"D Le, S Phan, Y Miyao, S Satoh et al (2016) @ TRECVID","DOI":"10.1016\/j.amcp.2016.02.004"},{"key":"6163_CR19","doi-asserted-by":"crossref","unstructured":"Lenz P, A Geiger, R Urtasun (2015) Followme: Efficient online min-cost flow tracking with bounded memory and computation. Proc IEEE Int Conf Comput Vis","DOI":"10.1109\/ICCV.2015.496"},{"key":"6163_CR20","unstructured":"Li Y, K He, J Sun (2016) \"R-fcn: Object detection via region-based fully convolutional networks. Adv Neural Info Proc Syst"},{"key":"6163_CR21","unstructured":"J. Liang, P. Huang, L. Jiang, Z. Lan, J. Chen, A. Hauptmann et al. @ TRECVID (2016) Multimedia event Detection, Ad-hoc Video Search, Surveillance event Detection"},{"issue":"1","key":"6163_CR22","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1109\/TCYB.2015.2399172","volume":"46","author":"L Liu","year":"2016","unstructured":"Liu L et al (2016) Learning spatio-temporal representations for action recognition: a genetic programming approach. IEEE Trans Cybernet 46(1):158\u2013170","journal-title":"IEEE Trans Cybernet"},{"issue":"2","key":"6163_CR23","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91\u2013110","journal-title":"Int J Comput Vis"},{"key":"6163_CR24","first-page":"841","volume":"2","author":"AY Ng","year":"2002","unstructured":"Ng AY, Jordan MI (2002) On discriminative vs. generative classifiers: a comparison of logistic regression and naive bayes. Adv Neural Inf Proces Syst 2:841\u2013848","journal-title":"Adv Neural Inf Proces Syst"},{"key":"6163_CR25","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.cviu.2016.03.013","volume":"150","author":"X Peng","year":"2016","unstructured":"Peng X, Wang L, Wang X et al (2016) Bag of visual words and fusion methods for action recognition: comprehensive study and good practice. Comput Vis Image Underst 150:109\u2013125","journal-title":"Comput Vis Image Underst"},{"key":"6163_CR26","doi-asserted-by":"crossref","unstructured":"Prince, SJD (2012) Computer vision: models, learning, and inference\". Cambridge University Press","DOI":"10.1017\/CBO9780511996504"},{"key":"6163_CR27","doi-asserted-by":"crossref","unstructured":"Redmon J et al. (2016) You only look once: Unified, real-time object detection.\" Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2016.91"},{"key":"6163_CR28","unstructured":"Ren S et al. (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Adv Neur Info Proc Syst"},{"issue":"3","key":"6163_CR29","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"key":"6163_CR30","unstructured":"Simonyan K, A Zisserman (2014) Two-stream convolutional networks for action recognition in videos. Adv Neur Info Proc Syst"},{"key":"6163_CR31","doi-asserted-by":"crossref","unstructured":"Solera F, S Calderara, R Cucchiara (2015) Learning to divide and conquer for online multi-target tracking. Proc IEEE Int Conf Comput Vis","DOI":"10.1109\/ICCV.2015.497"},{"key":"6163_CR32","doi-asserted-by":"crossref","unstructured":"Wang H et al. (2011) Action recognition by dense trajectories.\" Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE","DOI":"10.1109\/CVPR.2011.5995407"},{"issue":"1","key":"6163_CR33","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang H et al (2013) Dense trajectories and motion boundary descriptors for action recognition. Int J Comput Vis 103(1):60\u201379","journal-title":"Int J Comput Vis"},{"key":"6163_CR34","doi-asserted-by":"crossref","unstructured":"Wang, et al (2016) Tracklet association by online target-specific metric learning and coherent dynamics estimation. IEEE Trans Patt Anal Mach Intel","DOI":"10.1109\/TPAMI.2016.2551245"},{"issue":"12","key":"6163_CR35","doi-asserted-by":"publisher","first-page":"2978","DOI":"10.1109\/TCYB.2015.2493538","volume":"46","author":"J Wu","year":"2016","unstructured":"Wu J, Zhang Y, Lin W (2016) Good practices for learning to recognize actions using FV and VLAD. IEEE Trans Cybernet 46(12):2978\u20132990","journal-title":"IEEE Trans Cybernet"},{"key":"6163_CR36","unstructured":"P. Yang, J. Xiong, D. Xie, S. Pu, HRI Team @ TRECVID (2016) Surveillance event detection"},{"key":"6163_CR37","unstructured":"S Yu, L Jiang, CMU Informedia @ TRECVID (2015). Proc TRECVID 2015 Work"},{"key":"6163_CR38","doi-asserted-by":"crossref","unstructured":"Zach C, T Pock, H Bischof (2007) A duality based approach for realtime TV-L 1 optical flow. Pattern Recog 214\u2013223","DOI":"10.1007\/978-3-540-74936-3_22"},{"issue":"5","key":"6163_CR39","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1109\/TCSVT.2012.2226526","volume":"23","author":"Z-J Zha","year":"2013","unstructured":"Zha Z-J et al (2013) Detecting group activities with multi-camera context. IEEE Trans Circ Syst Video Technol 23(5):856\u2013869","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"6163_CR40","unstructured":"Zhang L, Y Li, R Nevatia (2008) Global data association for multi-object tracking using network flows. Comput Vis Patt Recog, 2008. CVPR 2008. IEEE Conference on. IEEE"},{"issue":"2","key":"6163_CR41","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1016\/j.patcog.2014.08.013","volume":"48","author":"S Zhang","year":"2015","unstructured":"Zhang S et al (2015) Multi-target tracking by learning local-to-global trajectory models. Pattern Recogn 48(2):580\u2013590","journal-title":"Pattern Recogn"},{"issue":"3","key":"6163_CR42","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1109\/TIP.2015.2511585","volume":"25","author":"X Zhang","year":"2016","unstructured":"Zhang X et al (2016) Deep fusion of multiple semantic cues for complex event recognition. IEEE Trans Image Process 25(3):1033\u20131046","journal-title":"IEEE Trans Image Process"},{"issue":"4","key":"6163_CR43","doi-asserted-by":"publisher","first-page":"1746","DOI":"10.1109\/TIP.2017.2658957","volume":"26","author":"D Zhang","year":"2017","unstructured":"Zhang D, Han J, Jiang L, Ye S, Chang X (2017) Revealing event saliency in unconstrained video collection. IEEE Trans Image Process 26(4):1746\u20131758","journal-title":"IEEE Trans Image Process"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-6163-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6163-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6163-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T01:41:28Z","timestamp":1751679688000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-6163-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,8]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,1]]}},"alternative-id":["6163"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-6163-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2018,6,8]]},"assertion":[{"value":"28 April 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 March 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}