{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:14:47Z","timestamp":1740132887731,"version":"3.37.3"},"reference-count":137,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1109\/tmm.2019.2959426","type":"journal-article","created":{"date-parts":[[2019,12,12]],"date-time":"2019-12-12T20:44:46Z","timestamp":1576183486000},"page":"1769-1784","source":"Crossref","is-referenced-by-count":9,"title":["Spatio-Temporal VLAD Encoding of Visual Events Using Temporal Ordering of the Mid-Level Deep Semantics"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5674-5931","authenticated-orcid":false,"given":"Mohammad","family":"Soltanian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0322-9324","authenticated-orcid":false,"given":"Sajjad","family":"Amini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9556-8090","authenticated-orcid":false,"given":"Shahrokh","family":"Ghaemmaghami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2863943"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.332"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref34","first-page":"76","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2359771"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/11744047_33"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291311"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2017.05.005"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2647904"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.60"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-013-0567-0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502171"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.207"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2013.6474994"},{"key":"ref56","first-page":"12","article-title":"ITI-CERTH participation to TRECVID 2013","author":"markatopoulou","year":"0","journal-title":"Proc TRECVID Workshop"},{"key":"ref55","first-page":"44","article-title":"Evaluating inverted files for visual compact codes on a large scale","author":"amato","year":"0","journal-title":"Proc 10th Int Workshop Large-Scale Distrib Syst Inf Retrieval LSDS-IR Co-Located"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2012.2206386"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2071944"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref40","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.265"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995435"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref8","article-title":"A learning-based frame pooling model for event detection","volume":"abs 1603 2078","author":"liu","year":"2016","journal-title":"CoRR"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2191395"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2166951"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2449660"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2191943"},{"key":"ref48","first-page":"1","article-title":"Visual categorization with bags of keypoints","volume":"1","author":"csurka","year":"0","journal-title":"Proc Workshop Learning in Computer Vision"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2264928"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2844101"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911826"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2321530"},{"article-title":"The monkeytyping solution to the youtube-8m video understanding challenge","year":"2017","author":"wang","key":"ref127"},{"article-title":"Learnable pooling with context gating for video classification","year":"2017","author":"miech","key":"ref126"},{"article-title":"Machine learning evaluation metrics, implemented in Python, R, Haskell, and MATLAB \/ Octave: Benhamner\/Metrics","year":"2019","author":"hamner","key":"ref125"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874249"},{"key":"ref73","first-page":"111","article-title":"A theoretical analysis of feature pooling in visual recognition","author":"boureau","year":"0","journal-title":"Proc 27th Int Conf Mach Learn"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CCECE.2015.7129346"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_19"},{"key":"ref71","first-page":"109","article-title":"Hybrid super vector with improved dense trajectories for action recognition","author":"peng","year":"0","journal-title":"Proc Workshops Int Conf Comput Vision"},{"article-title":"Temporal modeling approaches for large-scale youtube-8m video understanding","year":"2017","author":"li","key":"ref128"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2637379"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.5244\/C.27.132"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_23"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ISCID.2014.238"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2011.07.011"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.317"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_27"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2329648"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref79","first-page":"774","article-title":"Negative evidences and co-occurrences in image retrieval: The benefit of PCA and whitening","author":"j\u00e9gou","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref136","first-page":"305","article-title":"Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification","author":"xie","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01233"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.177"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2015.7177501"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025610"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471878"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2011.6116641"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2012.6467387"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_43"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2012.6467561"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CONECCT.2014.6740340"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-010-0643-7"},{"key":"ref69","first-page":"2486","article-title":"In defense of soft-assignment coding","author":"liu","year":"0","journal-title":"Proc IEEE Int Conf Comput Vision"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396477"},{"key":"ref109","article-title":"SA-CNN: dynamic scene classification using convolutional neural networks","volume":"abs 1502 5243","author":"gangopadhyay","year":"0","journal-title":"Proc CoRR"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.06.002"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.318"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2511585"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.94"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_24"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.339"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/3231739"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533142"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-51811-4_30"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2436813"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.288"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_38"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1964-11178-2"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.109"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0723-7"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2890749"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.427"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.154"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.228"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911830"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911832"},{"key":"ref15","first-page":"4321","article-title":"Encoding feature maps of CNNs for action recognition","author":"peng","year":"0","journal-title":"Proc THUMOS Challenge Workshop"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_38"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.219"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2666540"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"},{"key":"ref81","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"article-title":"The AXES submissions at TrecVid 2013","year":"2013","author":"aly","key":"ref17"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/NCVPRIPG.2013.6776268"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2895472"},{"article-title":"Youtube-8m: A large-scale video classification benchmark","year":"2016","author":"abu-el-haija","key":"ref119"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2712789"},{"article-title":"Deep learning using linear support vector machines","year":"2013","author":"tang","key":"ref114"},{"key":"ref113","first-page":"67","article-title":"Sur l quation en matrices px= xq","volume":"99","author":"sylvester","year":"1884","journal-title":"CR Acad Sci Paris"},{"key":"ref116","first-page":"10","article-title":"Deep ADMM-Net for compressive sensing MRI","author":"sun","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2012.06.005"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654931"},{"article-title":"The kinetics human action video dataset","year":"2017","author":"kay","key":"ref120"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"year":"2015","key":"ref122"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807412"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.330"},{"key":"ref86","first-page":"3021","article-title":"Robust late fusion with rank minimization","author":"ye","year":"0","journal-title":"Proc IEEE Conf Comput Vision Pattern Recognit"},{"key":"ref87","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1109\/TPAMI.2013.128","article-title":"Learning multimodal latent attributes","volume":"36","author":"fu","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref88","article-title":"UC merced submission to the ActivityNet challenge 2016","volume":"abs 1704 3503","author":"zhu","year":"2017","journal-title":"CoRR"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9132597\/08931623.pdf?arnumber=8931623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:56:14Z","timestamp":1651074974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8931623\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":137,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2959426","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2020,7]]}}}