{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T06:20:54Z","timestamp":1772605254975,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/tmm.2018.2808760","type":"journal-article","created":{"date-parts":[[2018,2,21]],"date-time":"2018-02-21T19:24:29Z","timestamp":1519241069000},"page":"2824-2835","source":"Crossref","is-referenced-by-count":37,"title":["Recognition of Emotions in User-Generated Videos With Kernelized Features"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0021-3634","authenticated-orcid":false,"given":"Haimin","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9581-8849","authenticated-orcid":false,"given":"Min","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","volume":"4","author":"folland","year":"1992","journal-title":"Fourier Analysis and its Applications"},{"key":"ref38","first-page":"675","article-title":"Caffe: Convolutional architecture for fast feature embedding","author":"jia","year":"0","journal-title":"Proc 22nd ACM Int Conf Multimedia"},{"key":"ref33","volume":"143","author":"alpay","year":"2012","journal-title":"Reproducing Kernel Spaces and Applications"},{"key":"ref32","article-title":"Near-optimal nonmyopic value of information in graphical models","author":"krause","year":"2012","journal-title":"arXiv 1207 1394"},{"key":"ref31","author":"sch\u00f6lkopf","year":"2001","journal-title":"Learning With Kernels Support Vector Machines Regularization Optimization and Beyond (Adaptive Computation and Machine Learning)"},{"key":"ref30","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref37","volume":"3","author":"plutchik","year":"1986","journal-title":"Emotion Theory Research and Experience"},{"key":"ref36","first-page":"3360","article-title":"Locality-constrained linear coding for image classification","author":"wang","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.20132"},{"key":"ref34","author":"sch\u00f6lkopf","year":"2002","journal-title":"Learning with kernels"},{"key":"ref10","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1981.1163711"},{"key":"ref11","first-page":"1440","article-title":"Fast R-CNN","author":"girshick","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref12","first-page":"2980","article-title":"Mask R-CNN","author":"he","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref13","first-page":"2064","article-title":"Deep supervised hashing for fast image retrieval","author":"liu","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref14","article-title":"Heterogeneous knowledge transfer in video emotion recognition, attribution and summarization","author":"xu","year":"0","journal-title":"IEEE Trans Affective Comput"},{"key":"ref15","first-page":"1097","article-title":"Imagenet\n classification with deep convolutional neural networks","author":"krizhevsky","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"1","article-title":"Going deeper with convolutions","author":"szegedy","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref17","author":"ekman","year":"1982","journal-title":"Emotion in the Human Face"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1037\/h0054570"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2163058"},{"key":"ref28","first-page":"770","article-title":"Deep residual learning for image recognition","author":"he","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref4","first-page":"1939","article-title":"Bidirectional multirate\n reconstruction for temporal modeling in videos","author":"zhu","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2482228"},{"key":"ref3","first-page":"3034","article-title":"Dynamic image networks for action recognition","author":"bilen","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref6","first-page":"73","article-title":"Predicting\n emotions in user-generated videos","author":"jiang","year":"0","journal-title":"Proc AAAI"},{"key":"ref29","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2539546"},{"key":"ref8","first-page":"459","article-title":"Sentibank: Large-scale ontology and\n classifiers for detecting sentiment and emotions in visual content","author":"borth","year":"0","journal-title":"Proc 21st ACM Int Conf Multimedia"},{"key":"ref7","first-page":"1378","article-title":"Object bank: A high-level\n image representation for scene classification & semantic feature sparsification","author":"li","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","first-page":"1951","article-title":"Vlad3: Encoding dynamics of deep features for\n action recognition","author":"li","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref9","first-page":"647","article-title":"Decaf: A deep convolutional activation feature\n for generic visual recognition","author":"donahue","year":"0","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref1","first-page":"1933","article-title":"Convolutional two-stream network fusion for video action recognition","author":"feichtenhofer","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1007\/978-3-642-03767-2_70","article-title":"Color based bags-of-emotions","author":"solli","year":"2009","journal-title":"Computer Analysis of Images and Patterns"},{"key":"ref45","author":"aharon","year":"2006","journal-title":"Overcomplete dictionaries for sparse representation of signals"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2004.839993"},{"key":"ref21","first-page":"259","article-title":"Affective content detection using HMMs","author":"kang","year":"0","journal-title":"Proc 11th ACM Int Conf Multimedia"},{"key":"ref42","first-page":"1798","article-title":"A discriminative cnn\n video representation for event detection","author":"xu","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref24","first-page":"127","article-title":"Emotion\n in context: Deep semantic feature fusion for video emotion recognition","author":"chen","year":"0","journal-title":"Proc ACM Multimedia Conf"},{"key":"ref41","first-page":"1871","article-title":"Liblinear: A library for large linear classification","volume":"9","author":"fan","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref23","first-page":"776","article-title":"Efficient object category recognition using classemes","author":"torresani","year":"0","journal-title":"Proc Computer Vision"},{"key":"ref44","first-page":"3304","article-title":"Aggregating local descriptors into\n a compact image representation","author":"j\u00e9gou","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2012.06.026"},{"key":"ref43","first-page":"1","article-title":"Fisher kernels on visual vocabularies for image categorization","author":"perronnin","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2006.873781"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8466674\/08299568.pdf?arnumber=8299568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T10:19:51Z","timestamp":1643192391000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8299568\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":45,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2808760","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10]]}}}