{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T02:55:09Z","timestamp":1773111309369,"version":"3.50.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3011977","type":"journal-article","created":{"date-parts":[[2020,7,27]],"date-time":"2020-07-27T21:23:11Z","timestamp":1595884991000},"page":"136843-136857","source":"Crossref","is-referenced-by-count":36,"title":["Enhanced Video Analytics for Sentiment Analysis Based on Fusing Textual, Auditory and Visual Information"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7893-1196","authenticated-orcid":false,"given":"Sadam","family":"Al-Azani","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6279-9776","authenticated-orcid":false,"given":"El-Sayed M.","family":"El-Alfy","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref38","first-page":"2378","article-title":"Toward’s Arabic multi-modal sentiment analysis","author":"alqarafi","year":"2018","journal-title":"Proc Int Conf Signal Process Commun"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2006.145"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00169"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18178\/joig.6.1.39-43"},{"key":"ref36","first-page":"1","article-title":"Predicting emotions in user-generated videos","author":"jiang","year":"2014","journal-title":"Proc 28th AAAI Conf Artif Intell"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2396531"},{"key":"ref34","first-page":"48","article-title":"Multimodal sentiment analysis of Telugu songs","author":"abburi","year":"2016","journal-title":"Proc 25th Int Joint Conf Artif Intell"},{"key":"ref60","first-page":"45","article-title":"Software framework for topic modelling with large corpora","author":"rehurek","year":"2010","journal-title":"Proc LREC Workshop New Challenges NLP Frameworks"},{"key":"ref62","author":"bradski","year":"2008","journal-title":"Learning OpenCV Computer Vision With the OpenCV Library"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0144610"},{"key":"ref63","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2010.5583006"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1002\/0470013494.ch3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.927665"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2200\/S00277ED1V01Y201008HLT010"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2017.2695613"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2200\/S00416ED1V01Y201204HLT016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0055"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-012-0314-x"},{"key":"ref21","first-page":"1","article-title":"Ensemble of SVM trees for multimodal emotion recognition","author":"rozgi?","year":"2012","journal-title":"Proc Asia Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2955300"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1109\/T-AFFC.2010.16","article-title":"Emotion recognition of affective speech based on multiple classifiers using acoustic-prosodic information and semantic labels","volume":"2","author":"wu","year":"2011","journal-title":"IEEE Trans Affect Comput"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.4108\/e-forensics.2008.2743"},{"key":"ref51","first-page":"121","article-title":"An iterative image registration technique with an application to stereo vision","author":"lucas","year":"1981","journal-title":"Proc Imag Understand Workshop"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1201\/b17320"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3264-1"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2018.090625"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.352"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45103-X_50"},{"key":"ref52","article-title":"Good features to track","author":"shi","year":"1994","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070509"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2013.34"},{"key":"ref40","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2009.194"},{"key":"ref13","first-page":"973","article-title":"Utterance-level multimodal sentiment analysis","author":"p\u00e9rez-rosas","year":"2013","journal-title":"Proc Assoc for Computational Linguistics (ACL '01)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2011.5771414"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2013.9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1303"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.01.095"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.04.024"},{"key":"ref19","first-page":"659","article-title":"Fusing audio, textual, and visual features for sentiment analysis of news videos","author":"pereira","year":"2016","journal-title":"Proc 10th Int'l Conf Web and Social Media"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2432791"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref6","first-page":"393","article-title":"Multimedia user interface design","author":"sutcliffe","year":"2008","journal-title":"The Human-Computer Interaction Handbook Fundamentals Evolving Technologies and Emerging Applications"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.07.041"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"1222","DOI":"10.1109\/TII.2013.2255616","article-title":"Intelligent video systems and analytics: A survey","volume":"9","author":"liu","year":"2013","journal-title":"IEEE Trans Ind Informat"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2682899"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1002\/scj.4690220607"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2926751"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.10.117"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.05.365"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.02.008"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-15530-2"},{"key":"ref42","first-page":"2418","article-title":"Word embeddings and convolutional neural network for Arabic sentiment classification","author":"dahou","year":"2016","journal-title":"Proc Int Conf on Computational Linguistics (COLING)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IACS.2018.8355456"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70096-0_51"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09148603.pdf?arnumber=9148603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T15:57:38Z","timestamp":1642003058000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9148603\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3011977","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}