{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T17:48:41Z","timestamp":1785865721132,"version":"3.56.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1109\/access.2021.3116530","type":"journal-article","created":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T21:37:51Z","timestamp":1632951471000},"page":"135559-135570","source":"Crossref","is-referenced-by-count":38,"title":["An End-To-End Emotion Recognition Framework Based on Temporal Aggregation of Multimodal Information"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7577-1067","authenticated-orcid":false,"given":"Anamaria","family":"Radoi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreea","family":"Birhala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolae-Catalin","family":"Ristea","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liviu-Cristian","family":"Dutu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref38","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume":"28","author":"sutskever","year":"2013","journal-title":"Proc ICML"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"612","DOI":"10.21437\/Interspeech.2014-147","article-title":"Comparing time-frequency representations for directional derivative features","author":"gibson","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"1558","DOI":"10.1109\/PROC.1977.10770","article-title":"a unified approach to short-time fourier analysis and synthesis","volume":"65","author":"allen","year":"1977","journal-title":"Proceedings of the IEEE"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2938007"},{"key":"ref30","article-title":"Deep representation learning in speech processing: Challenges, recent advances, and future trends","author":"latif","year":"2020","journal-title":"arXiv 2001 00378"},{"key":"ref37","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","year":"2019","journal-title":"Joint Challenge on Compound Emotion Recognition and Multimodal (Audio Facial and Gesture) Based Emotion Recognition (CER&MMER)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3019084"},{"key":"ref34","author":"o\u2019shaughnessy","year":"2000","journal-title":"Speech Communications Human and Machine"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3071503"},{"key":"ref40","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref13","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997627"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2928625"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054317"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref27","article-title":"A personalized affective memory neural model for improving emotion recognition","author":"barros","year":"2019","journal-title":"arXiv 1904 12632"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2512530.2512533"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2019.8906538"},{"key":"ref29","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/34.908962"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925444"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K18-1025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2008.918624"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3099900"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s42235-018-0015-y"},{"key":"ref46","first-page":"2322","article-title":"DeepRebirth: Accelerating deep neural network execution on mobile devices","author":"li","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell (AAAI) 30th Innov Appl Artif Intell (IAAI) 8th AAAI Symp Educ Adv Artif Intell (EAAI)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00490"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3355713"},{"key":"ref47","first-page":"1","article-title":"26ms inference time for ResNet-50: Towards real-time execution of all DNNs on smartphone","author":"niu","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn (PMLR)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.09.106"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref24","article-title":"Multimodal fusion with deep neural networks for audio-video emotion recognition","author":"ortega","year":"2019","journal-title":"arXiv 1907 03196"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2003.10057"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2019.2960219"},{"key":"ref43","first-page":"908","article-title":"Multimodal(audio, facial and Gesture) based emotion recognition challenge","author":"wei","year":"2020","journal-title":"Proc 15th IEEE Int Conf Autom Face Gesture Recognit (FG)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191330"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09552845.pdf?arnumber=9552845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T01:13:32Z","timestamp":1725844412000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9552845\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3116530","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}