{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:51:03Z","timestamp":1753602663921,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","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":[],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1109\/tsp49548.2020.9163474","type":"proceedings-article","created":{"date-parts":[[2020,8,11]],"date-time":"2020-08-11T18:52:41Z","timestamp":1597171961000},"page":"305-308","source":"Crossref","is-referenced-by-count":11,"title":["Temporal aggregation of audio-visual modalities for emotion recognition"],"prefix":"10.1109","author":[{"given":"Andreea","family":"Birhala","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Catalin Nicolae","family":"Ristea","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anamaria","family":"Radoi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liviu Cristian","family":"Dutu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/34.908962"},{"key":"ref11","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997627"},{"key":"ref14","article-title":"A personalized affective memory neural model for improving emotion recognition","volume":"abs 1904 12632","author":"barros","year":"2019","journal-title":"ArXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2019.2960219"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref18","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"arXiv preprint arXiv 1502 03167"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref4","first-page":"1","article-title":"Emotion recognition system from speech and visual information based on convolutional neural networks","author":"ristea","year":"2019","journal-title":"2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2008.918624"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"251","DOI":"10.18653\/v1\/K18-1025","article-title":"Multi-modal sequence fusion via recursive attention for emotion recognition","author":"beard","year":"2018","journal-title":"Proceedings of the Conference on Computational Natural Language Learning"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/2512530.2512533","article-title":"Avec 2013: The continuous audio\/visual emotion and depression recognition challenge","author":"valstar","year":"2013","journal-title":"Proceedings of the 3rd ACM International Workshop on Audio\/visual Emotion Challenge"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925444"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2019.8906635"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s42235-018-0015-y"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"}],"event":{"name":"2020 43rd International Conference on Telecommunications and Signal Processing (TSP)","start":{"date-parts":[[2020,7,7]]},"location":"Milan, Italy","end":{"date-parts":[[2020,7,9]]}},"container-title":["2020 43rd International Conference on Telecommunications and Signal Processing (TSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9158468\/9163396\/09163474.pdf?arnumber=9163474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T11:18:45Z","timestamp":1656587925000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9163474\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/tsp49548.2020.9163474","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}