{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:13:55Z","timestamp":1775229235427,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413608","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6339-6343","source":"Crossref","is-referenced-by-count":36,"title":["Multimodal Emotion Recognition with Capsule Graph Convolutional Based Representation Fusion"],"prefix":"10.1109","author":[{"given":"Jiaxing","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhilei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yahui","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lili","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380163"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053012"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"3030","DOI":"10.1109\/TCSVT.2017.2719043","article-title":"Learning affective features with a hybrid deep model for audio–visual emotion recognition","volume":"28","author":"zhang","year":"2017","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052916"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053762"},{"key":"ref15","first-page":"3856","article-title":"Dynamic routing between capsules","author":"sabour","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"7610","article-title":"Videocapsulenet: A simplified network for action detection","author":"duarte","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2874623"},{"key":"ref18","first-page":"3110","article-title":"Investigating capsule networks with dynamic routing for text classification","author":"min","year":"2018","journal-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1007\/978-3-319-93417-4_38","article-title":"Modeling relational data with graph convolutional networks","author":"schlichtkrull","year":"2018","journal-title":"European Semantic Web Conference"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1520"},{"key":"ref27","first-page":"384","article-title":"Learning a parametric embedding by preserving local structure","volume":"5","author":"der maaten","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053192"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/informatics7010006"},{"key":"ref5","article-title":"A generalized zero-shot framework for emotion recognition from body gestures","author":"wu","year":"2020","journal-title":"arXiv preprint arXiv 2010 00170"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.06.050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851942"},{"key":"ref9","article-title":"Multi-modal emotion recognition on iemocap dataset using deep learning","author":"tripathi","year":"2018","journal-title":"arXiv preprint arXiv 1804 05809"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.105443"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60450-9_46"},{"key":"ref24","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref23","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36808-1_74"},{"key":"ref25","article-title":"The enterface’05 audio-visual emotion database","author":"martin","year":"2006","journal-title":"International Conference on Data Engineering Workshops"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413608.pdf?arnumber=9413608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:09Z","timestamp":1652197269000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413608","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}