{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T18:12:06Z","timestamp":1768587126670,"version":"3.49.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095073","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Heterogeneous Graph Learning for Acoustic Event Classification"],"prefix":"10.1109","author":[{"given":"Amir","family":"Shirian","sequence":"first","affiliation":[{"name":"University of Warwick,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mona","family":"Ahmadian","sequence":"additional","affiliation":[{"name":"University of Surrey,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krishna","family":"Somandepalli","sequence":"additional","affiliation":[{"name":"Google Research,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tanaya","family":"Guha","sequence":"additional","affiliation":[{"name":"University of Glasgow,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"3070","article-title":"Multimodal graph networks for compositional generalization in visual question answering","volume":"33","author":"saqur","year":"2020","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16345"},{"key":"ref34","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10670"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.28"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3190083"},{"key":"ref30","author":"akbari","year":"2021","journal-title":"Vatt Transformers for multimodal self-supervised learning from raw video audio and text"},{"key":"ref11","article-title":"Dualgnn: Dual graph neural network for multimedia recommendation","author":"wang","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548365"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2017.12.034"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref17","article-title":"Spatial-temporal graphs for cross-modal text2video retrieval","author":"song","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref16","first-page":"1793","article-title":"Wasserstein coupled graph learning for crossmodal retrieval","author":"wang","year":"2021","journal-title":"ICCV"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380297"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413876"},{"key":"ref24","article-title":"Graph attention networks","author":"veli?kovi?","year":"2018","journal-title":"ICLRE"},{"key":"ref23","article-title":"Inductive representation learning on large graphs","volume":"30","author":"hamilton","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref25","article-title":"Dynamic emotion modeling with learnable graphs and graph inception network","author":"shirian","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"ref22","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"ICLRE"},{"key":"ref21","first-page":"1150","article-title":"Are we really making much progress? revisiting, benchmarking and refining heterogeneous graph neural networks","author":"lv","year":"2021","journal-title":"ACM SIGKDD"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref27","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952190"},{"key":"ref8","author":"shukla","year":"2020","journal-title":"Learning speech representations from raw audio by joint audiovisual self-supervision"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00694"},{"key":"ref9","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","author":"zbontar","year":"2021","journal-title":"ICML"},{"key":"ref4","article-title":"Active contrastive learning of audio-visual video representations","author":"ma","year":"2021","journal-title":"ICLRE"},{"key":"ref3","first-page":"25","article-title":"Self-supervised multimodal versatile networks","volume":"33","author":"alayrac","year":"2020","journal-title":"NeurIPS"},{"key":"ref6","article-title":"Contrastive learning of global and local video representations","volume":"34","author":"ma","year":"2021","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095073.pdf?arnumber=10095073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T13:57:02Z","timestamp":1700488622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095073\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095073","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}