{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T11:48:52Z","timestamp":1775216932995,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,13]],"date-time":"2022-12-13T00:00:00Z","timestamp":1670889600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,13]],"date-time":"2022-12-13T00:00:00Z","timestamp":1670889600000},"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":[[2022,12,13]]},"DOI":"10.1109\/vcip56404.2022.10008833","type":"proceedings-article","created":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T14:26:56Z","timestamp":1673879216000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["MAiVAR: Multimodal Audio-Image and Video Action Recognizer"],"prefix":"10.1109","author":[{"given":"Muhammad Bilal","family":"Shaikh","sequence":"first","affiliation":[{"name":"Edith Cowan University,Perth,WA,Australia,6027"}]},{"given":"Douglas","family":"Chai","sequence":"additional","affiliation":[{"name":"Edith Cowan University,Perth,WA,Australia,6027"}]},{"given":"Syed Mohammed Shamsul","family":"Islam","sequence":"additional","affiliation":[{"name":"Edith Cowan University,Perth,WA,Australia,6027"}]},{"given":"Naveed","family":"Akhtar","sequence":"additional","affiliation":[{"name":"The University of Western Australia,Perth,WA,Australia,6009"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref31","author":"kingma","year":"2015","journal-title":"ICLR (Poster)"},{"key":"ref30","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc of the NeurIPS"},{"key":"ref35","article-title":"A short note on the kinetics-700-2020 human action dataset","author":"smaira","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref34","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"ICML"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.215"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01282"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-0931-3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00077"},{"key":"ref28","article-title":"UCF101: A dataset of 10 1 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/s20041085"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00631"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"18","DOI":"10.25080\/Majora-7b98e3ed-003","article-title":"Librosa: Audio and music signal analysis in python","volume":"8","author":"mcfee","year":"2015","journal-title":"Proc of the Python in Science Conf"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref7","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Proc of the NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00806"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1207\/s15326969eco0501_1"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/s21124246"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3468872"},{"key":"ref22","first-page":"513","article-title":"AENet: Learning deep audio features for video analysis","volume":"20","author":"takahashi","year":"2017","journal-title":"IEEE TMM"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018401"},{"key":"ref24","year":"0","journal-title":"Welcome to mmaction2's documentation"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0265115"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"}],"event":{"name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","location":"Suzhou, China","start":{"date-parts":[[2022,12,13]]},"end":{"date-parts":[[2022,12,16]]}},"container-title":["2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10008391\/10008793\/10008833.pdf?arnumber=10008833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T15:50:10Z","timestamp":1705333810000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10008833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,13]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/vcip56404.2022.10008833","relation":{},"subject":[],"published":{"date-parts":[[2022,12,13]]}}}