{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T04:20:42Z","timestamp":1754108442076,"version":"3.37.3"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004410","name":"Scientific and Technological Research Council of Turkey (TUBITAK)-British Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004410","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,4]]},"DOI":"10.23919\/eusipco58844.2023.10290046","type":"proceedings-article","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T17:55:44Z","timestamp":1698861344000},"page":"745-749","source":"Crossref","is-referenced-by-count":2,"title":["Knowledge Distillation for Efficient Audio-Visual Video Captioning"],"prefix":"10.23919","author":[{"given":"\u00d6zkan","family":"\u00c7ayli","sequence":"first","affiliation":[{"name":"Electrical and Electronics Engineering, İzmir Katip Çelebi University,Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xubo","family":"Liu","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volkan","family":"Kili\u00e7","sequence":"additional","affiliation":[{"name":"Electrical and Electronics Engineering, İzmir Katip Çelebi University,Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747908"},{"key":"ref34","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096211"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3015714"},{"key":"ref31","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc 40th Ann Meeting of the Assoc for Computational Linguistics (ACL)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953072"},{"key":"ref33","first-page":"1","article-title":"Rouge: A package for automatic evaluation of sum-maries","author":"lin","year":"2004","journal-title":"Proceedings of the Association for Computational Linguistics (ACL) Workshop"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1179"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref2","first-page":"221","article-title":"Video captioning based on multilayer gated recurrent unit for smartphones","author":"fetiler","year":"2021","journal-title":"European Journal of Science and Technology"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.31590\/ejosat.1107035"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909761"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref19","article-title":"An encoder-decoder based audio captioning system with transfer and reinforcement learning","author":"mei","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746894"},{"key":"ref24","first-page":"1532","article-title":"Mobile application based automatic caption generation for visually impaired","author":"\u00e7ayli","year":"2020","journal-title":"International Conference on Intelligent and Fuzzy Systems"},{"key":"ref23","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref26","article-title":"Dropout training as adaptive regularization","volume":"26","author":"wager","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1126","DOI":"10.23919\/EUSIPCO55093.2022.9909624","article-title":"Auxiliary classifier based residual rnn for image captioning","author":"\u00e7ayli","year":"2022","journal-title":"2022 30th European Signal Processing Conference (EUSIPCO)"},{"key":"ref20","first-page":"250","article-title":"Label denoising with large ensembles of heterogeneous neural networks","author":"ostyakov","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops"},{"key":"ref22","first-page":"354","article-title":"Ef-ficient video classification using fewer frames","author":"bhardwaj","year":"0","journal-title":"Proceedings of the Conference on Computer Vision and Pattern Recognition (CVF) 2019"},{"key":"ref21","first-page":"1092","article-title":"Nextvlad: An efficient neural network to aggregate frame-level features for large-scale video classification","author":"lin","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.31590\/ejosat.1071835"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10714"},{"key":"ref7","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref9","article-title":"Low-complexity cnns for acoustic scene classification","author":"singh","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00259-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.31590\/ejosat.1013329"},{"key":"ref6","article-title":"Visually-aware audio captioning with adaptive audio-visual attention","author":"liu","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref5","article-title":"Automated audio captioning via fusion of low-and high-dimensional features","author":"sun","year":"2022","journal-title":"ArXiv Preprint"}],"event":{"name":"2023 31st European Signal Processing Conference (EUSIPCO)","start":{"date-parts":[[2023,9,4]]},"location":"Helsinki, Finland","end":{"date-parts":[[2023,9,8]]}},"container-title":["2023 31st European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10289698\/10289713\/10290046.pdf?arnumber=10290046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:20:50Z","timestamp":1701112850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10290046\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,4]]},"references-count":34,"URL":"https:\/\/doi.org\/10.23919\/eusipco58844.2023.10290046","relation":{},"subject":[],"published":{"date-parts":[[2023,9,4]]}}}