{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T23:35:59Z","timestamp":1776382559963,"version":"3.51.2"},"reference-count":12,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9052990","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"736-740","source":"Crossref","is-referenced-by-count":203,"title":["Clotho: an Audio Captioning Dataset"],"prefix":"10.1109","author":[{"given":"Konstantinos","family":"Drossos","sequence":"first","affiliation":[]},{"given":"Samuel","family":"Lipping","sequence":"additional","affiliation":[]},{"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref10","first-page":"145","article-title":"On the stratification of multi-label data","author":"sechidis","year":"2011","journal-title":"Machine Learning and Knowledge Discovery in Databases"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682377"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref5","article-title":"Microsoft COCO: common objects in context","volume":"abs 1405 312","author":"lin","year":"2014","journal-title":"CoRR"},{"key":"ref12","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd International Conference for Learning Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref7","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","author":"kim","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies Volume 1 (Long and Short Papers)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.33682\/sezz-vd31"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09052990.pdf?arnumber=9052990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:24:29Z","timestamp":1656375869000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9052990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9052990","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}