{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T00:49:59Z","timestamp":1775868599648,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747631","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"976-980","source":"Crossref","is-referenced-by-count":245,"title":["Audioclip: Extending Clip to Image, Text and Audio"],"prefix":"10.1109","author":[{"given":"Andrey","family":"Guzhov","sequence":"first","affiliation":[{"name":"Deutsches Forschungszentrum für Künstliche Intelligenz GmbH,Kaiserslautern,Germany"}]},{"given":"Federico","family":"Raue","sequence":"additional","affiliation":[{"name":"Deutsches Forschungszentrum für Künstliche Intelligenz GmbH,Kaiserslautern,Germany"}]},{"given":"Jorn","family":"Hees","sequence":"additional","affiliation":[{"name":"Deutsches Forschungszentrum für Künstliche Intelligenz GmbH,Kaiserslautern,Germany"}]},{"given":"Andreas","family":"Dengel","sequence":"additional","affiliation":[{"name":"Deutsches Forschungszentrum für Künstliche Intelligenz GmbH,Kaiserslautern,Germany"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937283"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065234"},{"key":"ref12","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref15","first-page":"435","article-title":"Objects that sound","author":"arandjelovic","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref16","first-page":"3354","article-title":"Mdmmt: Multidomain multi-modal transformer for video retrieval","author":"dzabraev","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref17","article-title":"Multimodal self-supervised learning of general audio representations","author":"wang","year":"2021"},{"key":"ref18","article-title":"Learning from between-class examples for deep sound recognition","author":"tokozume","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref4","first-page":"5447","article-title":"A sequential self teaching approach for improving generalization in sound event recognition","author":"kumar","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref27","first-page":"979","article-title":"Differential data augmentation techniques for medical imaging classification tasks","volume":"2017","author":"hussain","year":"2017","journal-title":"AMIA Annual Symposium Proceedings"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref6","article-title":"Eranns: Efficient residual audio neural networks for audio pattern recognition","author":"verbitskiy","year":"2021"},{"key":"ref29","article-title":"A method of solving a convex programming problem with convergence rate o (1\/k^ 2) o (1\/k2)","volume":"27","author":"nesterov","year":"1983","journal-title":"Sov Math Dokl"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533654"},{"key":"ref8","article-title":"Self-supervised multimodal versatile networks","author":"alayrac","year":"2020"},{"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":"10.1145\/2647868.2655045"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"3351","DOI":"10.1609\/aaai.v35i4.16447","article-title":"Enhancing audio-visual association with self-supervised curriculum learning","volume":"35","author":"zhang","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref20","first-page":"1","article-title":"Environmental sound classification with convolutional neural networks","author":"piczak","year":"2015","journal-title":"Machine Learning for Signal Processing (MLSP) 2015 IEEE 25th International Workshop on"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2939495"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref24","article-title":"Rethinking cnn models for audio classification","author":"palanisamy","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413035"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"3107","DOI":"10.21437\/Interspeech.2017-831","article-title":"Unsupervised filterbank learning using convolutional restricted boltzmann machine for environmental sound classification","author":"sailor","year":"2017","journal-title":"InterSpeech"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747631.pdf?arnumber=9747631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T03:21:11Z","timestamp":1727061671000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747631\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747631","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}