{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:35:19Z","timestamp":1730230519192,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446582","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"8040-8044","source":"Crossref","is-referenced-by-count":0,"title":["C-CLAPA: Improving Text-Audio Cross Domain Retrieval with Captioning and Augmentations"],"prefix":"10.1109","author":[{"given":"Amit","family":"Sofer","sequence":"first","affiliation":[{"name":"OriginAI,Ramat-Gan,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shlomo E.","family":"Chazan","sequence":"additional","affiliation":[{"name":"OriginAI,Ramat-Gan,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"article-title":"Coca: Contrastive captioners are image-text foundation models","year":"2022","author":"Yu","key":"ref2"},{"key":"ref3","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified visionlanguage understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref4","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","author":"Jia"},{"key":"ref5","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2227"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11115"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149712"},{"article-title":"Clap: Learning audio concepts from natural language supervision","year":"2022","author":"Elizalde","key":"ref11"},{"article-title":"Audio retrieval with wavtext5k and clap training","year":"2022","author":"Deshmukh","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"article-title":"Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation","year":"2022","author":"Wu","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"issue":"1","key":"ref16","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"article-title":"mixup: Beyond empirical risk minimization","year":"2017","author":"Zhang","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"article-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"Liu","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20160"},{"article-title":"Stanford alpaca: An instruction-following llama model","year":"2023","author":"Taori","key":"ref22"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref23"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446582.pdf?arnumber=10446582","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:21:24Z","timestamp":1722576084000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446582\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446582","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}