{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:49:28Z","timestamp":1730231368401,"version":"3.28.0"},"reference-count":18,"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\/icasspw62465.2024.10626141","type":"proceedings-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:19:18Z","timestamp":1723742358000},"page":"545-549","source":"Crossref","is-referenced-by-count":0,"title":["Positive and Negative Sampling Strategies for Self-Supervised Learning on Audio-Video Data"],"prefix":"10.1109","author":[{"given":"Shanshan","family":"Wang","sequence":"first","affiliation":[{"name":"Tampere University,Signal Processing Research Centre,Tampere,Finland"}]},{"given":"Soumya","family":"Tripathy","sequence":"additional","affiliation":[{"name":"Tampere University,Signal Processing Research Centre,Tampere,Finland"}]},{"given":"Toni","family":"Heittola","sequence":"additional","affiliation":[{"name":"Tampere University,Signal Processing Research Centre,Tampere,Finland"}]},{"given":"Annamaria","family":"Mesaros","sequence":"additional","affiliation":[{"name":"Tampere University,Signal Processing Research Centre,Tampere,Finland"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICASSP39728.2021.9415009"},{"key":"ref3","article-title":"Learning representations from audio-visual spatial alignment","volume":"33","author":"Morgado","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"year":"2018","author":"van den Oord","article-title":"Representation learning with contrastive predictive coding","key":"ref4"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/JSTSP.2022.3180592"},{"key":"ref6","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","volume":"31","author":"Korbar","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1007\/978-3-030-01231-1_39"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICASSP49357.2023.10094706"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP49357.2023.10095319"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1016\/j.sigpro.2021.108310"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICASSP39728.2021.9415085"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/ICASSP.2019.8683158"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICASSP.2017.7952261"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref16","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems 32"},{"year":"2020","author":"Tan","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","key":"ref17"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR.2009.5206848"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10625769\/10625780\/10626141.pdf?arnumber=10626141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T05:50:56Z","timestamp":1723787456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10626141\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10626141","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}