{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T17:29:28Z","timestamp":1782408568294,"version":"3.54.5"},"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":1,"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soumya","family":"Tripathy","sequence":"additional","affiliation":[{"name":"Tampere University,Signal Processing Research Centre,Tampere,Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toni","family":"Heittola","sequence":"additional","affiliation":[{"name":"Tampere University,Signal Processing Research Centre,Tampere,Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annamaria","family":"Mesaros","sequence":"additional","affiliation":[{"name":"Tampere University,Signal Processing Research Centre,Tampere,Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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"},{"key":"ref2","doi-asserted-by":"publisher","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"},{"key":"ref4","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","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"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094706"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095319"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2021.108310"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415085"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683158"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref15","doi-asserted-by":"publisher","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"},{"key":"ref17","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"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]]}}}