{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:15:59Z","timestamp":1787012159446,"version":"build-2736575974"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889950","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["The Sound of Water: Inferring Physical Properties from Pouring Liquids"],"prefix":"10.1109","author":[{"given":"Piyush","family":"Bagad","sequence":"first","affiliation":[{"name":"University of Oxford"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Makarand","family":"Tapaswi","sequence":"additional","affiliation":[{"name":"IIIT Hyderabad"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[{"name":"University of Amsterdam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[{"name":"University of Oxford"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.26.1.313"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0956797618813319"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/joss.12052"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.4324\/9781315740218"},{"key":"ref5","volume-title":"The theory of sound.","author":"William Strutt Baron Rayleigh","year":"1896"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1119\/1.12960"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1119\/1.880017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.39"},{"key":"ref10","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"NeurIPS","author":"Baevski"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989307"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v26i1.13787"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103692"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206626"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759326"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.207"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1039\/d1dd00014d"},{"key":"ref19","article-title":"Detection and tracking of liquids with fully convolutional networks","author":"Schenck","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00029"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812000"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968118"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340859"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref25","article-title":"Contrastive audio-visual masked autoencoder","author":"Gong","year":"2022"},{"key":"ref26","article-title":"Active contrastive learning of audio-visual video representations","author":"Ma","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01479"},{"key":"ref28","article-title":"Mavil: Masked audio-video learners","volume-title":"NeurIPS","author":"Huang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref30","article-title":"Cooperative learning of audio and video models from self-supervised syn-chronization","volume-title":"NeurIPS","author":"Korbar"},{"key":"ref31","article-title":"Selfsupervised learning by crossmodal audiovideo clustering","volume-title":"NeurIPS","author":"Alwassel"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00791"},{"key":"ref33","article-title":"Soundnet: Learning sound representations from unlabeled video","volume-title":"NeurIPS","author":"Aytar"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.31.267"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1121\/1.1916116"},{"key":"ref37","article-title":"Ddsp: Differentiable digital signal processing","volume-title":"ICLR","author":"Engel"},{"key":"ref38","article-title":"Soundspaces 2.0: A simulation platform for visual-acoustic learning","volume-title":"NeurIPS","author":"Chen"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref42","article-title":"Pesto: Pitch estimation with self-supervised transposition-equivariant objective","volume-title":"ISMIR","author":"Riou"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889950"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1119\/1.13147"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889950.pdf?arnumber=10889950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:03Z","timestamp":1774416243000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889950\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889950","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}