{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:24:02Z","timestamp":1777890242558,"version":"3.51.4"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01350","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14549-14558","source":"Crossref","is-referenced-by-count":0,"title":["Clink! Chop! Thud! - Learning Object Sounds From Real-World Interactions"],"prefix":"10.1109","author":[{"given":"Mengyu","family":"Yang","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiming","family":"Chen","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haozheng","family":"Pei","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddhant","family":"Agarwal","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arun Balajee","family":"Vasudevan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Hays","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref4","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"Aytar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref5","author":"Bertasius","year":"2021","journal-title":"Is space-time attention all you need for video understanding?"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02573"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_16"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991965"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2098"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"key":"ref13","article-title":"Objectfolder: A dataset of objects with implicit visual, auditory, and tactile representations","author":"Gao","year":"2021","journal-title":"CoRL"},{"key":"ref14","article-title":"Ob-jectfolder 2.0: A multisensory object dataset for sim2real transfer","author":"Gao","year":"2022","journal-title":"CVPR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952261"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/j.0956-7976.2005.00796.x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01246"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02149"},{"key":"ref22","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":"ref23","article-title":"Online","volume-title":"Labelbox. Labelbox","year":"2025"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00320"},{"key":"ref26","author":"Locatello","year":"2020","journal-title":"Objectcentric learning with slot attention"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3191"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2720"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_13"},{"key":"ref30","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref31","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00715"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1126\/science.1192788"},{"key":"ref38","author":"van den Oord","year":"2019","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_37"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01421"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_14"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611514"},{"key":"ref44","article-title":"Metatransformer: A unified framework for multimodal learning","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00233"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00233"},{"key":"ref47","author":"Zhu","year":"2023","journal-title":"Languagebind: Extending video-language pretraining to n modality by language-based semantic alignment"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446106.pdf?arnumber=11446106","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:33:18Z","timestamp":1777613598000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446106\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01350","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}