{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:41:21Z","timestamp":1730230881110,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094965","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Flowgrad: Using Motion for Visual Sound Source Localization"],"prefix":"10.1109","author":[{"given":"Rajsuryan","family":"Singh","sequence":"first","affiliation":[{"name":"Universitat Pompeu Fabra,MTG,Barcelona,Spain"}]},{"given":"Pablo","family":"Zinemanas","sequence":"additional","affiliation":[{"name":"Universitat Pompeu Fabra,MTG,Barcelona,Spain"}]},{"given":"Xavier","family":"Serra","sequence":"additional","affiliation":[{"name":"Universitat Pompeu Fabra,MTG,Barcelona,Spain"}]},{"given":"Juan Pablo","family":"Bello","sequence":"additional","affiliation":[{"name":"New York University,MARL,New York,USA"}]},{"given":"Magdalena","family":"Fuentes","sequence":"additional","affiliation":[{"name":"New York University,MARL,New York,USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747644"},{"key":"ref15","article-title":"You only learn one representation: Unified network for multiple tasks","author":"wang","year":"2021","journal-title":"arXiv preprint arXiv 2105 04206"},{"key":"ref14","first-page":"618","article-title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","author":"selvaraju","year":"2017","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-520"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref2","article-title":"Learning joint statistical models for audiovisual fusion and segregation","author":"fisher iii","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref1","article-title":"Audio vision: Using audio-visual synchrony to locate sounds","volume":"12","author":"hershey","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1007\/3-540-45103-X_50","article-title":"Two-frame motion estimation based on polynomial expansion","author":"farneb\u00e4ck","year":"2003","journal-title":"Scandinavian Conference on Image Analysis"},{"key":"ref16","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00065"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref9","article-title":"Do we need sound for sound source localization?","author":"oya","year":"2020","journal-title":"Proceedings of the Asian Conference on Computer Vision"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.274"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094965.pdf?arnumber=10094965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:11:12Z","timestamp":1700489472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094965\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094965","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}