{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T04:46:56Z","timestamp":1763959616101,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icra.2019.8794166","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"8070-8076","source":"Crossref","is-referenced-by-count":7,"title":["Sound-Indicated Visual Object Detection for Robotic Exploration"],"prefix":"10.1109","author":[{"given":"Feng","family":"Wang","sequence":"first","affiliation":[]},{"given":"Di","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Junfeng","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Fuchun","family":"Sun","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472179"},{"key":"ref11","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref18","first-page":"429","article-title":"Attention-based models for speech recognition","volume":"10","author":"chorowski","year":"2015","journal-title":"Computer Science"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907065"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759213"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353974"},{"key":"ref8","article-title":"Weakly supervised representation learning for unsynchronized audio-visual events","author":"parekh","year":"2018","journal-title":"ArXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989196"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354251"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1145\/2647868.2654936","article-title":"What’s making that sound?","author":"li","year":"2014","journal-title":"Proceedings of the 2nd ACM International Multimedia Conference"},{"key":"ref20","first-page":"1","article-title":"Cross-modal scene networks","volume":"pp","author":"aytar","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref22","article-title":"Objects that sound","author":"arandjelovi?","year":"2017","journal-title":"arXiv preprint arXiv 1712 06651"},{"key":"ref21","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"arXiv preprint arXiv 1804 02671"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759313"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2019,5,20]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8780387\/8793254\/08794166.pdf?arnumber=8794166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:19:30Z","timestamp":1657855170000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8794166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8794166","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}