{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:06:25Z","timestamp":1740099985464,"version":"3.37.3"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1109\/iscas51556.2021.9401232","type":"proceedings-article","created":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T21:33:36Z","timestamp":1619559216000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Learning Fine-Grained Semantics in Spoken Language Using Visual Grounding"],"prefix":"10.1109","author":[{"given":"Xinsheng","family":"Wang","sequence":"first","affiliation":[]},{"given":"Tian","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Jihua","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Odette","family":"Scharenborg","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Improved techniques for training gans","author":"salimans","year":"2016","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref30","first-page":"1060","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"2016","journal-title":"33rd International Conference on Machine Learning"},{"key":"ref35","article-title":"Visualizing data using t-sne","volume":"9","author":"maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref34","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"heusel","year":"2017","journal-title":"NeurIPS"},{"article-title":"The caltech-ucsd birds-200-2011 dataset","year":"2011","author":"wah","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1006"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3067"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2872106"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-502"},{"key":"ref8","first-page":"1","article-title":"Jointly discovering visual objects and spoken words from raw sensory input","author":"harwath","year":"2019","journal-title":"International Journal of Computer Vision"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_40"},{"key":"ref2","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"NeurIPS"},{"article-title":"Learning hierarchical discrete linguistic units from visually-grounded speech","year":"2019","author":"harwath","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"article-title":"Wasserstein gan","year":"2017","author":"arjovsky","key":"ref24"},{"key":"ref23","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"NeurIPS"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","start":{"date-parts":[[2021,5,22]]},"location":"Daegu, Korea","end":{"date-parts":[[2021,5,28]]}},"container-title":["2021 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9401028\/9401051\/09401232.pdf?arnumber=9401232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:44:05Z","timestamp":1652197445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9401232\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iscas51556.2021.9401232","relation":{},"subject":[],"published":{"date-parts":[[2021,5]]}}}