{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T03:16:22Z","timestamp":1773890182631,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747769","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7937-7941","source":"Crossref","is-referenced-by-count":13,"title":["Improving Cross-Modal Understanding in Visual Dialog Via Contrastive Learning"],"prefix":"10.1109","author":[{"given":"Feilong","family":"Chen","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}]},{"given":"Xiuyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}]},{"given":"Shuang","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.93"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","volume":"2015","author":"kingma","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref10","first-page":"314","article-title":"Best of both worlds: Transferring knowledge from discriminative learning to a generative visual dialog model","author":"lu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00639"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_10"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1648"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6248"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/693"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_14"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00683"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00214"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6769"},{"key":"ref28","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"CoRR"},{"key":"ref4","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"ICML"},{"key":"ref27","article-title":"Domain adaptive training BERT for response selection","author":"whang","year":"2019","journal-title":"CoRR"},{"key":"ref3","first-page":"2953","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.20"},{"key":"ref29","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.38"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.728"},{"key":"ref2","article-title":"Tinybert: Distilling bert for natural language understanding","author":"jiao","year":"2019","journal-title":"arXiv preprint arXiv 1909 11324"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01087"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.269"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01007"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413826"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref23","first-page":"91","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NeurIPS"},{"key":"ref26","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref25","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"CoRR"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747769.pdf?arnumber=9747769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:15:02Z","timestamp":1661199302000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747769\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747769","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}