{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T06:10:17Z","timestamp":1743833417219},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"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":[[2021,7,5]]},"DOI":"10.1109\/icme51207.2021.9428422","type":"proceedings-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T17:14:21Z","timestamp":1623258861000},"page":"1-6","source":"Crossref","is-referenced-by-count":4,"title":["Depth-Guided AdaIN and Shift Attention Network for Vision-And-Language Navigation"],"prefix":"10.1109","author":[{"given":"Qiang","family":"Sun","sequence":"first","affiliation":[{"name":"Academy for Engineering & Technology, Fudan University,China"}]},{"given":"Yifeng","family":"Zhuang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University,China"}]},{"given":"Zhengqing","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University,China"}]},{"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Data Science, Fudan University, MOE Frontiers Center for Brain Science, and Shanghai Key Lab of Intelligent Information Processing,China"}]},{"given":"Xiangyang","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University,China"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"arXiv preprint arXiv 1607 08022"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref12","article-title":"Neural turing machines","author":"graves","year":"2014","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref14","article-title":"Learnable gated temporal shift module for deep video inpainting","author":"chang","year":"2019","journal-title":"BMVC"},{"key":"ref15","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref16","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"NIPS"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/CVPR42600.2020.01315"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR.2019.00690"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/ICCV.2019.00750"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref3","article-title":"Speaker-follower models for vision-and-language navigation","author":"fried","year":"2018","journal-title":"NIPS"},{"key":"ref6","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","author":"ma","year":"2019","journal-title":"ICLRE"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/CVPR.2019.00679"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1007\/978-3-030-01270-0_3"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR42600.2020.01003"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/3DV.2017.00081"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/CVPR.2018.00387"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/CVPR.2019.00689"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref21","article-title":"On evaluation of embodied navigation agents","author":"anderson","year":"2018","journal-title":"arXiv preprint arXiv 1807 06757"}],"event":{"name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2021,7,5]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,9]]}},"container-title":["2021 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9428049\/9428068\/09428422.pdf?arnumber=9428422","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T17:28:00Z","timestamp":1656350880000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9428422\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icme51207.2021.9428422","relation":{},"subject":[],"published":{"date-parts":[[2021,7,5]]}}}