{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T03:41:56Z","timestamp":1771645316640,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010580","name":"Department of Science and Technology, Hubei Provincial People's Government","doi-asserted-by":"publisher","award":["2021CFB513,2021CFB281"],"award-info":[{"award-number":["2021CFB513,2021CFB281"]}],"id":[{"id":"10.13039\/501100010580","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/icme52920.2022.9859882","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:45:18Z","timestamp":1661543118000},"page":"1-6","source":"Crossref","is-referenced-by-count":4,"title":["Dual-Scale Alignment-Based Transformer on Linguistic Skeleton Tags for Non-Autoregressive Video Captioning"],"prefix":"10.1109","author":[{"given":"Xian","family":"Zhong","sequence":"first","affiliation":[{"name":"Wuhan University of Technology"}]},{"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology"}]},{"given":"Shuqin","family":"Chen","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology"}]},{"given":"Zhixin","family":"Sun","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology"}]},{"given":"Huantao","family":"Zheng","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology"}]},{"given":"Kui","family":"Jiang","sequence":"additional","affiliation":[{"name":"Wuhan University"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Partially non-autoregressive image captioning","author":"fei","year":"0","journal-title":"AAAI"},{"key":"ref11","article-title":"Non-autoregressive coarse-to-fine video captioning","author":"yang","year":"0","journal-title":"AAAI"},{"key":"ref12","article-title":"CLIP4Clip: An empirical study of CLIP for end to end video clip retrieval","volume":"abs 2104 8860","author":"luo","year":"2021","journal-title":"ArXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428380"},{"key":"ref14","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"NAACL-HLT"},{"key":"ref15","article-title":"YouTube2Text: Recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition","author":"sergio","year":"0","journal-title":"ICCV"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref18","article-title":"METEOR: an automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"0","journal-title":"IEEvaluation ACL"},{"key":"ref19","article-title":"CIDEr: Consensus-based image description evaluation","author":"ramakrishna","year":"0","journal-title":"CVPR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-020-10352-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2960586"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240667"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416291"},{"key":"ref8","article-title":"Guiding non-autoregressive neural machine translation decoding with reordering information","author":"ran","year":"0","journal-title":"AAAI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141886"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00647"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6413"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350932"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2894139"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","location":"Taipei, Taiwan","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859562\/9858923\/09859882.pdf?arnumber=9859882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:24:15Z","timestamp":1663619055000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859882\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859882","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}