{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:21:42Z","timestamp":1740100902342,"version":"3.37.3"},"reference-count":26,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102200"],"award-info":[{"award-number":["2018AAA0102200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122018,61772116,61872064"],"award-info":[{"award-number":["62122018,61772116,61872064"]}],"id":[{"id":"10.13039\/501100001809","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\/icme52920.2022.9859943","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":3,"title":["Support-Set Based Multi-Modal Representation Enhancement for Video Captioning"],"prefix":"10.1109","author":[{"given":"Xiaoya","family":"Chen","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengpeng","family":"Zeng","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref12","article-title":"Multi-modal dependency tree for video captioning","author":"zhao","year":"0","journal-title":"NIPS"},{"key":"ref13","first-page":"2514","article-title":"Semantic grouping network for video captioning","volume":"35","author":"ryu","year":"0","journal-title":"AAAI"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/104"},{"key":"ref17","first-page":"2205","author":"zeng","year":"2021","journal-title":"Conceptual and syntactical cross-modal alignment with cross-level consistency for image-text matching"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01137"},{"key":"ref19","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref4","first-page":"13096","article-title":"Syntax-aware action targeting for video captioning","author":"qi","year":"0","journal-title":"CVPR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref5","article-title":"Support-set bottlenecks for video-text representation learning","author":"patrick","year":"0","journal-title":"ICLRE"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref7","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"kelvin","year":"0","journal-title":"ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00157"},{"key":"ref9","first-page":"8347","article-title":"Memory-attended re-current network for video captioning","author":"pei","year":"0","journal-title":"CVPR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref22","first-page":"5288","article-title":"Msr-vtt: A large video description dataset for bridging video and language","author":"jun","year":"0","journal-title":"CVPR"},{"key":"ref21","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"0","journal-title":"ACL"},{"key":"ref24","article-title":"The kinetics human action video dataset","volume":"abs 1705 6950","author":"kay","year":"2017","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2022,7,18]]},"location":"Taipei, Taiwan","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\/09859943.pdf?arnumber=9859943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:25:00Z","timestamp":1663619100000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859943","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}