{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T01:01:35Z","timestamp":1730250095426,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10688196","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["A Dataset with Multi-Modal Information and Multi-Granularity Descriptions for Video Captioning"],"prefix":"10.1109","author":[{"given":"Mingrui","family":"Xiao","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,China"}]},{"given":"Zijian","family":"Zeng","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,China"}]},{"given":"Yue","family":"Zheng","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,China"}]},{"given":"Shu","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,China"}]},{"given":"Yali","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,China"}]},{"given":"Shengjin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref3","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies","author":"Chen"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref5"},{"issue":"8","key":"ref6","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01816"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.02.062"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.12.137"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.916"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-202249"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"article-title":"The kinetics human action video dataset","year":"2017","author":"Kay","key":"ref17"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10688196.pdf?arnumber=10688196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:41:11Z","timestamp":1727764871000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10688196\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10688196","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}