{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T13:25:01Z","timestamp":1762608301289,"version":"3.37.3"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413691","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"2245-2249","source":"Crossref","is-referenced-by-count":4,"title":["Cascade Attention Fusion for Fine-Grained Image Captioning Based on Multi-Layer LSTM"],"prefix":"10.1109","author":[{"given":"Shuang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiutiao","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingxian","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.3115\/v1\/W14-3348"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/CVPR.2015.7299087"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref14","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.3115\/v1\/D14-1162","article-title":"Glove: Global vectors for word representation","author":"pennington","year":"2014","journal-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/CVPR.2016.503"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.neucom.2018.08.069","article-title":"Image captioning with tripleattention and stack parallel lstm","volume":"319","author":"zhu","year":"2018","journal-title":"Neurocomputing"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1609\/aaai.v33i01.33018320"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1609\/aaai.v33i01.33018957"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref6","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"year":"2017","author":"faghri","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/CVPR.2015.7298932"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICCV.2015.303"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12266","article-title":"Stack-captioning: Coarse-to-fine learning for image captioning","author":"gu","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref9","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1016\/j.neucom.2018.12.026"},{"key":"ref21","article-title":"Context-aware visual policy network for fine-grained image captioning","author":"zha","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413691.pdf?arnumber=9413691","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:29:00Z","timestamp":1672129740000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413691\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413691","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}