{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:20:18Z","timestamp":1776889218795,"version":"3.51.2"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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\/501100017676","name":"Chunhui Project Foundation of the Education Department of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017676","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890521","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Non-Autoregressive Image Captioning with Multi-Label Classification and Self-Critical Sequence Training"],"prefix":"10.1109","author":[{"given":"Yuanqiu","family":"Liu","sequence":"first","affiliation":[{"name":"Dalian University of Technology,School of Software,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Yu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,School of Software,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,School of Software,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaotong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,School of Software,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Han","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,School of Software,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Liu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,School of Software,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16220"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"ref5","first-page":"9410","article-title":"Directed acyclic transformer for non-autoregressive machine translation","volume-title":"International Conference on Machine Learning (ICML)","author":"Huang"},{"key":"ref6","article-title":"Non-autoregressive machine translation with probabilistic context-free grammar","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Gui"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref8","article-title":"Non-autoregressive neural machine translation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Gu"},{"key":"ref9","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref12","article-title":"Masked non-autoregressive image captioning","author":"Gao","year":"2019","journal-title":"arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01190"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16219"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00350"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475179"},{"key":"ref17","article-title":"Fast image caption generation with position alignment","author":"Fei","year":"2019","journal-title":"arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/107"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"ref21","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021","journal-title":"Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref22","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095338"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25137"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1149"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413901"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref30","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890521.pdf?arnumber=10890521","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:55Z","timestamp":1774416115000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890521\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890521","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}