{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T22:00:00Z","timestamp":1769724000413,"version":"3.49.0"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650602","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["CLIP-Driven Low-Cost Image Captioning"],"prefix":"10.1109","author":[{"given":"Yiyu","family":"Wang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,101408"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jungang","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,101408"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingfei","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,101408"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref4","first-page":"65","article-title":"METEOR: an automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proceedings of the Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization@ACL","author":"Banerjee"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00512"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Dosovitskiy"},{"key":"ref10","volume":"abs\/1912.06365","author":"Fei","year":"2019","journal-title":"Fast image caption generation with position alignment"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413901"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16219"},{"key":"ref13","volume":"abs\/1906.00717","author":"Gao","year":"2019","journal-title":"Masked non-autoregressive image captioning"},{"key":"ref14","article-title":"Non-autoregressive neural machine translation","volume-title":"Proceedings of International Conference on Learning Representations, (ICLR)","author":"Gu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/107"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","first-page":"11135","article-title":"Image captioning: Transforming objects into words","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","author":"Herdade"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref23","article-title":"Decap: Decoding clip latents for zero-shot captioning via text-only training","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Li"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3573942.3574061"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1336"},{"key":"ref26","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proceedings of the ACL-04 workshop on Text Summarization Branches Out","author":"Lin"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","volume":"abs\/2101.10804","author":"Liu","year":"2021","journal-title":"CPTR: full transformer network for image captioning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191971"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref32","volume":"abs\/2111.09734","author":"Mokady","year":"2021","journal-title":"Clipcap: CLIP prefix for image captioning"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.299"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref36","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proceedings of the Advances in neural information processing systems (NeurIPS)","author":"Paszke"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00856"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref39","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref40","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.266"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref44","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Simonyan"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25359"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126287"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475179"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095338"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191558"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00350"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650602.pdf?arnumber=10650602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:33:52Z","timestamp":1725942832000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650602\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650602","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}