{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T05:05:40Z","timestamp":1737522340205,"version":"3.33.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:00:00Z","timestamp":1728172800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:00:00Z","timestamp":1728172800000},"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":[[2024,10,6]]},"DOI":"10.1109\/smc54092.2024.10831699","type":"proceedings-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:20Z","timestamp":1737398360000},"page":"587-592","source":"Crossref","is-referenced-by-count":0,"title":["ROP: Exploring Image Captioning with Retrieval-Augmented and Object Detection of Prompt"],"prefix":"10.1109","author":[{"given":"Meng","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, South China Normal University, Nanhai,Faculty of Engineering,Foshan,Guangdong,China,528225"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, South China Normal University, Nanhai,Faculty of Engineering,Foshan,Guangdong,China,528225"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shouqiang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, South China Normal University, Nanhai,Faculty of Engineering,Foshan,Guangdong,China,528225"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Simvlm: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref2","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref3","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref4","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref5","article-title":"Clipcap: Clip prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv preprint"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096424"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3549555.3549585"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.793"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-022-00571-w"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00512"},{"key":"ref17","article-title":"detrex: Benchmarking detection transformers","author":"Ren","year":"2023","journal-title":"arXiv preprint"},{"issue":"8","key":"ref18","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref19","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref21","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics","author":"Papineni","year":"2002"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"}],"event":{"name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2024,10,6]]},"location":"Kuching, Malaysia","end":{"date-parts":[[2024,10,10]]}},"container-title":["2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830919\/10830920\/10831699.pdf?arnumber=10831699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T06:41:57Z","timestamp":1737441717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10831699\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/smc54092.2024.10831699","relation":{},"subject":[],"published":{"date-parts":[[2024,10,6]]}}}