{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:28:21Z","timestamp":1763191701926,"version":"3.45.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227734","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Similarity: Aligning Retrieval with Generation for Enhanced Image Captioning"],"prefix":"10.1109","author":[{"given":"Gengqi","family":"Yang","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}]},{"given":"Dayan","family":"Wu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}]},{"given":"Jinyang","family":"An","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}]},{"given":"Shupei","family":"Xiao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}]},{"given":"Zheng","family":"Lin","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148210"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01745"},{"article-title":"Simvlm: Simple visual language model pretraining with weak supervision","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Wang","key":"ref4"},{"key":"ref5","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Li"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3663667"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.266"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01303"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.503"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"article-title":"Microsoft coco captions: Data collection and evaluation server","year":"2015","author":"Chen","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Clipcap: Clip prefix for image captioning","year":"2021","author":"Mokady","key":"ref18"},{"article-title":"I-tuning: Tuning language models with image for caption generation","year":"2022","author":"Luo","key":"ref19"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Dosovitskiy","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01368"},{"issue":"251","key":"ref23","first-page":"1","article-title":"Atlas: Few-shot learning with retrieval augmented language models","volume":"24","author":"Izacard","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00605"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.463"},{"article-title":"Ra-dit: Retrieval-augmented dual instruction tuning","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Lin","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.203"},{"issue":"8","key":"ref28","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"article-title":"Opt: Open pre-trained transformer language models","year":"2022","author":"Zhang","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00512"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00291"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref38","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Ordonez"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227734.pdf?arnumber=11227734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:25:19Z","timestamp":1763191519000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227734\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227734","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}