{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:20:06Z","timestamp":1777656006952,"version":"3.51.4"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10445969","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"8085-8089","source":"Crossref","is-referenced-by-count":1,"title":["Caption Unification for Multi-View Lifelogging Images Based on In-Context Learning with Heterogeneous Semantic Contents"],"prefix":"10.1109","author":[{"given":"Masaya","family":"Sato","sequence":"first","affiliation":[{"name":"Hokkaido University,School of Engineering,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keisuke","family":"Maeda","sequence":"additional","affiliation":[{"name":"Hokkaido University,Faculty of Information Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ren","family":"Togo","sequence":"additional","affiliation":[{"name":"Hokkaido University,Faculty of Information Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takahiro","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Hokkaido University,Faculty of Information Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miki","family":"Haseyama","sequence":"additional","affiliation":[{"name":"Hokkaido University,Faculty of Information Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3512729.3533012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35728-2_47"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3512729.3533006"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2018.05.008"},{"key":"ref5","author":"Zeng","year":"2022","journal-title":"Socratic models: Composing zero-shot multimodal reasoning with language"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_36"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref9","author":"Wang","year":"2022","journal-title":"GIT: A generative image-to-text transformer for vision and language"},{"key":"ref10","author":"Zhu","year":"2023","journal-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE59613.2023.10315286"},{"key":"ref12","author":"Yu","year":"2022","journal-title":"CoCa: Contrastive captioners are image-text foundation models"},{"key":"ref13","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Journal of Advances in Neural Information Processing Systems"},{"key":"ref14","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proceedings of International Conference on Machine Learning","author":"Kim"},{"key":"ref15","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Journal of Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1163\/2213-2139_emdt_sim_000972"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref18","author":"Hu","year":"2022","journal-title":"ExpansionNet v2: Block static expansion in fast end to end training for image captioning"},{"key":"ref19","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proceedings of International Conference on Machine Learning","author":"Wang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_9081"},{"key":"ref21","author":"Ye","year":"2023","journal-title":"mPLUG-Owl: Modularization empowers large language models with multimodality"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of International Conference on Machine Learning","author":"Radford"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10445969.pdf?arnumber=10445969","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:00:02Z","timestamp":1722574802000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445969\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445969","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}