{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T21:22:57Z","timestamp":1771017777447,"version":"3.50.1"},"reference-count":26,"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"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","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\/ijcnn64981.2025.11228877","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":["Multi-modal Knowledge Graph Generation with Semantics-enriched Prompts"],"prefix":"10.1109","author":[{"given":"Yajing","family":"Xu","sequence":"first","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaoyan","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Manchester,Department of Computer Science,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingchen","family":"Tu","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeff Z.","family":"Pan","sequence":"additional","affiliation":[{"name":"The University of Edinburgh,School of Informatics,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yushan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huajun","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103124"},{"issue":"1","key":"ref2","first-page":"2:1","article-title":"Large language models and knowledge graphs: Opportunities and challenges","volume-title":"TGDK","volume":"1","author":"Pan"},{"key":"ref3","article-title":"Unsupervised semantic correspondence using stable diffusion","author":"Hedlin","year":"2023","journal-title":"NeurIPS"},{"key":"ref4","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref5","article-title":"Draw me like my triples: Leveraging generative AI for wikidata image completion","volume-title":"Wikidata@ISWC, ser. CEUR Workshop Proceedings","volume":"3640","author":"Ahmad"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107173"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68204-4_8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.11"},{"key":"ref9","article-title":"Visualsem: a high-quality knowledge graph for vision and language","author":"Alberts","year":"2020","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","article-title":"Answering visual-relational queries in web-extracted knowledge graphs","volume-title":"AKBC","author":"O\u00f1oro-Rubio"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-21348-0_30"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612266"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-47243-5_2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.bdr.2020.100159"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614782"},{"key":"ref17","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"CoRR"},{"key":"ref18","article-title":"Prompt engineering for healthcare: Methodologies and applications","author":"Wang","year":"2023","journal-title":"CoRR"},{"key":"ref19","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","author":"Xu","year":"2023","journal-title":"NeurIPS"},{"key":"ref20","article-title":"Compositionbased multi-relational graph convolutional networks","volume-title":"ICLR","author":"Vashishth"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2629489"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3233\/SW-140134"},{"key":"ref23","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"NIPS","author":"Heusel"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","volume":"139","author":"Radford"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657800"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","location":"Rome, Italy","start":{"date-parts":[[2025,6,30]]},"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\/11228877.pdf?arnumber=11228877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T20:47:07Z","timestamp":1771015627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228877\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228877","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}