{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:18:53Z","timestamp":1784215133577,"version":"3.55.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","funder":[{"DOI":"10.13039\/501100012389","name":"NICT","doi-asserted-by":"publisher","award":["JPJ012368C01101"],"award-info":[{"award-number":["JPJ012368C01101"]}],"id":[{"id":"10.13039\/501100012389","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Commun."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.23919\/transcom.2024ebp3056","type":"journal-article","created":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T17:20:55Z","timestamp":1727976055000},"page":"260-273","source":"Crossref","is-referenced-by-count":10,"title":["Image Generative Semantic Communication with Multi-Modal Similarity Estimation for Resource-Limited Networks"],"prefix":"10.23919","volume":"E108-B","author":[{"given":"Eri","family":"Hosonuma","sequence":"first","affiliation":[{"name":"Institute of Industrial Science, The University of Tokyo,Tokyo,Japan,153-8505"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taku","family":"Yamazaki","sequence":"additional","affiliation":[{"name":"College of Systems Engineering and Science, Shibaura Institute of Technology,Saitama-shi,Japan,337-8570"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takumi","family":"Miyoshi","sequence":"additional","affiliation":[{"name":"College of Systems Engineering and Science, Shibaura Institute of Technology,Saitama-shi,Japan,337-8570"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akihito","family":"Taya","sequence":"additional","affiliation":[{"name":"Institute of Industrial Science, The University of Tokyo,Tokyo,Japan,153-8505"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuuki","family":"Nishiyama","sequence":"additional","affiliation":[{"name":"Center for Spatial Information Science at The University of Tokyo,Kashiwa-shi,Japan,277-8568"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaoru","family":"Sezaki","sequence":"additional","affiliation":[{"name":"Center for Spatial Information Science at The University of Tokyo,Kashiwa-shi,Japan,277-8568"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3150093"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2017.2713640"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2017.2652320"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2021.3112386"},{"key":"ref5","volume-title":"Information and Communications in Japan 2022","year":"2024"},{"key":"ref6","volume-title":"Ericsson Mobility Report June 2023","year":"2024"},{"key":"ref7","volume-title":"Cisco Annual Internet Report (2018\u20132023) White Paper","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2020.3028247"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/s18124457"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.02.094"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103089"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/79.952804"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106361"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2910119"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683463"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2919300"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.101.2100269"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3223408"},{"key":"ref19","first-page":"1","article-title":"Semantic communications: Principles and challenges","author":"Qin","year":"2021","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref21","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"38th Int. Conf. Machine Learning (ICML 2021)"},{"key":"ref22","first-page":"1","article-title":"Hierar-chical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"1","article-title":"StreamDiffusion: A pipeline-level solution for real-time interactive generation","author":"Kodaira","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446638"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC51664.2024.10454792"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref27","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pretraining for unified vision-language understanding and generation","volume-title":"39th Int. Conf. Machine Learning (ICML 2022)","author":"Li"},{"key":"ref28","first-page":"1","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2936841"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7965927"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00339"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/PCS.2018.8456308"},{"key":"ref33","first-page":"1","article-title":"Lossy image compression with compressive autoencoders","author":"Theis","year":"2017","journal-title":"arXiv preprint"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"38th Int. Conf. Machine Learning (ICML 2021)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref36","first-page":"1","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref37","first-page":"1","article-title":"BERTScore: Evaluating text generation with bert","author":"Zhang","year":"2020","journal-title":"2020 Int. Conf. Learning Representations (ICLR 2020)"},{"key":"ref38","first-page":"1","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"PhotoAC","year":"2024"},{"key":"ref40","first-page":"1","article-title":"Fast-SCNN: Fast semantic segmentation network","volume-title":"30th British Machine Vision Conference (BMVC 2019)","author":"Poudel"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01095"}],"container-title":["IEICE Transactions on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10400553\/10919252\/10705025.pdf?arnumber=10705025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T17:33:22Z","timestamp":1741714402000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10705025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":41,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.23919\/transcom.2024ebp3056","relation":{},"ISSN":["1745-1345","0916-8516"],"issn-type":[{"value":"1745-1345","type":"electronic"},{"value":"0916-8516","type":"print"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}