{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:52:29Z","timestamp":1774367549538,"version":"3.50.1"},"reference-count":47,"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\/icassp48485.2024.10448235","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"13021-13025","source":"Crossref","is-referenced-by-count":15,"title":["Enhancing Semantic Communication with Deep Generative Models: An Overview"],"prefix":"10.1109","author":[{"given":"Eleonora","family":"Grassucci","sequence":"first","affiliation":[{"name":"Sapienza University of Rome,Rome,Italy"}]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}]},{"given":"Ping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Danilo","family":"Comminiello","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome,Rome,Italy"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Semantic communications: Principles and challenges","author":"Qin","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.005.2200829"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.017.2100705"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685667"},{"key":"ref5","article-title":"Generative semantic communication: Diffusion models beyond bit recovery","author":"Grassucci","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448094"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446594"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447279"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221968"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447612"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094680"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3240969"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446638"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10437861"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/secon58729.2023.10287438"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.003.2200616"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref18","article-title":"SAN: Inducing metrizability of GAN with discriminative normalized linear layer","author":"Takida","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096372"},{"key":"ref20","article-title":"Auto-encoding variational Bayes","volume-title":"Int. Conf. on Learning Repr. (ICLR)","author":"Kingma"},{"key":"ref21","article-title":"SQ-VAE: Variational Bayes on discrete representation with self-annealed stochastic quantization","volume-title":"Int. Conf. on Machine Learning (ICML)","author":"Takida"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10437659"},{"key":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref24","article-title":"FP-Diffusion: Improving score-based diffusion models by enforcing the underlying score fokker-planck equation","volume-title":"Int. Conf. on Machine Learning (ICML)","author":"Lai"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps58843.2023.10464910"},{"key":"ref26","first-page":"261","article-title":"Recent contributions to the mathematical theory of communication","author":"Weaver","year":"1953","journal-title":"ETC: A Review of General Semantics"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.107930"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095749"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref33","article-title":"Generative models for 3d point clouds","author":"Kong","year":"2023"},{"key":"ref34","article-title":"A 3D generative model for structure-based drug design","author":"Luo","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref35","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","volume-title":"Int. Conf. on Learning Repr. (ICLR)","author":"Hong"},{"key":"ref36","article-title":"Make-A-Video: Text-to-video generation without text-video data","author":"Singer","year":"2022"},{"key":"ref37","article-title":"AC-VAE: Learning semantic representation with VAE for adaptive clustering","author":"Xie","year":"2021","journal-title":"Openreview id:o7YTArVXdEW"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00923"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3262140"},{"key":"ref40","article-title":"Diffusion models already have a semantic latent space","volume-title":"Int. Conf. on Learning Repr. (ICLR)","author":"Kwon"},{"key":"ref41","article-title":"Label-efficient semantic segmentation with diffusion models","volume-title":"Int. Conf. on Learning Repr. (ICLR)","author":"Baranchuk"},{"key":"ref42","article-title":"Semantic image synthesis via diffusion models","author":"Wang","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10315-0"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2023.3317629"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-91390-8_4"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3226772"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s12243-023-00980-9"}],"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\/10448235.pdf?arnumber=10448235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:42:44Z","timestamp":1722660164000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448235","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}