{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:18:57Z","timestamp":1772644737679,"version":"3.50.1"},"reference-count":27,"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"}],"funder":[{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446171","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"3650-3654","source":"Crossref","is-referenced-by-count":3,"title":["Extending Implicit Neural Representations for Text-to-Image Generation"],"prefix":"10.1109","author":[{"given":"Guanming","family":"Liu","sequence":"first","affiliation":[{"name":"Tongji University,Department of Computer Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihua","family":"Wei","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Computer Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Computer Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Computer Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aiquan","family":"Yuan","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanbao","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biao","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guodong","family":"Cao","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref2","author":"Sauer","year":"2023","journal-title":"Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","author":"Chen","year":"2018","journal-title":"On self modulation for generative adversarial networks"},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01061"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_10"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01124"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02146"},{"key":"ref10","article-title":"Hypercgan: Text-to-image synthesis with hypernet-modulated conditional generative adversarial networks","author":"Haydarov","year":"2021"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref13","first-page":"4487","article-title":"Generative adversarial transformers","volume-title":"International conference on machine learning","author":"Hudson"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00878"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01102"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International conference on learning representations","author":"Dosovitskiy"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611978"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"ref22","author":"Patro","year":"2023","journal-title":"Spectformer: Frequency and attention is what you need in a vision transformer"},{"key":"ref23","article-title":"The caltech-ucsd birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref25","article-title":"Gans trained by a two timescale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Benchmark for compositional text-to-image synthesis","volume-title":"Thirty-fifth conference on neural information processing systems datasets and benchmarks track (round 1)","author":"Park"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"}],"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\/10446171.pdf?arnumber=10446171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:05:37Z","timestamp":1722575137000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446171\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446171","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}