{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:09Z","timestamp":1777865349062,"version":"3.51.4"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01780","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19153-19162","source":"Crossref","is-referenced-by-count":0,"title":["VSC: Visual Search Compositional Text-to-Image Diffusion Model"],"prefix":"10.1109","author":[{"given":"Do Huu","family":"Dat","sequence":"first","affiliation":[{"name":"VinUniversity"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nam","family":"Hyeon-Woo","sequence":"additional","affiliation":[{"name":"POSTECH,Department of Electrical Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Po-Yuan","family":"Mao","sequence":"additional","affiliation":[{"name":"Academia Sinica"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tae-Hyun","family":"Oh","sequence":"additional","affiliation":[{"name":"POSTECH,Department of Electrical Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00217"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3604"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21236\/ad0616323"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_25"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00261"},{"key":"ref9","volume-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","author":"Feng","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0802"},{"key":"ref11","author":"Gal","year":"2022","journal-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.870"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref16","author":"Ilharco","year":"2021","journal-title":"Openclip"},{"key":"ref17","author":"Kang","year":"2024","journal-title":"Self-moe: Towards compositional large language models with self-specialized experts"},{"key":"ref18","author":"Kirstain","year":"2023","journal-title":"X&fuse: Fusing visual information in text-to-image generation"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-eacl.101"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00860"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref25","author":"Nie","year":"2024","journal-title":"Compositional text-to-image generation with dense blob representations"},{"key":"ref26","article-title":"Compositional abilities emerge multiplicatively: Exploring diffusion models on a synthetic task","volume":"36","author":"Okawa","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref28","article-title":"Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment","volume":"36","author":"Rassin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00416"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.524"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00914"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(80)90005-5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28364"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref39","author":"Zarei","year":"2024","journal-title":"Understanding and mitigating compositional issues in text-to-image generative models"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446224.pdf?arnumber=11446224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:31Z","timestamp":1777529971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446224\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01780","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}