{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T22:06:55Z","timestamp":1769033215560,"version":"3.49.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/cbmi66578.2025.11339318","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:38:56Z","timestamp":1768941536000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["GenFlow: Interactive Modular System for Image Generation"],"prefix":"10.1109","author":[{"given":"Duc-Hung","family":"Nguyen","sequence":"first","affiliation":[{"name":"University of Science,Ho Chi Minh City,Vietnam"}]},{"given":"Huu-Phuc","family":"Huynh","sequence":"additional","affiliation":[{"name":"University of Science,Ho Chi Minh City,Vietnam"}]},{"given":"Minh-Triet","family":"Tran","sequence":"additional","affiliation":[{"name":"University of Science,Ho Chi Minh City,Vietnam"}]},{"given":"Trung-Nghia","family":"Le","sequence":"additional","affiliation":[{"name":"University of Science,Ho Chi Minh City,Vietnam"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2022.1024449"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref3","article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3638884.3638908"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/10400419.2022.2107850"},{"key":"ref7","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3080920"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606719"},{"key":"ref10","volume-title":"Generative ai in multimodal user interfaces: Trends, challenges, and cross-platform adaptability","author":"Bieniek","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s40692-018-0101-5"},{"key":"ref12","article-title":"High-resolution image synthesis with latent diffusion models","volume-title":"CoRR","volume":"abs\/2112.10752","author":"Rombach","year":"2021"},{"key":"ref13","volume-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","author":"Lewis","year":"2021"},{"key":"ref14","article-title":"Retrieval-augmented generation for large language models: A survey","volume":"2","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"G-retriever: Retrieval-augmented generation for textual graph understanding and question answering","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Unims-rag: A unified multi-source retrieval-augmented generation for personalized dialogue systems","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/23311916.2021.1927469"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.371"},{"key":"ref19","article-title":"Omniparser for pure vision based gui agent","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"881","DOI":"10.18653\/v1\/2024.acl-long.50","article-title":"VisuaIWebArena: Evaluating multimodal agents on realistic visual web tasks","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Koh","year":"2024"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"9313","DOI":"10.18653\/v1\/2024.acl-long.505","article-title":"SeeClick: Harnessing GUI grounding for advanced visual GUI agents","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Cheng","year":"2024"},{"key":"ref22","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-010-9189-3"},{"key":"ref24","article-title":"Magentic-one: A generalist multi-agent system for solving complex tasks","volume-title":"Microsoft, Tech. Rep. MSR-TR-2024\u201347","author":"Fourney","year":"2024"},{"key":"ref25","volume-title":"An Introduction to MultiAgent Systems","author":"Wooldridge","year":"2009"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1166\/asl.2012.2227"}],"event":{"name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","location":"Dublin, Ireland","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 International Conference on Content-Based Multimedia Indexing (CBMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11339229\/11339242\/11339318.pdf?arnumber=11339318","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:11:38Z","timestamp":1768979498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339318\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/cbmi66578.2025.11339318","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}