{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:55:24Z","timestamp":1781196924730,"version":"3.54.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T00:00:00Z","timestamp":1723680000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T00:00:00Z","timestamp":1723680000000},"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":[[2024,8,15]]},"DOI":"10.1109\/mapr63514.2024.10660775","type":"proceedings-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T18:23:27Z","timestamp":1725992607000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["InstSynth: Instance-wise Prompt-guided Style Masked Conditional Data Synthesis for Scene Understanding"],"prefix":"10.1109","author":[{"given":"Thanh-Danh","family":"Nguyen","sequence":"first","affiliation":[{"name":"University of Information Technology,Ho Chi Minh City,Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bich-Nga","family":"Pham","sequence":"additional","affiliation":[{"name":"University of Information Technology,Ho Chi Minh City,Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trong-Tai Dam","family":"Vu","sequence":"additional","affiliation":[{"name":"University of Information Technology,Ho Chi Minh City,Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vinh-Tiep","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Information Technology,Ho Chi Minh City,Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thanh Duc","family":"Ngo","sequence":"additional","affiliation":[{"name":"University of Information Technology,Ho Chi Minh City,Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tam V.","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Dayton,Dayton,OH,United States,45469"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024"},{"key":"ref2","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2024"},{"key":"ref3","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref5","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref6","article-title":"Dataset diffusion: Diffusion-based synthetic data generation for pixel-level semantic segmentation","volume":"36","author":"Nguyen","year":"2023","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02266"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00532"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref12","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","author":"Xie","year":"2021","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref14","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MAPR59823.2023.10288682"},{"key":"ref21","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"ICML","author":"Ramesh"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref24","article-title":"Inst-inpaint: Instructing to remove objects with diffusion models","author":"Yildirim","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_28"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00576"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.04.005"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref29","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00259"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref33","article-title":"Scaling wide residual networks for panoptic segmentation","author":"Chen","year":"2020"},{"key":"ref34","article-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref36","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"}],"event":{"name":"2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","location":"Da Nang, Vietnam","start":{"date-parts":[[2024,8,15]]},"end":{"date-parts":[[2024,8,16]]}},"container-title":["2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10660665\/10660652\/10660775.pdf?arnumber=10660775","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T17:32:43Z","timestamp":1726075963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10660775\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,15]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/mapr63514.2024.10660775","relation":{},"subject":[],"published":{"date-parts":[[2024,8,15]]}}}