{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:15:39Z","timestamp":1772828139742,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446377","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6585-6589","source":"Crossref","is-referenced-by-count":8,"title":["Grounded-Instruct-Pix2Pix: Improving Instruction Based Image Editing with Automatic Target Grounding"],"prefix":"10.1109","author":[{"given":"Artur","family":"Shagidanov","sequence":"first","affiliation":[{"name":"Picsart AI Research (PAIR)"}]},{"given":"Hayk","family":"Poghosyan","sequence":"additional","affiliation":[{"name":"Picsart AI Research (PAIR)"}]},{"given":"Xinyu","family":"Gong","sequence":"additional","affiliation":[{"name":"UT Austin"}]},{"given":"Zhangyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Picsart AI Research (PAIR)"}]},{"given":"Shant","family":"Navasardyan","sequence":"additional","affiliation":[{"name":"Picsart AI Research (PAIR)"}]},{"given":"Humphrey","family":"Shi","sequence":"additional","affiliation":[{"name":"Picsart AI Research (PAIR)"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Mdp: A generalized framework for text-guided image editing by manipulating the diffusion path","author":"Wang","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref5","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2022"},{"key":"ref6","article-title":"Instructedit: Improving automatic masks for diffusion-based image editing with user instructions","author":"Wang","year":"2023"},{"key":"ref7","article-title":"Introducing chatgpt","year":"2022"},{"key":"ref8","article-title":"Grounded-segment-anything","year":"2022"},{"key":"ref9","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref10","article-title":"Diffusion models beat gans on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref11","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref12","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref14","article-title":"Towards coherent image inpainting using denoising diffusion implicit models","author":"Zhang","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref17","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref19","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02107"},{"key":"ref22","article-title":"Region-aware diffusion for zero-shot text-driven image editing","author":"Huang","year":"2023"},{"key":"ref23","article-title":"spacy: Industrial-strength nlp"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref25","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"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\/10446377.pdf?arnumber=10446377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:13:34Z","timestamp":1722575614000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446377\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446377","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}