{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T13:57:48Z","timestamp":1762869468165,"version":"3.30.2"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T00:00:00Z","timestamp":1729296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T00:00:00Z","timestamp":1729296000000},"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":[[2024,10,19]]},"DOI":"10.1109\/cvmi61877.2024.10782008","type":"proceedings-article","created":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T22:24:11Z","timestamp":1733955851000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Octopus: A Latent Diffusion Model for Enhanced Text-Driven Manipulation in Image Synthesis"],"prefix":"10.1109","author":[{"given":"M","family":"Nithin Skantha","sequence":"first","affiliation":[{"name":"Coimbatore Amrita Vishwa Vidyapeetham,Amrita School of Computing,Department of Computer Science and Engineering,India"}]},{"given":"B","family":"Meghadharsan","sequence":"additional","affiliation":[{"name":"Coimbatore Amrita Vishwa Vidyapeetham,Amrita School of Computing,Department of Computer Science and Engineering,India"}]},{"given":"C","family":"Sri Vignesh","sequence":"additional","affiliation":[{"name":"Coimbatore Amrita Vishwa Vidyapeetham,Amrita School of Computing,Department of Computer Science and Engineering,India"}]},{"given":"J","family":"Thiruselvan","sequence":"additional","affiliation":[{"name":"Coimbatore Amrita Vishwa Vidyapeetham,Amrita School of Computing,Department of Computer Science and Engineering,India"}]},{"given":"Arti","family":"Anuragi","sequence":"additional","affiliation":[{"name":"Coimbatore Amrita Vishwa Vidyapeetham,Amrita School of Computing,Department of Computer Science and Engineering,India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"journal-title":"arXiv preprint arXiv:2403.08295","article-title":"Gemma: open models based on Gemini research and technology","year":"2024","key":"ref3"},{"key":"ref4","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint arXiv:2208.01626"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2899108"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00101"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1275808.1276390"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref14","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022","journal-title":"arXiv preprint arXiv:2210.11416"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref16","article-title":"Llama: open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2302.13971"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2017.07.007"},{"key":"ref18","article-title":"Llama 2: open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.14569\/ijacsa.2021.01212115"},{"issue":"4","key":"ref20","first-page":"3131","article-title":"Image segmentation technique- a comparative study","volume":"7","author":"Brunda","year":"2018","journal-title":"International Journal of Engineering and Technology"},{"key":"ref21","article-title":"LoRA: low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv:2106.09685"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2023.01.065"},{"key":"ref23","article-title":"SDEdit: guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv preprint arXiv:2108.01073"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"}],"event":{"name":"2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","start":{"date-parts":[[2024,10,19]]},"location":"Prayagraj, India","end":{"date-parts":[[2024,10,20]]}},"container-title":["2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10781474\/10781502\/10782008.pdf?arnumber=10782008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T07:37:07Z","timestamp":1733989027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10782008\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,19]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cvmi61877.2024.10782008","relation":{},"subject":[],"published":{"date-parts":[[2024,10,19]]}}}