{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:22:07Z","timestamp":1778048527465,"version":"3.51.4"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00391","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"4015-4024","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Text-Guided Convolutional Adapter for the Diffusion Model"],"prefix":"10.1109","author":[{"given":"Aryan","family":"Das","sequence":"first","affiliation":[{"name":"VIT,Bhopal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koushik","family":"Biswas","sequence":"additional","affiliation":[{"name":"IIIT,Delhi"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swalpa Kumar","family":"Roy","sequence":"additional","affiliation":[{"name":"Tezpur University,Assam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Badri","family":"Narayana Patro","sequence":"additional","affiliation":[{"name":"IIT,Kanpur"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vinay Kumar","family":"Verma","sequence":"additional","affiliation":[{"name":"IIT,Kanpur"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ediffi: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref3","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","author":"Ding","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"Nice: Non-linear independent components estimation","author":"Dinh","year":"2014"},{"key":"ref5","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","author":"Feng","year":"2022"},{"key":"ref6","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref7","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Group diffusion transformers are unsupervised multitask learners","author":"Huang","year":"2024"},{"key":"ref9","article-title":"In-context lora for diffusion transformers","author":"Huang","year":"2024"},{"key":"ref10","article-title":"Chatdit: A training-free baseline for task-agnostic free-form chatting with diffusion transformers","author":"Huang","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref13","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref14","first-page":"129","article-title":"Controlnet++: Improving conditional controls with efficient consistency feedback","volume-title":"Computer Vision \u2013 ECCV 2024: 18th European Conference, Milan, Italy, September 29\u2013October 4, 2024, Proceedings, Part VII","author":"Li"},{"key":"ref15","article-title":"A simple approach to unifying diffusion-based conditional generation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Li"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01728"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref19","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref22","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref27","article-title":"pytorch-fid: FID Score for PyTorch","author":"Seitzer","year":"2020"},{"key":"ref28","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International Conference on Machine Learning","author":"Sohl-Dickstein"},{"key":"ref29","article-title":"In-context edit: Enabling instructional image editing with in-context generation in large scale diffusion transformer","author":"Song","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i11.37866"},{"key":"ref31","first-page":"32","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00507"},{"key":"ref33","article-title":"Pretraining is all you need for image-to-image translation","author":"Wang","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref35","article-title":"Videomaker: Zero-shot customized video generation with the inherent force of video diffusion models","author":"Wu","year":"2024"},{"key":"ref36","article-title":"CtrloRA: An extensible and efficient framework for controllable image generation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Xu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref38","article-title":"Lafite: Towards language-free training for text-to-image generation","author":"Zhou","year":"2021"},{"key":"ref39","first-page":"2223","article-title":"Unpaired image-to-image translation using cycleconsistent adversarial networks","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Zhu"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492717.pdf?arnumber=11492717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:06:24Z","timestamp":1778047584000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492717\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00391","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}