{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T14:44:39Z","timestamp":1785249879966,"version":"3.55.0"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227428","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models"],"prefix":"10.1109","author":[{"given":"Barbara Toniella","family":"Corradini","sequence":"first","affiliation":[{"name":"DIISM University of Siena,Siena,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mustafa","family":"Shukor","sequence":"additional","affiliation":[{"name":"CNRS, ISIR Sorbonne Université,Paris,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Couairon","sequence":"additional","affiliation":[{"name":"CNRS, ISIR Sorbonne Université,Paris,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillaume","family":"Couairon","sequence":"additional","affiliation":[{"name":"INRIA Sorbonne Université,Paris,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Franco","family":"Scarselli","sequence":"additional","affiliation":[{"name":"DIISM University of Siena,Siena,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthieu","family":"Cord","sequence":"additional","affiliation":[{"name":"CNRS, ISIR Sorbonne Université, Valeo.ai,Paris,France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02443-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3506283"},{"key":"ref4","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref5","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref6","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref8","first-page":"23 716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"Unified model for image, video, audio and language tasks","author":"Shukor","year":"2023"},{"issue":"2","key":"ref10","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"key":"ref11","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref13","article-title":"Text-to-image diffusion model in generative ai: A survey","author":"Zhang","year":"2023"},{"key":"ref14","article-title":"Denoising diffusion probabilistic models","volume-title":"CoRR","volume":"abs\/2006.11239","author":"Ho","year":"2020"},{"key":"ref15","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"ref19","article-title":"Sdxl: improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92089-9_23"},{"key":"ref21","article-title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","author":"Lialin","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1561\/0600000095"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01110"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IISA52424.2021.9555526"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004325"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3232153"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00421"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00733"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00743"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref33","article-title":"Label-efficient semantic segmentation with diffusion models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Baranchuk"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"ref35","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022"},{"key":"ref36","article-title":"Generative adversarial networks","author":"Goodfellow","year":"2014"},{"key":"ref37","article-title":"Zero-shot semantic segmentation","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Bucher","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01058"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00695"},{"key":"ref40","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","author":"Yu","year":"2023"},{"key":"ref41","first-page":"33 754","article-title":"Reco: Retrieve and co-segment for zero-shot transfer","volume":"35","author":"Shin","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref44","article-title":"Viewco: Discovering text-supervised segmentation masks via multi-view semantic consistency","volume-title":"The Eleventh International Conference on Learning Representations","author":"Ren"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"ref46","article-title":"Robust classification via a single diffusion model","author":"Chen","year":"2023"},{"key":"ref47","article-title":"Diffusion models beat gans on image classification","author":"Mukhopadhyay","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112141"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"ref51","article-title":"Diffusionseg: Adapting diffusion towards unsupervised object discovery","author":"Ma","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00384"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_18"},{"key":"ref54","article-title":"Peekaboo: Text to image diffusion models are zero-shot segmentors","author":"Burgert","year":"2022"},{"key":"ref55","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref56","article-title":"Efficient inference in fully connected crfs with gaussian edge potentials","volume":"24","author":"Kr\u00e4henb\u00fchl","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref59","article-title":"Perceptual grouping in vision-language models","author":"Ranasinghe","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"ref61","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref65","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref67","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref68","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00431"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","location":"Rome, Italy","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227428.pdf?arnumber=11227428","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:10:09Z","timestamp":1763190609000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227428\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227428","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}