{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:32:40Z","timestamp":1761895960086,"version":"build-2065373602"},"reference-count":31,"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\/icme59968.2025.11209990","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["SAMDiffusion: Semantic Segmentation with Diffusion Model and Segmentation Anything Model"],"prefix":"10.1109","author":[{"given":"Yihao","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing Info. Sci. Tech. Univ.,School of Computer Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Mu","sequence":"additional","affiliation":[{"name":"Beijing Info. Sci. Tech. Univ.,School of Computer Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peixiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Info. Sci. Tech. Univ.,School of Computer Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Info. Sci. Tech. Univ.,School of Computer Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Info. Sci. Tech. Univ.,School of Computer Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoming","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing Info. Sci. Tech. Univ.,School of Computer Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"ref4","article-title":"Dataset diffusion: Diffusion-based synthetic data generation for pixel-level semantic segmentation","author":"Nguyen","year":"2024","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"article-title":"Rethinking atrous convolution for semantic image segmentation","year":"2017","author":"Chieh","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"article-title":"Semantic image segmentation with deep convolutional nets and fully connected crfs","year":"2014","author":"Chieh","key":"ref9"},{"key":"ref10","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"Chieh","year":"2017","journal-title":"PAMI"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00341"},{"article-title":"Factorized diffusion architectures for unsupervised image generation and segmentation","year":"2023","author":"Yuan","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"article-title":"Diffusion model is secretly a training-free open vocabulary semantic segmenter","year":"2023","author":"Jinglong","key":"ref15"},{"article-title":"Attention as annotation: Generating images and pseudo-masks for weakly supervised semantic segmentation with diffusion","year":"2023","author":"Ryota","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128437"},{"article-title":"Diffusionseg: Adapting diffusion towards unsupervised object discovery","year":"2023","author":"Ma","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00379"},{"article-title":"Segment anything model (sam) enhanced pseudo labels for weakly supervised semantic segmentation","year":"2023","author":"Chen","key":"ref21"},{"article-title":"Am-sam: Automated prompting and mask calibration for segment anything model","year":"2024","author":"chen","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01844"},{"article-title":"Samaug: Point prompt augmentation for segment anything model","year":"2023","author":"xing","key":"ref24"},{"author":"Tran","key":"ref25","article-title":"Synthesizing image with high-quality segmentation mask by prompting large vision model"},{"key":"ref26","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"nan","year":"2022","journal-title":"ICML"},{"article-title":"React: Synergizing reasoning and acting in language models","year":"2022","author":"yu","key":"ref27"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref28"},{"article-title":"Deepseek-v3 technical report","year":"2024","author":"Liu","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref31","article-title":"Semantic understanding of scenes through the ade20k dataset","author":"lei","year":"2019","journal-title":"IJCV"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209990.pdf?arnumber=11209990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T06:03:36Z","timestamp":1761890616000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209990","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}