{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T04:13:36Z","timestamp":1749701616348,"version":"3.41.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272157"],"award-info":[{"award-number":["62272157"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3573471","type":"journal-article","created":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T18:04:21Z","timestamp":1748887461000},"page":"3294-3308","source":"Crossref","is-referenced-by-count":0,"title":["MCT-CCDiff: Context-Aware Contrastive Diffusion Model With Mediator-Bridging Cross-Modal Transformer for Image Change Captioning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4048-5827","authenticated-orcid":false,"given":"Jinhong","family":"Hu","sequence":"first","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6054-3694","authenticated-orcid":false,"given":"Guojin","family":"Zhong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9600-7789","authenticated-orcid":false,"given":"Jin","family":"Yuan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5527-2914","authenticated-orcid":false,"given":"Wenbo","family":"Pan","sequence":"additional","affiliation":[{"name":"CRRC Zhuzhou Institute Company Ltd., Zhuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoping","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1436"},{"key":"ref3","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref4","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00472"},{"key":"ref6","first-page":"2095","article-title":"Agnostic change captioning with cycle consistency","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Kim"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20218"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref12","first-page":"4328","article-title":"Diffusion-LM improves controllable text generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref13","article-title":"Exploring discrete diffusion models for image captioning","author":"Zhu","year":"2022","journal-title":"arXiv:2211.11694"},{"key":"ref14","first-page":"1","article-title":"Analog bits: Generating discrete data using diffusion models with self-conditioning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25360"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25137"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_34"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074803"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.735"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00198"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3268004"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3242142"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3254162"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00263"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3365104"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3660346"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.430"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_18"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3445337"},{"key":"ref32","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref33","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Nichol"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613781"},{"key":"ref36","first-page":"12454","article-title":"Argmax flows and multinomial diffusion: Learning categorical distributions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Hoogeboom"},{"key":"ref37","first-page":"1","article-title":"Step-unrolled denoising autoencoders for text generation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Savinov"},{"key":"ref38","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Austin"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.261"},{"key":"ref40","first-page":"1","article-title":"DiffuSeq: Sequence to sequence text generation with diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gong"},{"key":"ref41","article-title":"DiffCap: Exploring continuous diffusion on image captioning","author":"He","year":"2023","journal-title":"arXiv:2305.12144"},{"key":"ref42","first-page":"39957","article-title":"AR-diffusion: Auto-regressive diffusion model for text generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref43","first-page":"37636","article-title":"Improving diffusion-based image synthesis with context prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref44","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Kenton"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1065"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1182"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.196"},{"key":"ref49","first-page":"1","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref51","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref53","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization Branches Out","author":"Lin"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.451"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1387"},{"key":"ref56","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref58","article-title":"DPM-Solver++: Fast solver for guided sampling of diffusion probabilistic models","author":"Lu","year":"2022","journal-title":"arXiv:2211.01095"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00275"},{"article-title":"The caltech-UCSD birds-200\u20132011 dataset","year":"2011","author":"Wah","key":"ref61"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6301"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11021330.pdf?arnumber=11021330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T17:47:43Z","timestamp":1749664063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11021330\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3573471","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2025]]}}}