{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:46:20Z","timestamp":1793205980090,"version":"4.5.0"},"reference-count":116,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62376259"],"award-info":[{"award-number":["62376259"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306301"],"award-info":[{"award-number":["62306301"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012152","name":"National Postdoctoral Program for Innovative Talents","doi-asserted-by":"publisher","award":["BX20220310"],"award-info":[{"award-number":["BX20220310"]}],"id":[{"id":"10.13039\/501100012152","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3623508","type":"journal-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T17:57:06Z","timestamp":1760983026000},"page":"297-308","source":"Crossref","is-referenced-by-count":1,"title":["DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4481-0895","authenticated-orcid":false,"given":"Yinqi","family":"Li","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2668-0070","authenticated-orcid":false,"given":"Hong","family":"Chang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2480-6538","authenticated-orcid":false,"given":"Ruibing","family":"Hou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8348-392X","authenticated-orcid":false,"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3024-4404","authenticated-orcid":false,"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"ref2","first-page":"58921","article-title":"Text-to-image diffusion models are zero-shot classifiers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Clark","year":"2023"},{"key":"ref3","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref4","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref5","first-page":"1","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref6","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dhariwal","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref8","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Saharia","year":"2022"},{"key":"ref9","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"van den Oord","year":"2017"},{"key":"ref10","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Razavi","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref12","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref14","first-page":"1","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref16","first-page":"1","article-title":"Is synthetic data from generative models ready for image recognition?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00774"},{"key":"ref18","first-page":"1","article-title":"Synthetic data from diffusion models improves imagenet classification","author":"Azizi","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"ref20","first-page":"76872","article-title":"Dataset diffusion: Diffusion-based synthetic data generation for pixel-level semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Nguyen","year":"2023"},{"key":"ref21","first-page":"1","article-title":"GeoDiffusion: Text-prompted geometric control for object detection data generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00129"},{"key":"ref23","first-page":"1","article-title":"Label-efficient semantic segmentation with diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baranchuk","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01736"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01531"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01317"},{"key":"ref29","first-page":"1","article-title":"Diffusion models trained with large data are transferable visual models","author":"Xu","year":"2025","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref30","first-page":"841","article-title":"On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ng","year":"2001"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref32","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3415357"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3399075"},{"key":"ref35","first-page":"1","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3318297"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3382484"},{"key":"ref38","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3334019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3362149"},{"key":"ref41","article-title":"ImaginaryNet: Learning object detectors without real images and annotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ni","year":"2023"},{"key":"ref42","first-page":"43479","article-title":"Diffusion models and semi-supervised learners benefit mutually with few labels","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"You","year":"2023"},{"key":"ref43","first-page":"79024","article-title":"Diversify your vision datasets with automatic diffusion-based augmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dunlap","year":"2023"},{"key":"ref44","first-page":"18659","article-title":"FreeMask: Synthetic images with dense annotations make stronger segmentation models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_18"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02223-3"},{"key":"ref47","first-page":"1","article-title":"Gen2Det: Generate to detect","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Suri","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00705"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_15"},{"key":"ref50","first-page":"740","article-title":"Bridging generative and discriminative models for unified visual perception with diffusion priors","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Dong","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02672"},{"key":"ref52","article-title":"SegDiff: Image segmentation with diffusion probabilistic models","author":"Amit","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00090"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_25"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00751"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3394777"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00341"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00384"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3551648"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128437"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref66","article-title":"Score-based generative classifiers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop Deep Generative Models Downstream Appl.","author":"Zimmermann","year":"2021"},{"key":"ref67","first-page":"6643","article-title":"Robust classification via a single diffusion model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2024"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1584"},{"key":"ref69","first-page":"8385","article-title":"Are diffusion models vision-and-language reasoners?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Krojer","year":"2023"},{"key":"ref70","first-page":"1","article-title":"SelfEval: Leveraging the discriminative nature of generative models for evaluation","author":"Rambhatla","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_36"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181070"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2875194"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"ref77","article-title":"Improved StyleGAN embedding: Where are the good latents?","author":"Zhu","year":"2020"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459838"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01796"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3065230"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_35"},{"key":"ref83","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02158"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_2"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00207"},{"key":"ref88","first-page":"1","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gal","year":"2023"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01281"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00650"},{"key":"ref91","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25133"},{"key":"ref94","article-title":"LayoutDiffuse: Adapting foundational diffusion models for layout-to-image generation","author":"Cheng","year":"2023"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref100","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.472"},{"key":"ref105","article-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref106","article-title":"Adversarial attacks on image generation with made-up words","author":"Millire","year":"2022"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00236"},{"key":"ref108","article-title":"Evaluating the robustness of text-to-image diffusion models against real-world attacks","author":"Gao","year":"2023"},{"key":"ref109","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref110","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky","year":"2012"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1611.05431"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref114","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heusel","year":"2017"},{"key":"ref115","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Salimans","year":"2016"},{"key":"ref116","first-page":"3927","article-title":"Improved precision and recall metric for assessing generative models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kynknniemi","year":"2019"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11207541.pdf?arnumber=11207541","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:02:02Z","timestamp":1768255322000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11207541\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":116,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3623508","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}