{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T08:19:32Z","timestamp":1769674772436,"version":"3.49.0"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LD25F020001"],"award-info":[{"award-number":["LD25F020001"]}],"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":["62337001"],"award-info":[{"award-number":["62337001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2025-00057"],"award-info":[{"award-number":["226-2025-00057"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tcsvt.2025.3588357","type":"journal-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T17:44:27Z","timestamp":1752515067000},"page":"1203-1215","source":"Crossref","is-referenced-by-count":0,"title":["Generalized Visual Relation Detection With Diffusion Models"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2450-6551","authenticated-orcid":false,"given":"Kaifeng","family":"Gao","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}]},{"given":"Siqi","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7374-8739","authenticated-orcid":false,"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6142-9914","authenticated-orcid":false,"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7361-3084","authenticated-orcid":false,"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2689-317X","authenticated-orcid":false,"given":"Qianru","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Information Systems, Singapore Management University, Bras Basah, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268066"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01888"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358952"},{"key":"ref4","first-page":"17209","article-title":"Mining the benefits of two-stage and one-stage HOI detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Zhang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_26"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3216663"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3402247"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3282349"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231437"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319633"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3443417"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref15","first-page":"1","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. ICLR","author":"Gu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25385"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02652"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00285"},{"key":"ref22","first-page":"4328","article-title":"Diffusion-LM improves controllable text generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Li"},{"key":"ref23","first-page":"1","article-title":"DiffuSeq: Sequence to sequence text generation with diffusion models","volume-title":"Proc. ICLR","author":"Gong"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_24"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2990989"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3119892"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01645"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3130197"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00717"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413600"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6616"},{"key":"ref38","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zeng"},{"key":"ref39","first-page":"8765","article-title":"Debiased contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chuang"},{"key":"ref40","first-page":"1","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS Workshop Deep Generative Models Downstream Appl.","author":"Ho"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","first-page":"1","article-title":"VDT: General-purpose video diffusion transformers via mask modeling","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Lu"},{"key":"ref43","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","author":"Ho"},{"key":"ref44","article-title":"DiffWave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020","journal-title":"arXiv:2009.09761"},{"key":"ref45","article-title":"Guided-TTS 2: A diffusion model for high-quality adaptive text-to-speech with untranscribed data","author":"Kim","year":"2022","journal-title":"arXiv:2205.15370"},{"key":"ref46","first-page":"1","article-title":"Analog bits: Generating discrete data using diffusion models with self-conditioning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0908-6_9"},{"key":"ref49","article-title":"Exploring discrete diffusion models for image captioning","author":"Zhu","year":"2022","journal-title":"arXiv:2211.11694"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5603-2_18"},{"key":"ref51","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref53","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref55","article-title":"Understanding diffusion models: A unified perspective","author":"Luo","year":"2022","journal-title":"arXiv:2208.11970"},{"key":"ref56","first-page":"21696","article-title":"Variational diffusion models","volume-title":"Proc. NIPS","volume":"34","author":"Kingma"},{"key":"ref57","first-page":"3738","article-title":"Ladder variational autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"S\u00f8nderby"},{"key":"ref58","first-page":"4743","article-title":"Improved variational inference with inverse autoregressive flow","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Kingma"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1137\/0105003"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387349"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref65","article-title":"Visual semantic role labeling","author":"Gupta","year":"2015","journal-title":"arXiv:1505.04474"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref68","volume-title":"Natural Language Processing With Python: Analyzing Text With the Natural Language Toolkit","author":"Bird","year":"2009"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2812"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00101"},{"key":"ref71","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_1"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413722"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref75","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/176"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11365019\/11079713.pdf?arnumber=11079713","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:01:13Z","timestamp":1769634073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11079713\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":78,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3588357","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}