{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:10:35Z","timestamp":1781086235841,"version":"3.54.1"},"reference-count":114,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["62471148"],"award-info":[{"award-number":["62471148"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01151","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12381-12393","source":"Crossref","is-referenced-by-count":4,"title":["DreamRelation: Relation-Centric Video Customization"],"prefix":"10.1109","author":[{"given":"Yujie","family":"Wei","sequence":"first","affiliation":[{"name":"Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hangjie","family":"Yuan","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biao","family":"Gong","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longxiang","family":"Tang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haonan","family":"Qiu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengjia","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Tan","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingya","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongming","family":"Shan","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation","author":"An","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref4","article-title":"table video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00727"},{"key":"ref7","article-title":"Omnivcus: Feedforward subject-driven video customization with multimodal control conditions","author":"Cai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3687945"},{"key":"ref10","article-title":"Videodreamer: Customized multi-subject text-to-video generation with disen-mix finetuning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Open diffusion models for high-quality video generation","volume":"1","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680637"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00698"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00572"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1318"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02285"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref18","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref19","article-title":"Vchitect-2.0: Parallel transformer for scaling up video diffusion models","author":"Fan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref21","article-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413854"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680621"},{"key":"ref24","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390204"},{"key":"ref26","article-title":"Idanimator: Zero-shot identity-preserving human video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref28","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref29","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00591"},{"key":"ref32","article-title":"Lora: Low-rank adaptation of large language models","author":"Edward","year":"2021","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16250"},{"key":"ref34","article-title":"Conceptmaster: Multi-concept video customization on diffusion transformer models without test-time tuning","author":"Huang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Generalizable object re-identifcation via visual in-context prompting","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Huang","year":"2025"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687658"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_21"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00880"},{"key":"ref39","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref41","article-title":"Videopoet: A large language model for zero-shot video generation","author":"Kondratyuk","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","volume-title":"Open-sora: Democratizing efficient video production for all","author":"Lab","year":"2024"},{"key":"ref44","article-title":"Gca-3d: Towards generalized and consistent domain adaptation of 3d generators","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Personalvideo: High id-fidelity video customization without dynamic and semantic degradation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01183"},{"key":"ref47","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00689"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref51","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28177"},{"key":"ref53","article-title":"What is a good caption? a comprehensive visual caption benchmark for evaluating both correctness and thoroughness","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687587"},{"key":"ref58","article-title":"Follow-your-creation: Empowering 4d creation through video inpainting","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32643"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92808-6_2"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref62","article-title":"Dreamix: Video diffusion models are general video editors","author":"Molad","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01844"},{"key":"ref64","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref66","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00634"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73024-5_20"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref72","article-title":"Customvideox: 3d reference attention driven dynamic adaptation for zero-shot customized video diffusion transformers","author":"She","year":"2025","journal-title":"arXiv preprint"},{"key":"ref73","article-title":"Relationbooth: Towards relation-aware customized object generation","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02233"},{"key":"ref75","article-title":"Animate-x: Universal character image animation with enhanced motion representation","author":"Tan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_23"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02486"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref79","volume-title":"Mochi 1","author":"Team","year":"2024"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00753"},{"key":"ref81","article-title":"Motionfollower: Editing video motion via lightweight score-guided diffusion","author":"Tu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref83","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref84","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref85","article-title":"Motion inversion for video customization","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref87","article-title":"Videolcm: Video latent consistency model","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4592-3"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00628"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2026.3668653"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00625"},{"key":"ref94","article-title":"Dreamvideo-2: Zero-shot subjectdriven video customization with precise motion control","author":"Wei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref95","article-title":"Motionbooth: Motion-aware customized text-tovideo generation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref96","article-title":"Videomaker: Zero-shot customized video generation with the inherent force of video diffusion models","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32914"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730604"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00129"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3607711"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"ref103","article-title":"Rethinking video tokenization: A conditioned diffusion-based approach","author":"Yang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref104","article-title":"Cogvideox: Text-tovideo diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00809"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2712"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00618"},{"key":"ref108","article-title":"Identitypreserving text-to-video generation by frequency decomposition","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02271-9"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref111","article-title":"Fantasyid: Face knowledge enhanced id-preserving video generation","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_16"},{"key":"ref113","volume-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref114","article-title":"Sugar: Subject-driven video customization in a zero-shot manner","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref115","article-title":"Storydiffusion: Consistent selfattention for long-range image and video generation","author":"Zhou","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446316.pdf?arnumber=11446316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:44Z","timestamp":1777529804000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446316\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":114,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01151","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}