{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:20:39Z","timestamp":1778080839317,"version":"3.51.4"},"reference-count":65,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01387","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14951-14961","source":"Crossref","is-referenced-by-count":2,"title":["Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment"],"prefix":"10.1109","author":[{"given":"Lijie","family":"Liu","sequence":"first","affiliation":[{"name":"ByteDance,Intelligent Creation Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianxiang","family":"Ma","sequence":"additional","affiliation":[{"name":"ByteDance,Intelligent Creation Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingchuan","family":"Li","sequence":"additional","affiliation":[{"name":"ByteDance,Intelligent Creation Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuowei","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance,Intelligent Creation Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance,Intelligent Creation Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gen","family":"Li","sequence":"additional","affiliation":[{"name":"ByteDance,Intelligent Creation Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"ByteDance,Intelligent Creation Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"He","sequence":"additional","affiliation":[{"name":"ByteDance,Intelligent Creation Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinglong","family":"Wu","sequence":"additional","affiliation":[{"name":"ByteDance,Intelligent Creation Team"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Bai","year":"2025","journal-title":"Qwen2.5-vl technical report"},{"key":"ref2","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00572"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01166"},{"key":"ref6","first-page":"1281","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Chen","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref9","volume-title":"dreamina. Generate image and video capabilities","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref11","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":"ref12","author":"Gal","year":"2022","journal-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion"},{"key":"ref13","author":"Guo","year":"2023","journal-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning"},{"key":"ref14","author":"Guo","year":"2024","journal-title":"Pulid: Pure and lightning id customization via contrastive alignment"},{"key":"ref15","author":"Han","year":"2024","journal-title":"Ace: Allround creator and editor following instructions via diffusion transformer"},{"key":"ref16","author":"He","year":"2024","journal-title":"Id-animator: Zero-shot identity-preserving human video generation"},{"key":"ref17","author":"Ho","year":"2022","journal-title":"Classifier-free diffusion guidance"},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","author":"Edward","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref20","author":"Huang","year":"2024","journal-title":"In-context lora for diffusion transformers"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00714"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"ref23","author":"Huang","year":"2025","journal-title":"Conceptmaster: Multi-concept video customization on diffusion transformer models without test-time tuning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02060"},{"key":"ref25","volume-title":"Imagededup","author":"Jain","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00639"},{"key":"ref27","volume-title":"keling. Image to video elements feature","year":"2024"},{"key":"ref28","author":"Kong","year":"2024","journal-title":"Hunyuanvideo: A systematic framework for large video generative models"},{"key":"ref29","volume-title":"Labs. Flux","author":"Forest","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01227"},{"key":"ref31","author":"Lin","year":"2025","journal-title":"Diffusion adversarial post-training for one-step video generation"},{"key":"ref32","author":"Lipman","year":"2022","journal-title":"Flow matching for generative modeling"},{"key":"ref33","author":"Liu","year":"2022","journal-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow"},{"key":"ref34","author":"Lu","year":"2024","journal-title":"Qwen2vl-flux: Unifying image and text guidance for controllable image generation"},{"key":"ref35","volume-title":"MiniMax. Hailuo s2v-01","year":"2024"},{"key":"ref36","volume-title":"OpenAI. Sora","year":"2023"},{"key":"ref37","volume-title":"OpenAI. Chatgpt","year":"2024"},{"key":"ref38","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref40","volume-title":"Pika. Pikascenes","year":"2024"},{"key":"ref41","author":"Polyak","year":"2024","journal-title":"Movie gen: A cast of media foundation models"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","first-page":"234","article-title":"Unet: Convolutional networks for biomedical image segmentation","volume-title":"Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany","author":"Ronneberger","year":"2015"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"ref47","author":"Shao","year":"2022","journal-title":"1st place solution in google universal images embedding"},{"key":"ref48","author":"Singer","year":"2022","journal-title":"Make-a-video: Text-to-video generation without text-video data"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref50","author":"Team","year":"2023","journal-title":"Gemini: a family of highly capable multimodal models"},{"key":"ref51","volume-title":"Team. Pyscenedetect: An open-source video scene detection tool","author":"Development","year":"2024"},{"key":"ref52","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref53","first-page":"30","author":"Vaswani","year":"2017","journal-title":"Attention is all you need. Advances in neural information processing systems"},{"key":"ref54","volume-title":"Vidu. Reference to video","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00207"},{"key":"ref56","author":"Wang","year":"2024","journal-title":"Instantid: Zero-shot identity-preserving generation in seconds"},{"key":"ref57","author":"Wang","year":"2022","journal-title":"Internvideo: General video foundation models via generative and discriminative learning"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01241"},{"key":"ref59","author":"Yang","year":"2024","journal-title":"Qwen2. 5 technical report"},{"key":"ref60","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref61","author":"Ye","year":"2023","journal-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.32388\/o51iwn"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref64","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00218"}],"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\/11445782.pdf?arnumber=11445782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:59Z","timestamp":1777529759000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01387","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}