{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:00:39Z","timestamp":1777888839420,"version":"3.51.4"},"reference-count":76,"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\/iccv51701.2025.01770","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19043-19053","source":"Crossref","is-referenced-by-count":0,"title":["QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing"],"prefix":"10.1109","author":[{"given":"Tiancheng","family":"Shen","sequence":"first","affiliation":[{"name":"CUHK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zilong","family":"Huang","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangtai","family":"Li","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhijie","family":"Lin","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiyang","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yitong","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"UC Merced"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun Hao","family":"Liew","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_12"},{"key":"ref2","first-page":"3","article-title":"Stable flow: Vital layers for training-free image editing","author":"Avrahami","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755462"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref5","volume-title":"The announcements page of black forest labs website.","year":"2023"},{"key":"ref6","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1102"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00846"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref10","first-page":"3","article-title":"Ditctrl: Exploring attention control in multi-modal diffusion transformer for tuning-free multi-prompt longer video generation","author":"Cai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00823"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00616"},{"key":"ref14","article-title":"Consistent video-to-video transfer using synthetic dataset","author":"Cheng","year":"2024","journal-title":"In ICLR"},{"key":"ref15","article-title":"Flatten: optical flow-guided attention for consistent text-to-video editing","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Cong"},{"key":"ref16","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"In ICML"},{"key":"ref17","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"In ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00641"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01208"},{"key":"ref20","article-title":"Edit3k: Universal representation learning for video editing components","author":"Gu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00667"},{"key":"ref22","first-page":"2","article-title":"Prompt-to-prompt image editing with cross-attention control","author":"Hertz","year":"2023","journal-title":"In ICLR"},{"key":"ref23","article-title":"Vivid10 m: A dataset and baseline for versatile and interactive video local editing","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8429-9_14"},{"key":"ref25","first-page":"3","article-title":"Smartedit: Exploring complex instruction-based image editing with multimodal large","author":"Huang","year":"2024","journal-title":"language models. In CVPR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"ref27","article-title":"Hq-edit: A high-quality dataset for instruction-based image editing","author":"Hui","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Taming encoder for zero fine-tuning image cus-tomization with text-to-image diffusion models","author":"Jia","year":"2024","journal-title":"ICLR"},{"key":"ref29","article-title":"Designedit: Multilayered latent decomposition and fusion for unified & accurate image editing","author":"Jia","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Pnp inversion: Boosting diffusion-based editing with 3 lines of code","author":"Ju","year":"2024","journal-title":"In ICLR"},{"key":"ref31","article-title":"Pnp inversion: Boosting diffusion-based editing with 3 lines of code","author":"Ju","year":"2024","journal-title":"In ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref34","first-page":"2","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","first-page":"3","article-title":"Anyv2v: A tuning-free framework for any video-tovideo editing tasks","author":"Ku","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref36","article-title":"Blip-diffusion: Pretrained subject representation for controllable text-to-image generation and editing","author":"Li","year":"2023","journal-title":"NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00598"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref39","article-title":"Magicedit: High-fidelity and temporally coherent video editing","author":"Liew","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Open-sora plan: Open-source large video generation model","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00747"},{"key":"ref42","article-title":"Stablev2v: Stablizing shape consistency in video-tovideo editing","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_2"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref46","article-title":"Dreamix: Video diffusion models are general video editors","volume-title":"arXiv preprint","author":"Molad","year":"2023"},{"key":"ref47","first-page":"3","article-title":"Dreamcreature: Crafting photorealistic virtual creatures from imagination","author":"Woh Ng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","first-page":"3","year":"2024","journal-title":"Video generation models as world simulators."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref51","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref53","article-title":"Unicontrol: a unified diffusion model for controllable visual generation in the wild","author":"Qin","year":"2023","journal-title":"In NeurIPS"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref56","article-title":"Semantic image inversion and editing using rectified stochastic differential equations","author":"Rout","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Edit-a-video: Single video editing with object-aware consistency","author":"Shin","year":"2024","journal-title":"In ACML"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_26"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00875"},{"key":"ref60","volume-title":"Mochi 1.","year":"2024"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref62","first-page":"3","article-title":"Taming rectified flow for inversion and editing","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Zero-shot video editing using off-the-shelf image diffusion models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"ref68","article-title":"Headrouter: A training-free image editing framework for mmdits by adaptively routing attention heads","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref69","article-title":"Object-aware inversion and reassembly for image editing","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref70","first-page":"2","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","article-title":"Ye","author":"Chul","year":"2024","journal-title":"Ground-a-video: Zero-shot grounded video editing using text-to-image diffusion models. In ICLR"},{"key":"ref72","article-title":"Magicbrush: A manually annotated dataset for instructionguided image editing","author":"Zhang","year":"2023","journal-title":"NeurIPS"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00862"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_16"},{"key":"ref75","article-title":"Make-a-protagonist: Generic video editing with an ensemble of experts","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106818"}],"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\/11443302.pdf?arnumber=11443302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:23Z","timestamp":1777611563000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01770","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}