{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:07:06Z","timestamp":1761898026616},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687813","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Training-Free Semantic Video Composition via Pre-trained Diffusion Model"],"prefix":"10.1109","author":[{"given":"Jiaqi","family":"Guo","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sitong","family":"Su","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junchen","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,Shenzhen Institute for Advanced Study,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,Shenzhen Institute for Advanced Study,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Dreamix: Video Diffusion Models are General Video Editors","year":"2023","author":"Molad","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2013.2251642"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2019.2916769"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2017.2706197"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28300"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2022\/172","volume-title":"Deep Video Harmonization with Color Mapping Consistency","author":"Lu","year":"2022"},{"volume-title":"Temporally Coherent Video Harmonization Using Adversarial Networks","year":"2018","author":"Huang","key":"ref7"},{"volume-title":"Harmonizer: Learning to Perform White-Box Image and Video Harmonization","year":"2022","author":"Ke","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"volume-title":"Making Images Real Again: A Comprehensive Survey on Deep Image Composition","year":"2022","author":"Niu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01792"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00573"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01754"},{"volume-title":"Hierarchical Dynamic Image Harmonization","year":"2022","author":"Chen","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3207091"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00479","article-title":"SSH: A Self-Supervised Framework for Image Harmonization","volume-title":"ICCV2021","author":"Jiang","year":"2021"},{"article-title":"AnyDoor: Zero-shot Object-level Image Customization","year":"2023","author":"Chen","key":"ref18"},{"volume-title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","year":"2023","author":"Lu","key":"ref19"},{"volume-title":"Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model","year":"2023","author":"Zhang","key":"ref20"},{"volume-title":"Compositional GAN: Learning Image-Conditional Binary Composition","year":"2019","author":"Azadi","key":"ref21"},{"volume-title":"ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing","year":"2018","author":"Lin","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/wacv45572.2020.9093632"},{"volume-title":"HS-Diffusion: Semantic-Mixing Diffusion for Head Swapping","year":"2023","author":"Wang","key":"ref24"},{"volume-title":"Prompt-to-Prompt Image Editing with Cross Attention Control","year":"2022","author":"Hertz","key":"ref25"},{"volume-title":"DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation","year":"2022","author":"Kim","key":"ref26"},{"volume-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","year":"2022","author":"Couairon","key":"ref27"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.00574","article-title":"Semi-supervised Parametric Real-world Image Harmonization","volume-title":"CVPR2023","author":"Wang","year":"2023"},{"volume-title":"The 2017 DAVIS Challenge on Video Object Segmentation","year":"2018","author":"Pont-Tuset","key":"ref29"},{"volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","year":"2015","author":"Simonyan","key":"ref30"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687813.pdf?arnumber=10687813","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:36:05Z","timestamp":1727764565000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687813\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687813","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}