{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:02:43Z","timestamp":1784268163167,"version":"3.55.0"},"reference-count":47,"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\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0160201"],"award-info":[{"award-number":["2022ZD0160201"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001459","name":"Ministry of Education, Singapore","doi-asserted-by":"publisher","award":["MOE-T2EP202210012,MOE-T2EP20223-0002"],"award-info":[{"award-number":["MOE-T2EP202210012,MOE-T2EP20223-0002"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Hong Kong RGC","doi-asserted-by":"publisher","award":["TRS T41-603\/20-R"],"award-info":[{"award-number":["TRS T41-603\/20-R"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003452","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003452","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\/iccv51701.2025.01694","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18229-18239","source":"Crossref","is-referenced-by-count":1,"title":["GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography"],"prefix":"10.1109","author":[{"given":"Mengchen","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Wu","sequence":"additional","affiliation":[{"name":"Stanford University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Tan","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gordon","family":"Wetzstein","sequence":"additional","affiliation":[{"name":"Stanford University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cosmos world foundation model platform for physical A","volume":"abs\/2501.03575","author":"Agarwal","year":"2025","journal-title":"CoRR"},{"key":"ref2","article-title":"Navigation world model","volume":"abs\/2412.03572","author":"Bar","year":"2024","journal-title":"CoRR"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large dataset","volume":"abs\/2311.15127","author":"Blattmann","year":"2023","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/38.7751"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21931"},{"key":"ref6","article-title":"Meshanything: Artistcreated mesh generation with autoregressive transformer","volume":"abs\/2406.10163","author":"Chen","year":"2024","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_26"},{"key":"ref8","first-page":"67","article-title":"CINEMA: A system for procedural camera movement","volume-title":"SI3D","author":"Mark Drucker","year":"1992"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1037\/h0031619"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2822013.2822025"},{"key":"ref11","article-title":"Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesi","volume":"abs\/2412.04431","author":"Han","year":"2024","journal-title":"CoRR"},{"key":"ref12","article-title":"Cameractrl: Enabling camera control for text-to-video generatio","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibriu","author":"Heusel","year":"2017","journal-title":"NIPS"},{"key":"ref14","article-title":"Training-free camera control for video generatio","volume":"abs\/2406.10126","author":"Hou","year":"2024","journal-title":"CoRR"},{"key":"ref15","article-title":"Learning camera movement control from real-world drone video","author":"Hou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112823"},{"key":"ref17","first-page":"4244","article-title":"Learning to film from professional human motion video","volume-title":"CVPR","author":"Huang","year":"2019"},{"key":"ref18","article-title":"Gpt-4o system car","volume":"abs\/2410.21276","author":"Hurst","year":"2024","journal-title":"CoRR"},{"key":"ref19","article-title":"Opencli","author":"Ilharco","year":"2021","journal-title":"If you use this software, please cite it as below"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392427"},{"issue":"2","key":"ref21","first-page":"i","article-title":"Cinematographic camera diffusion model. Comput. Graph","volume":"43","author":"Jiang","year":"2024","journal-title":"Forum"},{"key":"ref22","article-title":"Videopoet: A large language model for zero-shot video generatio","volume-title":"ICML","author":"Kondratyuk","year":"2024"},{"key":"ref23","article-title":"Hunyuanvideo: A systematic framework for large video generative model","volume":"abs\/2412.03603","author":"Kong","year":"2024","journal-title":"CoRR"},{"key":"ref24","article-title":"Direc-tor3d: Real-world camera trajectory and 3d scene generation from tex","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802055"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2766965"},{"key":"ref28","article-title":"Splatraj: Camera trajectory generation with semantic gaussian splattin","volume":"abs\/2410.06014","author":"Liu","year":"2024","journal-title":"CoRR"},{"key":"ref29","article-title":"Lindell. Sg-i2v: Selfguided trajectory control in image-to-video generatio","author":"Namekata","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Learning transferable visual models from natural language supervisio","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref31","first-page":"8821","article-title":"Zero-shot text-to-image generatio","volume-title":"ICML","author":"Ramesh","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","article-title":"LAION-5b: An open large-scale dataset for training next generation image-text model","volume-title":"Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Schuhmann","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"ref36","article-title":"Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusio","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Edgerunner: Auto-regressive auto-encoder for artistic mesh generatio","volume":"abs\/2409.18114","author":"Tang","year":"2024","journal-title":"CoRR"},{"key":"ref38","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale predictio","author":"Tian","year":"2024","journal-title":"NeurIPS"},{"key":"ref39","article-title":"Loong: Generating minute-level long videos with autoregressive language model","volume":"abs\/2410.02757","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref40","article-title":"Videogpt: Video generation using VQ-VAE and transformer","volume":"abs\/2104.10157","author":"Yan","year":"2021","journal-title":"CoRR"},{"key":"ref41","article-title":"Scaling autoregressive models for content-rich text-to-image generatio","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res., 202"},{"key":"ref42","first-page":"9150","article-title":"Mvimgnet: A largescale dataset of multi-view image","volume-title":"In CVPR","author":"Yu","year":"2023"},{"key":"ref43","article-title":"Monst3r: A simple approach for estimating geometry in the presence of motio","volume":"abs\/2410.03825","author":"Zhang","year":"2024","journal-title":"CoRR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_13"},{"key":"ref45","article-title":"OPT: open pre-trained transformer language model","volume":"abs\/2205.01068","author":"Zhang","year":"2022","journal-title":"CoRR"},{"key":"ref46","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"}],"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\/11444464.pdf?arnumber=11444464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:12:02Z","timestamp":1777529522000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01694","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}