{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T10:07:01Z","timestamp":1789380421706,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370280","type":"print"},{"value":"9783032370297","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37029-7_34","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:49:20Z","timestamp":1789379360000},"page":"586-602","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Who Does What and\u00a0Where to\u00a0Go: Orthogonal Alignment and\u00a0Hierarchical Planning for\u00a0Multi-entity Trajectories"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0930-9284","authenticated-orcid":false,"given":"Zhang","family":"Wan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1331-5020","authenticated-orcid":false,"given":"Yu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3732-9173","authenticated-orcid":false,"given":"Tianze","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7857-1546","authenticated-orcid":false,"given":"Juan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3573-2407","authenticated-orcid":false,"given":"Sheng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"issue":"4","key":"34_CR1","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1109\/38.7751","volume":"8","author":"J Blinn","year":"2002","unstructured":"Blinn, J.: Where am i? What am i looking at?(Cinematography). In IEEE Comput. Graphics Appl. 8(4), 76\u201381 (2002)","journal-title":"In IEEE Comput. Graphics Appl."},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Chang, W.J., Zhan, W., Tomizuka, M., Chandraker, M., Pittaluga, F.: Langtraj: diffusion model and dataset for language-conditioned trajectory simulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 26622\u201326631 (2025)","DOI":"10.1109\/ICCV51701.2025.02471"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Courant, R., Dufour, N., Wang, X., Christie, M., Kalogeiton, V.: Et the exceptional trajectories: text-to-camera-trajectory generation with character awareness. In: European Conference on Computer Vision, pp. 464\u2013480. Springer (2024)","DOI":"10.1007\/978-3-031-73235-5_26"},{"key":"34_CR4","unstructured":"Galoaa, B., Bai, X., Ostadabbas, S.: Lang2motion: bridging language and motion through joint embedding spaces. arXiv preprint arXiv:2512.10617 (2025)"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Galvane, Q., Christie, M., Lino, C., Ronfard, R.: Camera-on-rails: automated computation of constrained camera paths. In: ACM SIGGRAPH Conference on Motion in Games, pp. 151\u2013157 (2015)","DOI":"10.1145\/2822013.2822025"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Ji, L., Zhong, L., Wei, P., Li, C.: Posetraj: pose-aware trajectory control in video diffusion. arXiv preprint arXiv:2503.16068 (2025)","DOI":"10.1109\/CVPR52734.2025.02121"},{"issue":"4","key":"34_CR7","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1145\/3386569.3392427","volume":"39","author":"H Jiang","year":"2020","unstructured":"Jiang, H., Wang, B., Wang, X., Christie, M., Chen, B.: Example-driven virtual cinematography by learning camera behaviors. ACM Trans. Graph. 39(4), 45 (2020)","journal-title":"ACM Trans. Graph."},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Jiang, H., Wang, X., Christie, M., Liu, L., Chen, B.: Cinematographic camera diffusion model. In: Computer Graphics Forum. vol. 43, p. e15055. Wiley Online Library (2024)","DOI":"10.1111\/cgf.15055"},{"key":"34_CR9","doi-asserted-by":"publisher","first-page":"75125","DOI":"10.52202\/079017-2391","volume":"37","author":"X Li","year":"2024","unstructured":"Li, X., et al.: Director3d: real-world camera trajectory and 3D scene generation from text. Adv. Neural. Inf. Process. Syst. 37, 75125\u201375151 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Ling, L., et al.: Dl3dv-10k: a large-scale scene dataset for deep learning-based 3D vision. In: Computer Vision and Pattern Recognition, pp. 22160\u201322169 (2024)","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"34_CR11","unstructured":"Liu, X., Zhang, T., Johnson-Roberson, M., Zhi, W.: Splatraj: camera trajectory generation with semantic gaussian splatting. arXiv preprint arXiv:2410.06014 (2024)"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Tevet, G., Gordon, B., Hertz, A., Bermano, A.H., Cohen-Or, D.: Motionclip: exposing human motion generation to clip space. In: European Conference on Computer Vision, pp. 358\u2013374. Springer (2022)","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Wan, Z., Tang, S., Wei, J., Zhang, R., Cao, J.: Dragentity: trajectory guided video generation using entity and positional relationships. In: ACM International Conference on Multimedia, pp. 108\u2013116 (2024)","DOI":"10.1145\/3664647.3681567"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Wang, W., Yu, C., Wang, Y., Min, B.C.: Human-robot cooperative distribution coupling for Hamiltonian-constrained social navigation. In: 2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 10808\u201310815. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11128561"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Motionctrl: a unified and flexible motion controller for video generation. In: ACM SIGGRAPH, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657518"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Wu, W., et al.: Draganything: motion control for anything using entity representation. In: European Conference on Computer Vision, pp. 331\u2013348. Springer (2024)","DOI":"10.1007\/978-3-031-72670-5_19"},{"key":"34_CR17","unstructured":"Xiao, F., et al.: 3dtrajmaster: mastering 3D trajectory for multi-entity motion in video generation. In: International Conference on Learning Representations (2025)"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Yang, H., Xie, K., Huang, S., Huang, H.: Uncut aerial video via a single sketch. In: Computer Graphics Forum, vol. 37, pp. 191\u2013199. Wiley Online Library (2018)","DOI":"10.1111\/cgf.13559"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: Direct-a-video: customized video generation with user-directed camera movement and object motion. In: ACM SIGGRAPH, pp. 1\u201312 (2024)","DOI":"10.1145\/3641519.3657481"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Yariv, G., et al.: Through-the-mask: Mask-based motion trajectories for image-to-video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18198\u201318208 (2025)","DOI":"10.1109\/CVPR52734.2025.01696"},{"key":"34_CR21","unstructured":"Yin, S., et al.: Dragnuwa: finegrained control in video generation by integrating text, image, and trajectory. arXiv preprint arXiv:2308.08089 (2023)"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Yu, X., et al.: Mvimgnet: a large-scale dataset of multi-view images. In: Computer Vision and Pattern Recognition, pp. 9150\u20139161 (2023)","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, M., Wu, T., Tan, J., Liu, Z., Wetzstein, G., Lin, D.: Gendop: autoregressive camera trajectory generation as a director of photography. arXiv preprint arXiv:2504.07083 (2025)","DOI":"10.1109\/ICCV51701.2025.01694"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Zo3t: Zeroshot 3D-aware trajectory-guided image-to-video generation via test-time training. arXiv preprint arXiv:2509.06723 (2025)","DOI":"10.1609\/aaai.v40i15.38267"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Zhou, T., Tucker, R., Flynn, J., Fyffe, G., Snavely, N.: Stereo magnification: learning view synthesis using multiplane images. arXiv preprint arXiv:1805.09817 (2018)","DOI":"10.1145\/3197517.3201323"},{"key":"34_CR26","unstructured":"Zhu, Y., et al.: Astra: general interactive world model with autoregressive denoising. arXiv preprint arXiv:2512.08931 (2025)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37029-7_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:49:30Z","timestamp":1789379370000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37029-7_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370280","9783032370297"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37029-7_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"15 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}