{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:06:05Z","timestamp":1789034765113,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370129","type":"print"},{"value":"9783032370136","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\/978-3-032-37013-6_15","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:06:29Z","timestamp":1789031189000},"page":"262-280","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Natural Language Camera Movement Understanding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2417-2955","authenticated-orcid":false,"given":"Yuwen","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9427-1955","authenticated-orcid":false,"given":"Joey","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1803-7077","authenticated-orcid":false,"given":"Jin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1525-3942","authenticated-orcid":false,"given":"Haoxiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3915-5977","authenticated-orcid":false,"given":"Boqing","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Bai, J., et\u00a0al.: RECAMMASTER: camera-controlled generative rendering from a single video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14834\u201314844 (2025)","DOI":"10.1109\/ICCV51701.2025.01376"},{"key":"15_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"15_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"15_CR4","unstructured":"Bordwell, D., Thompson, K., Smith, J.: Film Art: An Introduction, vol. 7, McGraw-Hill, New York (2008)"},{"key":"15_CR5","unstructured":"Brooks, T., et al.: Video generation models as world simulators (2024). https:\/\/openai.com\/research\/video-generation-models-as-world-simulators. Accessed 29 June 2026"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Brown, B.: Cinematography: Theory and Practice: Image Making for Cinematographers and Directors. Routledge (2016)","DOI":"10.4324\/9781315667829"},{"key":"15_CR7","unstructured":"Du, Y., et al.: MotionSight: boosting fine-grained motion understanding in multimodal LLMS. arXiv preprint arXiv:2506.01674 (2025)"},{"key":"15_CR8","unstructured":"Fan, Z., et\u00a0al.: VLM-3R: vision-language models augmented with instruction-aligned 3D reconstruction. arXiv preprint arXiv:2505.20279 (2025)"},{"key":"15_CR9","unstructured":"Google: VEO (2024). https:\/\/deepmind.google\/models\/veo\/. Accessed 29 June 2026"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Hong, W., et al.: MotionBench: benchmarking and improving fine-grained video motion understanding for vision language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 8450\u20138460 (2025)","DOI":"10.1109\/CVPR52734.2025.00791"},{"key":"15_CR11","unstructured":"Hu, W., et al.: G$$^2$$ VLM: geometry grounded vision language model with unified 3D reconstruction and spatial reasoning. arXiv preprint arXiv:2511.21688 (2025)"},{"key":"15_CR12","unstructured":"Huang, J., et al.: VIPE: Video pose engine for 3D geometric perception. arXiv preprint arXiv:2508.10934 (2025)"},{"key":"15_CR13","doi-asserted-by":"publisher","unstructured":"Huang, Q., Xiong, Y., Rao, A., Wang, J., Lin, D.: MovieNet: a holistic dataset for movie understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds.) European Conference on Computer Vision, pp. 709\u2013727. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_41","DOI":"10.1007\/978-3-030-58548-8_41"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Jia, Z., et al.: VQA2: visual question answering for video quality assessment. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 6751\u20136760 (2025)","DOI":"10.1145\/3746027.3754696"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Keating, P.: The Dynamic Frame: Camera Movement in Classical Hollywood. Columbia University Press (2019)","DOI":"10.7312\/keat19050"},{"key":"15_CR16","unstructured":"Kong, W., et\u00a0al.: HunyuanVideo: a systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Kuaishou: Kling (2024). https:\/\/kling.ai\/. Accessed 29 June 2026","DOI":"10.5771\/2941-0371-2026-2-29"},{"key":"15_CR18","unstructured":"Li, B., et al.: LLaVA-OneVision: easy visual task transfer. Trans. Mach. Learn. Res. (2025). https:\/\/openreview.net\/forum?id=zKv8qULV6n"},{"key":"15_CR19","unstructured":"Li, X., et\u00a0al.: Can video generation replace cinematographers? Research on the cinematic language of generated video. arXiv preprint arXiv:2412.12223 (2024)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: MEGASAM: accurate, fast and robust structure and motion from casual dynamic videos. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10486\u201310496 (2025)","DOI":"10.1109\/CVPR52734.2025.00981"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Lin, Z., et\u00a0al.: Towards understanding camera motions in any video. arXiv preprint arXiv:2504.15376 (2025)","DOI":"10.52202\/085713-4477"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Liu, H., et\u00a0al.: ShotBench: expert-level cinematic understanding in vision-language models. arXiv preprint arXiv:2506.21356 (2025)","DOI":"10.52202\/085713-4329"},{"key":"15_CR23","unstructured":"MiniMax: Hailuo (2024). https:\/\/hailuoai.video\/. Accessed 29 June 2026"},{"key":"15_CR24","unstructured":"Mou, Z., Xia, B., Huang, Z., Yang, W., Jia, J.: GRADEO: towards human-like evaluation for text-to-video generation via multi-step reasoning. arXiv preprint arXiv:2503.02341 (2025)"},{"key":"15_CR25","unstructured":"Nielsen, J.I., Kau, E., Raskin, R.: Camera movement in narrative cinema: towards a taxonomy of functions. University of Aarhus, Department of Inf. & Media Studies (2007)"},{"key":"15_CR26","unstructured":"OpenAI: GPT-4O system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"15_CR27","doi-asserted-by":"publisher","unstructured":"Pan, L., Bar\u00e1th, D., Pollefeys, M., Sch\u00f6nberger, J.L.: Global structure-from-motion revisited. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference on Computer Vision, pp. 58\u201377. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-73661-2_4","DOI":"10.1007\/978-3-031-73661-2_4"},{"key":"15_CR28","doi-asserted-by":"publisher","unstructured":"Rao, A., Wang, J., Xu, L., Jiang, X., Huang, Q., Zhou, B., Lin, D.: A unified framework for shot type classification based on subject centric lens. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds.) European Conference on Computer Vision, pp. 17\u201334. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_2","DOI":"10.1007\/978-3-030-58621-8_2"},{"key":"15_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2023.109627","volume":"51","author":"M Savardi","year":"2023","unstructured":"Savardi, M., Kov\u00e1cs, A.B., Signoroni, A., Benini, S.: CineScale2: a dataset of cinematic camera features in movies. Data Brief 51, 109627 (2023)","journal-title":"Data Brief"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"15_CR31","unstructured":"Singh, A., et\u00a0al.: OpenAI GPT-5 system card. arXiv preprint arXiv:2601.03267 (2025)"},{"key":"15_CR32","unstructured":"Spottiswoode, R.: A Grammar of the Film: An Analysis of Film Technique. Univ of California Press (1969)"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Sun, K., et al.: T2V-CompBench: a comprehensive benchmark for compositional text-to-video generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 8406\u20138416 (2025)","DOI":"10.1109\/CVPR52734.2025.00787"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Tang, Y., et\u00a0al.: VidComposition: can MLLMS analyze compositions in compiled videos? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8490\u20138500 (2025)","DOI":"10.1109\/CVPR52734.2025.00794"},{"key":"15_CR35","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Tu, C., et al.: Favor-bench: a comprehensive benchmark for fine-grained video motion understanding. arXiv preprint arXiv:2503.14935 (2025)","DOI":"10.52202\/085713-4791"},{"key":"15_CR37","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"15_CR38","unstructured":"Wang, J., et al.: SpatialVID: a large-scale video dataset with spatial annotations. arXiv preprint arXiv:2509.09676 (2025)"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual geometry grounded transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"15_CR40","unstructured":"Wang, J., et\u00a0al.: Love: benchmarking and evaluating text-to-video generation and video-to-text interpretation. arXiv preprint arXiv:2505.12098 (2025)"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, Y., Holynski, A., Efros, A.A., Kanazawa, A.: Continuous 3D perception model with persistent state. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10510\u201310522 (2025)","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"15_CR42","unstructured":"Wang, W., et al.: InternVL3. 5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: CinetechBench: a benchmark for cinematographic technique understanding and generation. arXiv preprint arXiv:2505.15145 (2025)","DOI":"10.52202\/085713-1810"},{"key":"15_CR44","unstructured":"Wang, Y., et\u00a0al.: InternVideo2. 5: empowering video MLLMS with long and rich context modeling. arXiv preprint arXiv:2501.12386 (2025)"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Wu, D., Liu, F., Hung, Y.H., Duan, Y.: Spatial-MLLM: boosting MLLM capabilities in visual-based spatial intelligence. arXiv preprint arXiv:2505.23747 (2025)","DOI":"10.52202\/085713-0457"},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Wu, H., Cai, Y., Ge, H., Chen, H., Yang, M.H., Wang, Y.: RefineShot: rethinking cinematography understanding with foundational skill evaluation. arXiv preprint arXiv:2510.02423 (2025)","DOI":"10.36227\/techrxiv.176107519.98547757\/v1"},{"key":"15_CR47","unstructured":"Wu, H., et al.: CamReasoner: reinforcing camera movement understanding via structured spatial reasoning. arXiv preprint arXiv:2602.00181 (2026)"},{"key":"15_CR48","unstructured":"Yang, Z., et\u00a0al.: CogVideox: text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)"},{"key":"15_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, M., Wu, T., Tan, J., Liu, Z., Wetzstein, G., Lin, D.: GenDOP: auto-regressive camera trajectory generation as a director of photography. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18229\u201318239 (2025)","DOI":"10.1109\/ICCV51701.2025.01694"},{"key":"15_CR50","unstructured":"Zhu, J., et al.: InternVL3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (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\/978-3-032-37013-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:06:50Z","timestamp":1789031210000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37013-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370129","9783032370136"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37013-6_15","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":"11 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"}}]}}