{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T12:10:16Z","timestamp":1789042216341,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":69,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370198","type":"print"},{"value":"9783032370204","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\/978-3-032-37020-4_12","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:22:53Z","timestamp":1789039373000},"page":"213-230","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Benchmark and\u00a0Multi-agent System for\u00a0Instruction-Driven Cinematic Video Compilation"],"prefix":"10.1007","author":[{"given":"Peixuan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hualuo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunjie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingqi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuchen","family":"Weng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Si","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boxin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"12_CR1","unstructured":"Claude-3.7-sonnet. https:\/\/claude.ai\/. Accessed 25 Feb 2025"},{"key":"12_CR2","unstructured":"Insightface. https:\/\/github.com\/deepinsight\/insightface\/"},{"key":"12_CR3","unstructured":"Tencent video. https:\/\/v.qq.com\/"},{"key":"12_CR4","unstructured":"TikTok short. https:\/\/www.tiktok.com\/"},{"key":"12_CR5","unstructured":"YouTube short. https:\/\/www.youtube.com\/shorts\/"},{"key":"12_CR6","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Argaw, D.M., et al.: Towards automated movie trailer generation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00711"},{"key":"12_CR8","unstructured":"Bain, M., Huh, J., Han, T., Zisserman, A.: WhisperX: time-accurate speech transcription of long-form audio. arXiv preprint arXiv:2303.00747"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Barua, A., Benharrak, K., Chen, M., Huh, M., Pavel, A.: Lotus: creating short videos from long videos with abstractive and extractive summarization. arXiv preprint arXiv:2502.07096 (2025)","DOI":"10.1145\/3708359.3712090"},{"key":"12_CR10","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"12_CR11","unstructured":"Cai, S., et\u00a0al.: Mixture of contexts for long video generation. arXiv preprint arXiv:2508.21058 (2025)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Chen, W., et al.: Beyond appearance: a semantic controllable self-supervised learning framework for human-centric visual tasks. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01445"},{"key":"12_CR13","unstructured":"Cui, C., et al.: PaddleOCR 3.0 technical report (2025). https:\/\/arxiv.org\/abs\/2507.05595"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Du, S., Bai, Y., Ma, J., Liu, M., Li, Y.: Frequency-decoupled learning for joint thin-cloud removal and pansharpening. In: ICASSP (2026)","DOI":"10.1109\/ICASSP55912.2026.11464322"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Du, S., et al.: Pansharpening for thin-cloud contaminated remote sensing images: a unified framework and benchmark dataset. In: AAAI (2026)","DOI":"10.1609\/aaai.v40i5.37369"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Du, S., et al.: Unsupervised hyperspectral image super-resolution via self-supervised modality decoupling. IJCV (2026)","DOI":"10.1007\/s11263-026-02757-8"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Gan, B., et al.: Collaborative noisy label cleaner: Learning scene-aware trailers for multi-modal highlight detection in movies. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01812"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Guo, Y., et al.: Long context tuning for video generation. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01605"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"12_CR20","unstructured":"Hong, S., et\u00a0al.: MetaGPT: meta programming for a multi-agent collaborative framework. In: ICLR (2023)"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Hu, P., Xiao, N., Li, F., Chen, Y., Huang, R.: A reinforcement learning-based automatic video editing method using pre-trained vision-language model. In: ACMMM (2023)","DOI":"10.1145\/3581783.3611878"},{"key":"12_CR22","unstructured":"Huang, K., et al.: CineScene: implicit 3D as effective scene representation for cinematic video generation. In: CVPR (2026)"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Huang, Z., et\u00a0al.: VBench: comprehensive benchmark suite for video generative models. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Huber, B., Shin, H.V., Russell, B., Wang, O., Mysore, G.J.: B-script: transcript-based B-roll video editing with recommendations. In: CHI (2019)","DOI":"10.1145\/3290605.3300311"},{"key":"12_CR25","unstructured":"Jia, W., et al.: MoGA: mixture-of-groups attention for end-to-end long video generation. arXiv preprint arXiv:2510.18692 (2025)"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Koorathota, S., Adelman, P., Cotton, K., Sajda, P.: Editing like humans: a contextual, multimodal framework for automated video editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1701\u20131709 (2021)","DOI":"10.1109\/CVPRW53098.2021.00186"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Landis, J.R., Koch, G.G.: The measurement of observer agreement for categorical data. biometrics (1977)","DOI":"10.2307\/2529310"},{"key":"12_CR28","unstructured":"Li, Y., et al.: Personalize your large vision-language models with in-context prompt tuning. arXiv preprint arXiv:2605.31513 (2026)"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, J., Shen, Z., Han, L., Xu, H., Tang, R.: CATP: contextually adaptive token pruning for efficient and enhanced multimodal in-context learning. In: AAAI (2026)","DOI":"10.1609\/aaai.v40i8.37592"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"12_CR31","unstructured":"Lu, J., Xiao, M., Wang, W., Du, Y., Wu, Z., Hua, C.: Multi-modal and metadata capture model for micro video popularity prediction. arXiv preprint arXiv:2502.17038 (2025)"},{"key":"12_CR32","unstructured":"Meng, Y., et\u00a0al.: Holocine: holistic generation of cinematic multi-shot long video narratives. In: CVPR (2026)"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Mun, J., Shin, M., Han, G., Lee, S., Ha, S., Lee, J., Kim, E.S.: Boundary-aware self-supervised learning for video scene segmentation. arXiv preprint arXiv:2201.05277 (2022)","DOI":"10.1007\/978-3-031-26316-3_29"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Pardo, A., Caba, F., Alc\u00e1zar, J.L., Thabet, A.K., Ghanem, B.: Learning to cut by watching movies. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00678"},{"key":"12_CR35","unstructured":"Pardo, A., Wang, J.H., Ghanem, B., Sivic, J., Russell, B., Heilbron, F.C.: Generative timelines for instructed visual assembly. arXiv preprint arXiv:2411.12293 (2024)"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Pavel, A., Reyes, G., Bigham, J.P.: Rescribe: authoring and automatically editing audio descriptions. In: Proceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology, pp. 747\u2013759 (2020)","DOI":"10.1145\/3379337.3415864"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Phung, Q., Mai, L., Heilbron, F.D.C., Liu, F., Huang, J.B., Ham, C.: CineVerse: consistent keyframe synthesis for cinematic scene composition. arXiv preprint arXiv:2504.19894 (2025)","DOI":"10.1109\/WACV61042.2026.00258"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Podlesnyy, S.: Towards data-driven automatic video editing. In: Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery, vol. 1, pp. 361\u2013368. Springer (2020)","DOI":"10.1007\/978-3-030-32456-8_39"},{"key":"12_CR39","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: ICML (2023)"},{"key":"12_CR40","doi-asserted-by":"crossref","unstructured":"Sandoval-Castaneda, M., Russell, B., Sivic, J., Shakhnarovich, G., Caba Heilbron, F.: EditDuet: a multi-agent system for video non-linear editing. In: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers (2025)","DOI":"10.1145\/3721238.3730761"},{"key":"12_CR41","unstructured":"Soe, T.H., Slavkovik, M.: AI video editing tools. Want and how far is AI from delivering them (2021)"},{"key":"12_CR42","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"12_CR43","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv:2302.13971 arXiv preprint (2023)"},{"key":"12_CR44","unstructured":"Touvron, H., et al.: LLaMA 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"12_CR45","doi-asserted-by":"crossref","unstructured":"Truong, A., Berthouzoz, F., Li, W., Agrawala, M.: QuickCut: an interactive tool for editing narrated video. In: Proceedings of the 29th Annual Symposium on User Interface Software and Technology, pp. 497\u2013507 (2016)","DOI":"10.1145\/2984511.2984569"},{"key":"12_CR46","doi-asserted-by":"crossref","unstructured":"Wagner, R.A., Fischer, M.J.: The string-to-string correction problem. JACM (1974)","DOI":"10.1145\/321796.321811"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"Wang, B., Li, Y., Lv, Z., Xia, H., Xu, Y., Sodhi, R.: LAVE: LLM-powered agent assistance and language augmentation for video editing. In: Proceedings of the 29th International Conference on Intelligent User Interfaces (2024)","DOI":"10.1145\/3640543.3645143"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Wespeaker: a research and production oriented speaker embedding learning toolkit. In: ICASSP (2023)","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"12_CR49","doi-asserted-by":"crossref","unstructured":"Wang, L., Liu, D., Puri, R., Metaxas, D.N.: Learning trailer moments in full-length movies with co-contrastive attention. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58523-5_18"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"Wang, M., Yang, G.W., Hu, S.M., Yau, S.T., Shamir, A., et al.: Write-a-video: computational video montage from themed text. ACM Trans. Graph (2019)","DOI":"10.1145\/3355089.3356520"},{"key":"12_CR51","doi-asserted-by":"crossref","unstructured":"Wang, X., et\u00a0al.: From long videos to engaging clips: a human-inspired video editing framework with multimodal narrative understanding. arXiv preprint arXiv:2507.02790 (2025)","DOI":"10.18653\/v1\/2025.emnlp-industry.185"},{"key":"12_CR52","doi-asserted-by":"crossref","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: NeurIPS (2022)","DOI":"10.52202\/068431-1800"},{"key":"12_CR53","doi-asserted-by":"crossref","unstructured":"Weng, S., Zhang, P., Chang, Z., Wang, X., Li, S., Shi, B.: Affective image filter: reflecting emotions from text to images. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00992"},{"key":"12_CR54","unstructured":"Wu, W., Zhu, Z., Shou, M.Z.: Automated movie generation via multi-agent cot planning. arXiv preprint arXiv:2503.07314 (2025)"},{"key":"12_CR55","unstructured":"Xiao, J., et al.: Captain cinema: towards short movie generation. In: ICLR (2025)"},{"key":"12_CR56","doi-asserted-by":"crossref","unstructured":"Xiao, X., et al.: Staying vigilant: mitigating visual laziness via counterfactual visual alignment in MLLMs. In: ECCV (2026)","DOI":"10.1007\/978-3-032-37232-1_16"},{"key":"12_CR57","doi-asserted-by":"crossref","unstructured":"Xiao, X., et al.: Visual instance-aware prompt tuning. In: ACMMM (2025)","DOI":"10.1145\/3746027.3754858"},{"key":"12_CR58","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Heilbron, F.C., Lin, D.: Transcript to video: efficient clip sequencing from texts. In: ACMMM (2022)","DOI":"10.1145\/3503161.3548268"},{"key":"12_CR59","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: FilmAgent: automating virtual film production through a multi-agent collaborative framework. In: SIGGRAPH Asia (2024)","DOI":"10.1145\/3681758.3698014"},{"key":"12_CR60","unstructured":"Zhang, L., et al.: Pretraining frame preservation in autoregressive video memory compression. arXiv preprint arXiv:2512.23851 (2025)"},{"key":"12_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, P., Jia, Z., Cai, Z., Weng, S., Li, S., Shi, B.: ReContraster: making your posters stand out with regional contrast. In: ACL (2026)","DOI":"10.18653\/v1\/2026.acl-long.98"},{"key":"12_CR62","unstructured":"Zhang, P., Jia, Z., Liu, K., Weng, S., Li, S., Shi, B.: STAGE: storyboard-anchored generation for cinematic multi-shot narrative. In: CVPR (2026)"},{"key":"12_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, P., Weng, S., Tang, J., Li, S., Shi, B.: Towards deeper emotional reflection: crafting affective image filters with generative priors. TPAMI (2025)","DOI":"10.1109\/TPAMI.2025.3643911"},{"key":"12_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: Affective image editing: shaping emotional factors via text descriptions. IJCV (2026)","DOI":"10.1007\/s11263-025-02678-y"},{"key":"12_CR65","unstructured":"Zhang, X., et\u00a0al.: How far are video models from true multimodal reasoning? arXiv preprint arXiv:2604.19193 (2026)"},{"key":"12_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sun, R., Chen, Y., Pfister, T., Zhang, R., Arik, S.: Chain of agents: large language models collaborating on long-context tasks. In: NeurIPS (2024)","DOI":"10.52202\/079017-4202"},{"key":"12_CR67","unstructured":"Zheng, M., et al.: VideoGen-of-thought: a collaborative framework for multi-shot video generation. In: NeurIPS NextVid Workshop Oral (2025)"},{"key":"12_CR68","unstructured":"Zhou, H., Huang, L., Wu, S., Xia, L., Huang, C., et\u00a0al.: VideoAgent: all-in-one agentic framework for video understanding and editing (2026)"},{"key":"12_CR69","doi-asserted-by":"crossref","unstructured":"Zhu, W., et al.: AutoShot: a short video dataset and state-of-the-art shot boundary detection. In: CVPR (2023)","DOI":"10.1109\/CVPRW59228.2023.00218"}],"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\/978-3-032-37020-4_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:23:25Z","timestamp":1789039405000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37020-4_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370198","9783032370204"],"references-count":69,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37020-4_12","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"}}]}}