{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T11:59:21Z","timestamp":1790855961592,"version":"4.1.0"},"publisher-location":"Cham","reference-count":67,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374639","type":"print"},{"value":"9783032374646","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\/978-3-032-37464-6_30","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:36:37Z","timestamp":1789036597000},"page":"557-575","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Vision-as-Inverse-Graphics Agent via\u00a0Interleaved Multimodal Reasoning"],"prefix":"10.1007","author":[{"given":"Shaofeng","family":"Yin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxin","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zora Zhiruo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael J.","family":"Black","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angjoo","family":"Kanazawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiwen","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"30_CR1","unstructured":"Aguina-Kang, R., et al.: Open-universe indoor scene generation using LLM program synthesis and uncurated object databases (2024). https:\/\/arxiv.org\/abs\/2403.09675"},{"key":"30_CR2","unstructured":"Anthropic: The complete guide to building skills for claude. Tech. rep., Anthropic (2026). https:\/\/resources.anthropic.com\/hubfs\/The-Complete-Guide-to-Building-Skill-for-Claude.pdf"},{"key":"30_CR3","unstructured":"Azam, R., Vempaty, A., Jagmohan, A.: Reflection-based memory for web navigation agents (2025). https:\/\/arxiv.org\/abs\/2506.02158"},{"key":"30_CR4","doi-asserted-by":"publisher","unstructured":"Bandyopadhyay, S., Maheshwari, H., Natarajan, A., Saxena, A.: Enhancing presentation slide generation by LLMs with a multi-staged end-to-end approach. In: Mahamood, S., Minh, N.L., Ippolito, D. (eds.) Proceedings of the 17th International Natural Language Generation Conference, pp. 222\u2013229. Association for Computational Linguistics, Tokyo, Japan (2024). https:\/\/doi.org\/10.18653\/v1\/2024.inlg-main.18","DOI":"10.18653\/v1\/2024.inlg-main.18"},{"key":"30_CR5","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. Seminal Graphics Papers: Pushing the Boundaries, vol. 2 (1999). https:\/\/api.semanticscholar.org\/CorpusID:203705211"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: SpatialVLM: endowing vision-language models with spatial reasoning capabilities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14455\u201314465 (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, A.C., et al.: SpatialRGPT: grounded spatial reasoning in vision-language models. In: NeurIPS (2024)","DOI":"10.52202\/079017-4293"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: ProcTHOR: large-scale embodied AI using procedural generation. In: NeurIPS (2022). outstanding Paper Award","DOI":"10.52202\/068431-0433"},{"key":"30_CR9","unstructured":"Dwedari, M.M., Niessner, M., Chen, Z.: Generating context-aware natural answers for questions in 3D scenes. In: Proceedings of the British Machine Vision Conference (BMVC), BMVA Press (2023)"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Feng, W., et al.: LayoutGPT: compositional visual planning and generation with large language models. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. NIPS \u201923 (2023)","DOI":"10.52202\/075280-0802"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Feng, Y., Feng, H., Black, M.J., Bolkart, T.: Learning an animatable detailed 3D face model from in-the-wild images. ACM Trans. Graph. (ToG), Proc. SIGGRAPH 40(4), 88:1\u201388:13 (2021)","DOI":"10.1145\/3450626.3459936"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Ge, J., Subramanian, S., Shi, B., Herzig, R., Darrell, T.: Recursive visual programming. In: European Conference on Computer Vision, pp. 1\u201318. Springer (2024)","DOI":"10.1007\/978-3-031-72775-7_1"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Ge, J., et al.: AutoPresent: designing structured visuals from scratch. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2902\u20132911 (2025)","DOI":"10.1109\/CVPR52734.2025.00276"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Gu, Y., Huang, I., Je, J., Yang, G., Guibas, L.: BlenderGYM: benchmarking foundational model systems for graphics editing. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 18574\u201318583 (2025)","DOI":"10.1109\/CVPR52734.2025.01731"},{"issue":"1\u20132","key":"30_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2500000010","volume":"4","author":"S Gulwani","year":"2017","unstructured":"Gulwani, S., Polozov, O., Singh, R.: Program synthesis. Found. Trends Program. Lang. 4(1\u20132), 1\u2013119 (2017). https:\/\/doi.org\/10.1561\/2500000010","journal-title":"Program synthesis. Found. Trends Program. Lang."},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, T., Kembhavi, A.: Visual programming: compositional visual reasoning without training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14953\u201314962 (2023)","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"30_CR17","doi-asserted-by":"publisher","unstructured":"He, J., Treude, C., Lo, D.: LLM-based multi-agent systems for software engineering: literature review, vision, and the road ahead. ACM Trans. Softw. Eng. Methodol. 34(5) (2025). https:\/\/doi.org\/10.1145\/3712003","DOI":"10.1145\/3712003"},{"key":"30_CR18","unstructured":"Hong, K., Troynikov, A., Huber, J.: Context Rot: how increasing input tokens impacts LLM performance. Tech. rep., Chroma (2025). https:\/\/research.trychroma.com\/context-rot, published July 2025"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Hong, Y.,et al.: 3DLLM: injecting the 3D world into large language models. In: Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a036, pp. 20482\u201320494. Curran Associates, Inc. (2023)","DOI":"10.52202\/075280-0900"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: Visual program distillation: distilling tools and programmatic reasoning into vision-language models (2023)","DOI":"10.1109\/CVPR52733.2024.00916"},{"key":"30_CR21","unstructured":"Hu, Z., et al.: SceneCraft: an LLM agent for synthesizing 3D scenes as blender code. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Huang, I., Yang, G., Guibas, L.: Blenderalchemy: editing 3D graphics with vision-language models. In: European Conference on Computer Vision, pp. 297\u2013314. Springer (2024)","DOI":"10.1007\/978-3-031-73024-5_18"},{"key":"30_CR23","doi-asserted-by":"publisher","unstructured":"Kodnongbua, M., Jones, B., Ahmad, M.B.S., Kim, V., Schulz, A.: ReparamCAD: zero-shot cad re-parameterization for interactive manipulation. In: ACM SIGGRAPH Asia 2023 Conference Papers. ACM, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3610548.3618219","DOI":"10.1145\/3610548.3618219"},{"key":"30_CR24","unstructured":"Koh, J.Yet al.: VisualWebArena: evaluating multimodal agents on realistic visual web tasks. In: ICLR 2024 Workshop on Large Language Model (LLM) Agents (2024). https:\/\/openreview.net\/forum?id=RPKxrKTJbj"},{"key":"30_CR25","unstructured":"Kulits, P., Feng, H., Liu, W., Abrevaya, V.F., Black, M.J.: Re-thinking inverse graphics with large language models. Trans. Mach. Learn. Res. (2024)"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Kulkarni, T.D., Kohli, P., Tenenbaum, J.B., Mansinghka, V.: Picture: a probabilistic programming language for scene perception. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society (2015)","DOI":"10.1109\/CVPR.2015.7299068"},{"key":"30_CR27","unstructured":"Ling, L., et al.: SceneThesis: a language and vision agentic framework for 3D scene generation. arXiv preprint arXiv:2505.02836 (2025)"},{"key":"30_CR28","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1162\/tacl_a_00638","volume":"12","author":"NF Liu","year":"2024","unstructured":"Liu, N.F., et al.: Lost in the middle: how language models use long contexts. Trans. Assoc. Comput. Ling. 12, 157\u2013173 (2024). https:\/\/doi.org\/10.1162\/tacl_a_00638","journal-title":"Trans. Assoc. Comput. Ling."},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Liu, S., Li, T., Chen, W., Li, H.: Soft rasterizer: a differentiable renderer for image-based 3D reasoning. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7707\u20137716 (2019). https:\/\/api.semanticscholar.org\/CorpusID:102484000","DOI":"10.1109\/ICCV.2019.00780"},{"key":"30_CR30","doi-asserted-by":"crossref","unstructured":"Loper, M., Black, M.J.: OpenDR: an approximate differentiable renderer. In: European Conference on Computer Vision (2014). https:\/\/api.semanticscholar.org\/CorpusID:17868098","DOI":"10.1007\/978-3-319-10584-0_11"},{"key":"30_CR31","unstructured":"Meshy: Meshy: Fast 3D generative AI. https:\/\/www.meshy.ai\/ (2024)"},{"key":"30_CR32","doi-asserted-by":"publisher","unstructured":"\u00d6cal, B.M., Tatarchenko, M., Karao\u011flu, S., Gevers, T.: SceneTeller: language-to-3D scene generation. In: Computer Vision \u2013 ECCV 2024: 18th European Conference, Milan, Italy, September 29\u2013October 4, 2024, Proceedings, Part LXXXV, pp. 362\u2013378 (2024). https:\/\/doi.org\/10.1007\/978-3-031-73013-9_21","DOI":"10.1007\/978-3-031-73013-9_21"},{"key":"30_CR33","doi-asserted-by":"crossref","unstructured":"Qin, Y., Xu, Z., Liu, Y.: Apply hierarchical-chain-of-generation to complex attributes text-to-3D generation. 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18521\u201318530 (2025). https:\/\/api.semanticscholar.org\/CorpusID:278481349","DOI":"10.1109\/CVPR52734.2025.01726"},{"key":"30_CR34","unstructured":"Qin, Y., et\u00a0al.: UI-TARS: pioneering automated GUI interaction with native agents. arXiv preprint arXiv:2501.12326 (2025)"},{"key":"30_CR35","doi-asserted-by":"crossref","unstructured":"Raistrick, A., et al.: Infinite photorealistic worlds using procedural generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12630\u201312641 (2023)","DOI":"10.1109\/CVPR52729.2023.01215"},{"key":"30_CR36","doi-asserted-by":"crossref","unstructured":"Raistrick, A., et al.: InfiniGen Indoors: photorealistic indoor scenes using procedural generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21783\u201321794 (2024)","DOI":"10.1109\/CVPR52733.2024.02058"},{"key":"30_CR37","doi-asserted-by":"crossref","unstructured":"Ritchie, D., et al.: Neurosymbolic models for computer graphics. Comput. Graph. Forum 42(2), 545\u2013568 (2023). https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1111\/cgf.14775","DOI":"10.1111\/cgf.14775"},{"key":"30_CR38","unstructured":"Roberts, L.G.: Machine Perception of Three-Dimensional Solids, Cambridge, Massachusetts, USA (1963). Ph.D. thesis"},{"key":"30_CR39","doi-asserted-by":"crossref","unstructured":"Subramanian, S., et al.: Modular visual question answering via code generation (2023). arXiv:2306.05392 arXiv preprint","DOI":"10.18653\/v1\/2023.acl-short.65"},{"key":"30_CR40","doi-asserted-by":"crossref","unstructured":"Sun, C., Han, J., Deng, W., Wang, X., Qin, Z., Gould, S.: 3D-GPT: procedural 3D modeling with large language models. In: 2025 International Conference on 3D Vision (3DV), pp. 1253\u20131263. IEEE (2025)","DOI":"10.1109\/3DV66043.2025.00119"},{"key":"30_CR41","doi-asserted-by":"crossref","unstructured":"Sun, F.Y., et al.: LayoutVLM: differentiable optimization of 3D layout via vision-language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 29469\u201329478 (2025)","DOI":"10.1109\/CVPR52734.2025.02744"},{"key":"30_CR42","doi-asserted-by":"crossref","unstructured":"Sun, F.Y., et al.: 3D-generalist: self-improving vision-language-action models for crafting 3D worlds (2025). https:\/\/arxiv.org\/abs\/2507.06484","DOI":"10.1109\/3DV69130.2026.00177"},{"key":"30_CR43","doi-asserted-by":"crossref","unstructured":"Sur\u00eds, D., Menon, S., Vondrick, C.: ViperGPT: visual inference via python execution for reasoning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11888\u201311898 (2023)","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"30_CR44","doi-asserted-by":"crossref","unstructured":"Suzgun, M., Yuksekgonul, M., Bianchi, F., Jurafsky, D., Zou, J.: Dynamic cheatSheet: test-time learning with adaptive memory (2025). arXiv:2504.07952 arXiv preprint","DOI":"10.18653\/v1\/2026.eacl-long.333"},{"key":"30_CR45","doi-asserted-by":"crossref","unstructured":"Tang, W., et al.: SlideCoder: layout-aware rag-enhanced hierarchical slide generation from design (2025). https:\/\/arxiv.org\/abs\/2506.07964","DOI":"10.18653\/v1\/2025.emnlp-main.458"},{"key":"30_CR46","doi-asserted-by":"crossref","unstructured":"Tawosi, V., Ramani, K., Alamir, S., Liu, X.: ALMAS: an autonomous LLM-based multi-agent software engineering framework (2025). https:\/\/arxiv.org\/abs\/2510.03463","DOI":"10.1109\/ASEW67777.2025.00059"},{"key":"30_CR47","unstructured":"Team, S.D., et al.: SAM 3D: 3Dfy anything in images. arXiv preprint arXiv:2511.16624v1 (2025). https:\/\/arxiv.org\/abs\/2511.16624v1, version 1. submitted 20 Nov 2025"},{"key":"30_CR48","unstructured":"Tripo AI: Tripo: AI 3D model generator. https:\/\/www.tripo3d.ai\/ (2024)"},{"key":"30_CR49","doi-asserted-by":"publisher","unstructured":"Wang, F., et al.: SVGEN: interpretable vector graphics generation with large language models. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 9608\u20139617. MM \u201925, Association for Computing Machinery, New York, NY, USA (2025). https:\/\/doi.org\/10.1145\/3746027.3755011","DOI":"10.1145\/3746027.3755011"},{"key":"30_CR50","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Is a picture worth a thousand words? Delving into spatial reasoning for vision language models. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. NIPS \u201924 (2024)","DOI":"10.52202\/079017-2400"},{"key":"30_CR51","unstructured":"Wang, Z.Z., Mao, J., Fried, D., Neubig, G.: Agent workflow memory. In: Forty-second International Conference on Machine Learning (2025). https:\/\/openreview.net\/forum?id=NTAhi2JEEE"},{"key":"30_CR52","doi-asserted-by":"crossref","unstructured":"Wu, J., Tenenbaum, J.B., Kohli, P.: Neural scene de-rendering. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.744"},{"key":"30_CR53","doi-asserted-by":"crossref","unstructured":"Wu, R., Su, W., Liao, J.: Chat2SVG: vector graphics generation with large language models and image diffusion models. 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 23690\u201323700 (2024). https:\/\/api.semanticscholar.org\/CorpusID:274280554","DOI":"10.1109\/CVPR52734.2025.02206"},{"key":"30_CR54","doi-asserted-by":"crossref","unstructured":"Xie, T., et al.: OSWorld: benchmarking multimodal agents for open-ended tasks in real computer environments. In: The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2024). https:\/\/openreview.net\/forum?id=tN61DTr4Ed","DOI":"10.52202\/079017-1650"},{"key":"30_CR55","doi-asserted-by":"crossref","unstructured":"Xing, X., Hu, J., Liang, G., Zhang, J., Xu, D., Yu, Q.: Empowering LLMs to understand and generate complex vector graphics (2024). arXiv:2412.11102 arXiv preprint","DOI":"10.1109\/CVPR52734.2025.01815"},{"key":"30_CR56","doi-asserted-by":"crossref","unstructured":"Xu, W., Liang, Z., Mei, K., Gao, H., Tan, J., Zhang, Y.: A-MEM: agentic memory for LLM agents. In: Advances in Neural Information Processing Systems, (2025)","DOI":"10.52202\/085713-0593"},{"key":"30_CR57","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: ULIP: learning a unified representation of language, images, and point clouds for 3D understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1179\u20131189. IEEE Computer Society (2023)","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"30_CR58","doi-asserted-by":"publisher","first-page":"50528","DOI":"10.52202\/079017-1601","volume":"37","author":"J Yang","year":"2024","unstructured":"Yang, J., et al.: SWE-Agent: agent-computer interfaces enable automated software engineering. Adv. Neural. Inf. Process. Syst. 37, 50528\u201350652 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"30_CR59","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: OmniSVG: a unified scalable vector graphics generation model (2025). arXiv:2504.06263 arXiv preprint","DOI":"10.52202\/085713-3791"},{"key":"30_CR60","doi-asserted-by":"publisher","first-page":"20744","DOI":"10.52202\/068431-1508","volume":"35","author":"S Yao","year":"2022","unstructured":"Yao, S., Chen, H., Yang, J., Narasimhan, K.: WebShop: towards scalable real-world web interaction with grounded language agents. Adv. Neural. Inf. Process. Syst. 35, 20744\u201320757 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"30_CR61","unstructured":"Ye, Y.: Task memory engine: Spatial memory for robust multi-step LLM agents (2025). https:\/\/arxiv.org\/abs\/2505.19436"},{"key":"30_CR62","unstructured":"Yi, K., Wu, J., Gan, C., Torralba, A., Kohli, P., Tenenbaum, J.: Neural-symbolic VQA: disentangling reasoning from vision and language understanding. In: Advances in Neural Information Processing Systems (NeurIPS) 31, pp. 1039\u20131050 (2018)"},{"key":"30_CR63","unstructured":"Zhang, H., et al.: Building cooperative embodied agents modularly with large language models. arXiv preprint arXiv:2307.02485 (2023)"},{"key":"30_CR64","unstructured":"Zhang, Q., et al.: Agentic context engineering: evolving contexts for self-improving language models (2025). arXiv:2510.04618 arXiv preprint"},{"key":"30_CR65","doi-asserted-by":"crossref","unstructured":"Zheng, H., et al.: PPTAgent: generating and evaluating presentations beyond text-to-slides. arXiv preprint arXiv:2501.03936 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.728"},{"key":"30_CR66","doi-asserted-by":"publisher","unstructured":"Zhou, M., et al.: SceneX: procedural controllable large-scale scene generation. In: Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteenth Symposium on Educational Advances in Artificial Intelligence. AAAI\u201925\/IAAI\u201925\/EAAI\u201925, AAAI Press (2025). https:\/\/doi.org\/10.1609\/aaai.v39i10.33174","DOI":"10.1609\/aaai.v39i10.33174"},{"key":"30_CR67","unstructured":"Zhou, S., et\u00a0al.: WebArena: a realistic web environment for building autonomous agents. arXiv preprint arXiv:2307.13854 (2023)"}],"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\/978-3-032-37464-6_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:36:59Z","timestamp":1789036619000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37464-6_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374639","9783032374646"],"references-count":67,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37464-6_30","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"}}]}}