{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T10:08:29Z","timestamp":1789380509918,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":64,"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_24","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:49:48Z","timestamp":1789379388000},"page":"390-409","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Error-Driven Scene Editing for\u00a03D Grounding in\u00a0Large Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2153-6536","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9502-050X","authenticated-orcid":false,"given":"Zun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1303-8636","authenticated-orcid":false,"given":"Han","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8807-2644","authenticated-orcid":false,"given":"Jialu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0297-7889","authenticated-orcid":false,"given":"Jianing","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonatan","family":"Bitton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Idan","family":"Szpektor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2965-5354","authenticated-orcid":false,"given":"Mohit","family":"Bansal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"24_CR1","unstructured":"An, S., Ma, Z., Lin, Z., Zheng, N., Lou, J.G., Chen, W.: Learning from mistakes makes LLM better reasoner. arXiv:2310.20689 arXiv preprint (2023)"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Azuma, D., Miyanishi, T., Kurita, S., Kawanabe, M.: Scanqa: 3d question answering for spatial scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19129\u201319139 (2022)","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Cai, D., Zhao, L., Zhang, J., Sheng, L., Xu, D.: 3djcg: a unified framework for joint dense captioning and visual grounding on 3d point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16464\u201316473 (2022)","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Cai, D., Zhao, L., Zhang, J., Sheng, L., Xu, D.: 3djcg: a unified framework for joint dense captioning and visual grounding on 3d point clouds. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16443\u201316452 (2022). https:\/\/api.semanticscholar.org\/CorpusID:250980730","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Chang, A.X., Nie\u00dfner, M.: Scanrefer: 3d object localization in RGB-d scans using natural language. In: European Conference on Computer Vision, pp. 202\u2013221. Springer (2020)","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"24_CR6","unstructured":"Chen, D.Z., Wu, Q., Nie\u00dfner, M., Chang, A.X.: D3net: a speaker-listener architecture for semi-supervised dense captioning and visual grounding in RGB-d scans. ArXiv abs\/2112.01551 (2021). https:\/\/api.semanticscholar.org\/CorpusID:244896259"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Chen, L., Yan, X., Xiao, J., Zhang, H., Pu, S., Zhuang, Y.: Counterfactual samples synthesizing for robust visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10800\u201310809 (2020)","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Ll3da: visual interactive instruction tuning for omni-3d understanding reasoning and planning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26428\u201326438 (2024)","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"24_CR9","unstructured":"Chen, Y., et al.: Grounded 3d-LLM with referent tokens. arXiv:2405.10370 arXiv preprint (2024)"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Z., Gholami, A., Nie\u00dfner, M., Chang, A.X.: Scan2cap: context-aware dense captioning in RGB-d scans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3193\u20133203 (2021)","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"24_CR11","doi-asserted-by":"publisher","first-page":"135062","DOI":"10.52202\/079017-4293","volume":"37","author":"AC Cheng","year":"2024","unstructured":"Cheng, A.C., et al.: Spatialrgpt: grounded spatial reasoning in vision-language models. Adv. Neural. Inf. Process. Syst. 37, 135062\u2013135093 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., He, T., Jiang, L., Wang, T., Dayoub, F., Reid, I.: 3d-LLAVA: towards generalist 3d LMMS with omni superpoint transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 3772\u20133782 (2025)","DOI":"10.1109\/CVPR52734.2025.00357"},{"key":"24_CR13","unstructured":"Duan, J., et al.: Aha: a vision-language-model for detecting and reasoning over failures in robotic manipulation. arXiv:2410.00371 arXiv preprint (2024)"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Fu, R., Liu, J., Chen, X., Nie, Y., Xiong, W.: Scene-LLM: extending language model for 3d visual understanding and reasoning. arXiv:2403.11401 arXiv preprint (2024)","DOI":"10.1109\/WACV61041.2025.00220"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Fu, T.J., Wang, X.E., Peterson, M.F., Grafton, S.T., Eckstein, M.P., Wang, W.Y.: Counterfactual vision-and-language navigation via adversarial path sampler. In: European Conference on Computer Vision, pp. 71\u201386. Springer (2020)","DOI":"10.1007\/978-3-030-58539-6_5"},{"key":"24_CR16","unstructured":"Gardner, M., et al.: Evaluating models\u2019 local decision boundaries via contrast sets. arXiv:2004.02709 arXiv preprint (2020)"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Haque, A., Tancik, M., Efros, A.A., Holynski, A., Kanazawa, A.: Instruct-nerf2nerf: editing 3d scenes with instructions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19740\u201319750 (2023)","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"24_CR18","doi-asserted-by":"publisher","first-page":"20482","DOI":"10.52202\/075280-0900","volume":"36","author":"Y Hong","year":"2023","unstructured":"Hong, Y., et al.: 3d-LLM: injecting the 3d world into large language models. Adv. Neural. Inf. Process. Syst. 36, 20482\u201320494 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Hu, W., et al.: 3dllm-mem: long-term spatial-temporal memory for embodied 3d large language model. arXiv:2505.22657 arXiv preprint (2025)","DOI":"10.52202\/085713-2278"},{"key":"24_CR20","first-page":"67856","volume":"38","author":"W Hu","year":"2026","unstructured":"Hu, W., et al.: 3dllm-mem: Long-term spatial-temporal memory for embodied 3d large language model. Adv. Neural. Inf. Process. Syst. 38, 67856\u201367884 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR21","doi-asserted-by":"publisher","first-page":"113991","DOI":"10.52202\/079017-3620","volume":"37","author":"H Huang","year":"2024","unstructured":"Huang, H., et al.: Chat-scene: bridging 3d scene and large language models with object identifiers. Adv. Neural. Inf. Process. Syst. 37, 113991\u2013114017 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: Unveiling the mist over 3d vision-language understanding: object-centric evaluation with chain-of-analysis. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 24570\u201324581 (2025)","DOI":"10.1109\/CVPR52734.2025.02288"},{"key":"24_CR23","unstructured":"Huang, J., et al.: An embodied generalist agent in 3d world. arXiv preprint arXiv:2311.12871 (2023)"},{"key":"24_CR24","unstructured":"Huang, T., Zhang, Z., Tang, H.: 3d-r1: enhancing reasoning in 3d VLMs for unified scene understanding. arXiv preprint arXiv:2507.23478 (2025)"},{"key":"24_CR25","unstructured":"Kaushik, D., Hovy, E., Lipton, Z.C.: Learning the difference that makes a difference with counterfactually-augmented data. arXiv:1909.12434 arXiv preprint (2019)"},{"key":"24_CR26","unstructured":"Khan, Z., Stengel-Eskin, E., Cho, J., Bansal, M.: Dataenvgym: data generation agents in teacher environments with student feedback. ArXiv abs\/2410.06215 (2024). https:\/\/api.semanticscholar.org\/CorpusID:273228651"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Lai, C., Song, S., Yan, S., Hu, G.: Improving vision and language concepts understanding with multimodal counterfactual samples. In: European Conference on Computer Vision, pp. 174\u2013191. Springer (2024)","DOI":"10.1007\/978-3-031-72890-7_11"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Lee, D.I., et al.: Editsplat: multi-view fusion and attention-guided optimization for view-consistent 3d scene editing with 3d gaussian splatting. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 11135\u201311145 (2025)","DOI":"10.1109\/CVPR52734.2025.01040"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Li, J., Tan, H., Bansal, M.: Envedit: environment editing for vision-and-language navigation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 15386\u201315396 (2022). https:\/\/api.semanticscholar.org\/CorpusID:247778977","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Li, R., Li, S., Kong, L., Yang, X., Liang, J.: Seeground: see and ground for zero-shot open-vocabulary 3d visual grounding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 3707\u20133717 (2025)","DOI":"10.1109\/CVPR52734.2025.00351"},{"key":"24_CR31","doi-asserted-by":"publisher","first-page":"140903","DOI":"10.52202\/079017-4473","volume":"37","author":"X Linghu","year":"2024","unstructured":"Linghu, X., Huang, J., Niu, X., Ma, X.S., Jia, B., Huang, S.: Multi-modal situated reasoning in 3d scenes. Adv. Neural. Inf. Process. Syst. 37, 140903\u2013140936 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR32","unstructured":"Ma, X., et\u00a0al.: When LLMs step into the 3d world: s survey and meta-analysis of 3d tasks via multi-modal large language models. arXiv preprint arXiv:2405.10255 (2024)"},{"key":"24_CR33","unstructured":"Ma, X., et al.: Sqa3d: situated question answering in 3d scenes. arXiv preprint arXiv:2210.07474 (2022)"},{"key":"24_CR34","unstructured":"Maudslay, R.H., Gonen, H., Cotterell, R., Teufel, S.: It\u2019s all in the name: mitigating gender bias with name-based counterfactual data substitution. arXiv:1909.00871 arXiv preprint (2019)"},{"key":"24_CR35","doi-asserted-by":"publisher","first-page":"133207","DOI":"10.52202\/079017-4233","volume":"37","author":"T Melistas","year":"2024","unstructured":"Melistas, T., et al.: Benchmarking counterfactual image generation. Adv. Neural. Inf. Process. Syst. 37, 133207\u2013133230 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR36","first-page":"5296","volume":"33","author":"A Parvaneh","year":"2020","unstructured":"Parvaneh, A., Abbasnejad, E., Teney, D., Shi, J.Q., Van den Hengel, A.: Counterfactual vision-and-language navigation: unravelling the unseen. Adv. Neural. Inf. Process. Syst. 33, 5296\u20135307 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR37","unstructured":"Sauer, A., Geiger, A.: Counterfactual generative networks. arXiv:2101.06046 arXiv preprint (2021)"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Schult, J., Engelmann, F., Hermans, A., Litany, O., Tang, S., Leibe, B.: Mask3d: mask transformer for 3d semantic instance segmentation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA) pp. 8216\u20138223 (2022). https:\/\/api.semanticscholar.org\/CorpusID:258079403","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"24_CR39","unstructured":"Song, L., Wang, G., Liu, J., Fu, Z., Miao, Y.: Sc-nerf: self-correcting neural radiance field with sparse views. arXiv:2309.05028 arXiv preprint (2023)"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Teney, D., Abbasnedjad, E., van\u00a0den Hengel, A.: Learning what makes a difference from counterfactual examples and gradient supervision. In: European Conference on Computer Vision, pp. 580\u2013599. Springer (2020)","DOI":"10.1007\/978-3-030-58607-2_34"},{"key":"24_CR41","doi-asserted-by":"crossref","unstructured":"Uwaeze, J., Kulkarni, P., Braverman, V., Jacobs, M.A., Parekh, V.S.: Generative counterfactual augmentation for bias mitigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1153\u20131160 (2025)","DOI":"10.1109\/ICCVW69036.2025.00125"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Wang, D., Li, L.: Learning from mistakes via cooperative study assistant for large language models. arXiv:2305.13829 arXiv preprint (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.659"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Wang, H., Liang, W., Shen, J., Van\u00a0Gool, L., Wang, W.: Counterfactual cycle-consistent learning for instruction following and generation in vision-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15471\u201315481 (2022)","DOI":"10.1109\/CVPR52688.2022.01503"},{"key":"24_CR44","doi-asserted-by":"crossref","unstructured":"Wang, S., Huang, L.: Targeted augmentation for low-resource event extraction. arXiv:2405.08729 arXiv preprint (2024)","DOI":"10.18653\/v1\/2024.findings-naacl.275"},{"key":"24_CR45","unstructured":"Wang, Z., Huang, H., Zhao, Y., Zhang, Z., Zhao, Z.: Chat-3d: data-efficiently tuning large language model for universal dialogue of 3d scenes. arXiv preprint arXiv:2308.08769 (2023)"},{"key":"24_CR46","doi-asserted-by":"crossref","unstructured":"Wen, M., Wu, S., Wang, K., Liang, D.: Intergsedit: interactive 3d gaussian splatting editing with 3d geometry-consistent attention prior. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 26136\u201326145 (2025)","DOI":"10.1109\/ICCV51701.2025.02425"},{"key":"24_CR47","doi-asserted-by":"crossref","unstructured":"Xu, R., Wang, X., Wang, T., Chen, Y., Pang, J., Lin, D.: Pointllm: empowering large language models to understand point clouds. In: European Conference on Computer Vision, pp. 131\u2013147. Springer (2024)","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"24_CR48","unstructured":"Yan, Z., et al.: 3dsceneeditor: controllable 3d scene editing with gaussian splatting. arXiv:2412.01583 arXiv preprint (2024)"},{"key":"24_CR49","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"24_CR50","doi-asserted-by":"crossref","unstructured":"Yang, Z., Li, P., Liu, Y.: Failures pave the way: enhancing large language models through tuning-free rule accumulation. arXiv preprint arXiv:2310.15746 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.109"},{"key":"24_CR51","doi-asserted-by":"crossref","unstructured":"Yao, B.M., Wang, Q., Huang, L.: Error-driven data-efficient large multimodal model tuning. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 20289\u201320306 (2025)","DOI":"10.18653\/v1\/2025.acl-long.992"},{"key":"24_CR52","doi-asserted-by":"crossref","unstructured":"Yu, H., Li, W., Wang, S., Chen, J., Zhu, J.: Inst3d-LMM: instance-aware 3d scene understanding with multi-modal instruction tuning. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 14147\u201314157 (2025)","DOI":"10.1109\/CVPR52734.2025.01320"},{"key":"24_CR53","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Ren, J., Feng, C.M., Zhao, H., Cui, S., Li, Z.: Visual programming for zero-shot open-vocabulary 3d visual grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20623\u201320633 (2024)","DOI":"10.1109\/CVPR52733.2024.01949"},{"key":"24_CR54","unstructured":"Zala, A., Cho, J., Lin, H., Yoon, J., Bansal, M.: Envgen: generating and adapting environments via LLMs for training embodied agents. ArXiv abs\/2403.12014 (2024). https:\/\/api.semanticscholar.org\/CorpusID:268531207"},{"key":"24_CR55","unstructured":"Zhang, W., et\u00a0al.: The point, the vision and the text: does point cloud boost spatial reasoning of large language models? arXiv preprint arXiv:2504.04540 (2025)"},{"key":"24_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Gong, Z., Chang, A.X.: Multi3drefer: grounding text description to multiple 3d objects. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15225\u201315236 (2023)","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"24_CR57","unstructured":"Zhang, Y., et al.: Vision-and-language navigation today and tomorrow: a survey in the era of foundation models. arXiv:2407.07035 arXiv preprint (2024)"},{"key":"24_CR58","unstructured":"Zhang, Y., Xu, Z., Shen, Y., Kordjamshidi, P., Huang, L.: Spartun3d: situated spatial understanding of 3d world in large language model. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"24_CR59","doi-asserted-by":"crossref","unstructured":"Zhao, L., Cai, D., Sheng, L., Xu, D.: 3dvg-transformer: relation modeling for visual grounding on point clouds. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2908\u20132917 (2021). https:\/\/api.semanticscholar.org\/CorpusID:244127479","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"24_CR60","doi-asserted-by":"crossref","unstructured":"Zhi, H., et al.: LSCENELLM: enhancing large 3d scene understanding using adaptive visual preferences. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 3761\u20133771 (2025)","DOI":"10.1109\/CVPR52734.2025.00356"},{"key":"24_CR61","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Ma, X., Chen, Y., Deng, Z., Huang, S., Li, Q.: 3d-vista: pre-trained transformer for 3d vision and text alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2911\u20132921 (2023)","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"24_CR62","doi-asserted-by":"crossref","unstructured":"Zhu, Z., et al.: Unifying 3d vision-language understanding via promptable queries. In: European Conference on Computer Vision, pp. 188\u2013206. Springer (2024)","DOI":"10.1007\/978-3-031-72784-9_11"},{"key":"24_CR63","doi-asserted-by":"crossref","unstructured":"Zhuang, J., Wang, C., Lin, L., Liu, L., Li, G.: Dreameditor: text-driven 3d scene editing with neural fields. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1\u201310 (2023)","DOI":"10.1145\/3610548.3618190"},{"key":"24_CR64","doi-asserted-by":"crossref","unstructured":"Zmigrod, R., Mielke, S.J., Wallach, H., Cotterell, R.: Counterfactual data augmentation for mitigating gender stereotypes in languages with rich morphology. arXiv:1906.04571 arXiv preprint (2019)","DOI":"10.18653\/v1\/P19-1161"}],"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_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:50:18Z","timestamp":1789379418000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37029-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370280","9783032370297"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37029-7_24","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"}}]}}