{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T04:55:29Z","timestamp":1743137729399,"version":"3.40.3"},"publisher-location":"Cham","reference-count":96,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031357473"},{"type":"electronic","value":"9783031357480"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-35748-0_32","type":"book-chapter","created":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T18:03:19Z","timestamp":1689012199000},"page":"461-479","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic Scene Builder: Towards a\u00a0Context Sensitive Text-to-3D Scene Framework"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2611-1417","authenticated-orcid":false,"given":"Alexander","family":"Henlein","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Attila","family":"Kett","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Baumartz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7084-4909","authenticated-orcid":false,"given":"Giuseppe","family":"Abrami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2567-7539","authenticated-orcid":false,"given":"Alexander","family":"Mehler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johannes","family":"Bastian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yannic","family":"Blecher","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Budgenhagen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roman","family":"Christof","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim-Oliver","family":"Ewald","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"Fauerbach","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Masny","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julian","family":"Mende","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul","family":"Schn\u00fcre","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Viel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,9]]},"reference":[{"key":"32_CR1","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. arXiv preprint arXiv:2204.14198 (2022)"},{"issue":"2","key":"32_CR2","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1037\/0022-3514.45.2.293","volume":"4","author":"CA Anderson","year":"1983","unstructured":"Anderson, C.A.: Imagination and expectation: The effect of imagining. J. PmonaIity Soc. Psychol. 4(2), 293\u2013330 (1983)","journal-title":"J. PmonaIity Soc. Psychol."},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Baden-Powell, C.: Architect\u2019s pocket book of kitchen design. Routledge (2006)","DOI":"10.4324\/9780080455099"},{"key":"32_CR4","unstructured":"Biewald, L.: Experiment tracking with weights and biases (2020). https:\/\/www.wandb.com\/, software available from wandb.com"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Bisk, Y., et al.: Experience grounds language. arXiv preprint arXiv:2004.10151 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.703"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Chang, A.X., et al.: Matterport3d: Learning from rgb-d data in indoor environments. In: International Conference on 3D Vision (3DV) (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"32_CR7","unstructured":"Chang, A.X., Eric, M., Savva, M., Manning, C.D.: SceneSeer: 3D scene design with natural language. arXiv preprint arXiv:1703.00050 (2017)"},{"key":"32_CR8","unstructured":"Chang, A.X., et al.: ShapeNet: An Information-Rich 3D Model Repository. Tech. Rep. arXiv:1512.03012 [cs.GR], Stanford University \u2013 Princeton University \u2013 Toyota Technological Institute at Chicago (2015)"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Chang, A.X., Monroe, W., Savva, M., Potts, C., Manning, C.D.: Text to 3D scene generation with rich lexical grounding. In: Association for Computational Linguistics and International Joint Conference on Natural Language Processing (ACL-IJCNLP) (2015)","DOI":"10.3115\/v1\/P15-1006"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Chang, A.X., Savva, M., Manning, C.D.: Interactive learning of spatial knowledge for text to 3D scene generation. In: Association for Computational Linguistics (ACL) Workshop on Interactive Language Learning, Visualization, and Interfaces (ILLVI) (2014)","DOI":"10.3115\/v1\/W14-3102"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Chang, A.X., Savva, M., Manning, C.D.: Learning spatial knowledge for text to 3D scene generation. In: Empirical Methods in Natural Language Processing (EMNLP) (2014)","DOI":"10.3115\/v1\/W14-3102"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Chen, K., Choy, C.B., Savva, M., Chang, A.X., Funkhouser, T., Savarese, S.: Text2shape: Generating shapes from natural language by learning joint embeddings. arXiv preprint arXiv:1803.08495 (2018)","DOI":"10.1007\/978-3-030-20893-6_7"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Chu, C.X., Tandon, N., Weikum, G.: Distilling task knowledge from how-to communities. In: Proceedings of the 26th International Conference on World Wide Web, pp. 805\u2013814 (2017)","DOI":"10.1145\/3038912.3052715"},{"key":"32_CR14","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511620539","volume-title":"Using Language","author":"HH Clark","year":"1996","unstructured":"Clark, H.H.: Using Language. Cambridge University Press, Cambridge (1996)"},{"key":"32_CR15","unstructured":"Coyne, B., Bauer, D., Rambow, O.: VigNet: Grounding language in graphics using frame semantics. In: Proceedings of the ACL 2011 Workshop on Relational Models of Semantics, pp. 28\u201336. Association for Computational Linguistics, Portland, Oregon, USA (Jun 2011). https:\/\/www.aclweb.org\/anthology\/W11-0905"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Coyne, B., Sproat, R.: Wordseye: an automatic text-to-scene conversion system. In: Proceedings of the 28th annual conference on Computer Graphics and Interactive Techniques, pp. 487\u2013496 (2001)","DOI":"10.1145\/383259.383316"},{"key":"32_CR17","doi-asserted-by":"publisher","unstructured":"Dayma, B., et al.: (July 2021). https:\/\/doi.org\/10.5281\/zenodo.5146400, https:\/\/github.com\/borisdayma\/dalle-mini","DOI":"10.5281\/zenodo.5146400"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Dennerlein, K.: Narratologie des raumes. In: Narratologie des Raumes. de Gruyter (2009)","DOI":"10.1515\/9783110219920"},{"key":"32_CR19","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (Jun 2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/www.aclweb.org\/anthology\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"32_CR20","unstructured":"Ding, M., Zheng, W., Hong, W., Tang, J.: Cogview2: Faster and better text-to-image generation via hierarchical transformers. arXiv preprint arXiv:2204.14217 (2022)"},{"key":"32_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-642-00437-7_1","volume-title":"Human Machine Interaction","author":"B Dumas","year":"2009","unstructured":"Dumas, B., Lalanne, D., Oviatt, S.: Multimodal interfaces: a survey of principles, models and frameworks. In: Lalanne, D., Kohlas, J. (eds.) Human Machine Interaction. LNCS, vol. 5440, pp. 3\u201326. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-00437-7_1"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"D\u2019Souza, J., Ng, V.: Utd: Ensemble-based spatial relation extraction. In: Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pp. 862\u2013869 (2015)","DOI":"10.18653\/v1\/S15-2146"},{"key":"32_CR23","unstructured":"Eberts, M., Ulges, A.: Span-based joint entity and relation extraction with transformer pre-training. CoRR abs\/ arXiv: 1909.07755 (2019). https:\/\/arxiv.org\/abs\/1909.07755"},{"key":"32_CR24","unstructured":"Etzioni, O., Fader, A., Christensen, J., Soderland, S., et al.: Open information extraction: The second generation. In: Twenty-Second International Joint Conference on Artificial Intelligence (2011)"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Feist, M.I., Gentner, D.: On plates, bowls, and dishes: Factors in the use of english in and on. In: Proceedings of the Twentieth Annual Conference of the Cognitive Science Society, pp. 345\u2013349. Routledge (1998)","DOI":"10.4324\/9781315782416-69"},{"key":"32_CR26","unstructured":"Ferrucci, D., Lally, A.: Uima: an architectural approach to unstructured information processing in the corporate research environment. In: Natural Language Engineering, pp. 1\u201326 (2004)"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Fisher, M., Ritchie, D., Savva, M., Funkhouser, T., Hanrahan, P.: Example-based synthesis of 3d object arrangements. In: ACM SIGGRAPH Asia 2012 papers, SIGGRAPH Asia 2012 (2012)","DOI":"10.1145\/2366145.2366154"},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: 3d-front: 3d furnished rooms with layouts and semantics. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10933\u201310942 (2021)","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: 3d-front: 3d furnished rooms with layouts and semantics. arXiv preprint arXiv:2011.09127 (2020)","DOI":"10.1109\/ICCV48922.2021.01075"},{"issue":"12","key":"32_CR30","doi-asserted-by":"publisher","first-page":"3313","DOI":"10.1007\/s11263-021-01534-z","volume":"129","author":"H Fu","year":"2021","unstructured":"Fu, H., et al.: 3d-future: 3d furniture shape with texture. Int. J. Comput. Vision 129(12), 3313\u20133337 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Gardner, M., et al.: Allennlp: A deep semantic natural language processing platform (2017)","DOI":"10.18653\/v1\/W18-2501"},{"issue":"1","key":"32_CR32","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.tics.2003.10.016","volume":"8","author":"S Garrod","year":"2004","unstructured":"Garrod, S., Pickering, M.J.: Why is conversation so easy? Trends Cogn. Sci. 8(1), 8\u201311 (2004)","journal-title":"Trends Cogn. Sci."},{"issue":"5","key":"32_CR33","doi-asserted-by":"publisher","first-page":"559","DOI":"10.3390\/nu10050559","volume":"10","author":"MJ Gibney","year":"2018","unstructured":"Gibney, M.J., et al.: Breakfast in human nutrition: The international breakfast research initiative. Nutrients 10(5), 559 (2018)","journal-title":"Nutrients"},{"key":"32_CR34","doi-asserted-by":"publisher","unstructured":"Hassani, K., Lee, W.S.: Visualizing natural language descriptions: A survey. ACM Comput. Surv. 49(1) (June 2016). https:\/\/doi.org\/10.1145\/2932710, https:\/\/doi.org\/10.1145\/2932710","DOI":"10.1145\/2932710"},{"key":"32_CR35","unstructured":"Henlein, A., Abrami, G., Kett, A., Mehler, A.: Transfer of isospace into a 3d environment for annotations and applications. In: Proceedings of the 16th Joint ACL - ISO Workshop on Interoperable Semantic Annotation, pp. 32\u201335. European Language Resources Association, Marseille (May 2020), https:\/\/www.aclweb.org\/anthology\/2020.isa-1.4"},{"key":"32_CR36","unstructured":"Herskovits, A.: Language and spatial cognition, vol. 12. Cambridge University Press Cambridge (1986)"},{"key":"32_CR37","doi-asserted-by":"crossref","unstructured":"Hua, B.S., Pham, Q.H., Nguyen, D.T., Tran, M.K., Yu, L.F., Yeung, S.K.: Scenenn: A scene meshes dataset with annotations. In: International Conference on 3D Vision (3DV) (2016)","DOI":"10.1109\/3DV.2016.18"},{"key":"32_CR38","doi-asserted-by":"crossref","unstructured":"Huguet Cabot, P.L., Navigli, R.: REBEL: Relation extraction by end-to-end language generation. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 2370\u20132381. Association for Computational Linguistics, Punta Cana, Dominican Republic (Nov 2021). https:\/\/aclanthology.org\/2021.findings-emnlp.204","DOI":"10.18653\/v1\/2021.findings-emnlp.204"},{"key":"32_CR39","doi-asserted-by":"crossref","unstructured":"Hwang, J.D., et al.: Comet-atomic 2020: On symbolic and neural commonsense knowledge graphs. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i7.16792"},{"key":"32_CR40","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-024-0881-2","volume-title":"Handbook of Linguistic Annotation","year":"2017","unstructured":"Ide, N., Pustejovsky, J. (eds.): Handbook of Linguistic Annotation. Springer, Dordrecht (2017). https:\/\/doi.org\/10.1007\/978-94-024-0881-2"},{"key":"32_CR41","unstructured":"ISO: Language resource management - Semantic annotation framework (SemAF) - Part 4: Semantic roles (SemAF-SR). Standard ISO\/IEC TR 24617\u20134:2014, International Organization for Standardization (2014). https:\/\/www.iso.org\/standard\/56866.html"},{"key":"32_CR42","unstructured":"ISO: Language resource management - Semantic annotation framework (SemAF) - Part 7: Spatial information (ISO-Space). Standard ISO\/IEC TR 24617\u20137:2014, International Organization for Standardization (2014). https:\/\/www.iso.org\/standard\/60779.html"},{"key":"32_CR43","unstructured":"ISO: Language resource management - Semantic annotation framework (SemAF) - Part 7: Spatial information (ISO-Space). Standard ISO\/IEC TR 24617\u20137:2019, International Organization for Standardization (2019). https:\/\/www.iso.org\/standard\/76442.html"},{"key":"32_CR44","doi-asserted-by":"crossref","unstructured":"Kermani, Z.S., Liao, Z., Tan, P., Zhang, H.: Learning 3d scene synthesis from annotated rgb-d images. In: Computer Graphics Forum, vol. 35, pp. 197\u2013206. Wiley Online Library (2016)","DOI":"10.1111\/cgf.12976"},{"key":"32_CR45","unstructured":"Klie, J.C., de Castilho, R.E.: Dkpro cassis - reading and writing uima cas files in python (2020)"},{"key":"32_CR46","unstructured":"Kordjamshidi, P., Moens, M.F., van Otterlo, M.: Spatial role labeling: Task definition and annotation scheme. In: Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC 2010), pp. 413\u2013420. European Language Resources Association (ELRA) (2010)"},{"issue":"3","key":"32_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2050104.2050105","volume":"8","author":"P Kordjamshidi","year":"2011","unstructured":"Kordjamshidi, P., Van Otterlo, M., Moens, M.F.: Spatial role labeling: Towards extraction of spatial relations from natural language. ACM Trans. Speech Lang. Process. (TSLP) 8(3), 1\u201336 (2011)","journal-title":"ACM Trans. Speech Lang. Process. (TSLP)"},{"issue":"1","key":"32_CR48","doi-asserted-by":"publisher","first-page":"40","DOI":"10.3758\/s13423-020-01792-x","volume":"28","author":"AA Kumar","year":"2021","unstructured":"Kumar, A.A.: Semantic memory: A review of methods, models, and current challenges. Psychon. Bull. Rev. 28(1), 40\u201380 (2021)","journal-title":"Psychon. Bull. Rev."},{"issue":"2","key":"32_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3303766","volume":"38","author":"M Li","year":"2019","unstructured":"Li, M., et al.: Grains: Generative recursive autoencoders for indoor scenes. ACM Trans. Graph. (TOG) 38(2), 1\u201316 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"32_CR50","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"32_CR51","doi-asserted-by":"publisher","unstructured":"Loureiro, D., Camacho-Collados, J.: Don\u2019t neglect the obvious: On the role of unambiguous words in word sense disambiguation. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3514\u20133520. Association for Computational Linguistics, Online (Nov 2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.283, https:\/\/www.aclweb.org\/anthology\/2020.emnlp-main.283","DOI":"10.18653\/v1\/2020.emnlp-main.283"},{"key":"32_CR52","doi-asserted-by":"publisher","unstructured":"Loureiro, D., Jorge, A.: Language modelling makes sense: Propagating representations through WordNet for full-coverage word sense disambiguation. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 5682\u20135691. Association for Computational Linguistics, Florence, Italy (Jul 2019). https:\/\/doi.org\/10.18653\/v1\/P19-1569, https:\/\/www.aclweb.org\/anthology\/P19-1569","DOI":"10.18653\/v1\/P19-1569"},{"issue":"6","key":"32_CR53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3272127.3275035","volume":"37","author":"R Ma","year":"2018","unstructured":"Ma, R., et al.: Language-driven synthesis of 3d scenes from scene databases. ACM Trans. Graph. (TOG) 37(6), 1\u201316 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"1","key":"32_CR54","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1207\/S15427633SCC0301_2","volume":"3","author":"SD Mainwaring","year":"2003","unstructured":"Mainwaring, S.D., Tversky, B., Ohgishi, M., Schiano, D.J.: Descriptions of simple spatial scenes in english and japanese. Spat. Cogn. Comput. 3(1), 3\u201342 (2003)","journal-title":"Spat. Cogn. Comput."},{"key":"32_CR55","doi-asserted-by":"crossref","unstructured":"Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S.J., McClosky, D.: The Stanford CoreNLP natural language processing toolkit. In: Association for Computational Linguistics (ACL) System Demonstrations, pp. 55\u201360 (2014). https:\/\/www.aclweb.org\/anthology\/P\/P14\/P14-5010","DOI":"10.3115\/v1\/P14-5010"},{"key":"32_CR56","unstructured":"Marcus, G., Davis, E., Aaronson, S.: A very preliminary analysis of dall-e 2. arXiv preprint arXiv:2204.13807 (2022)"},{"key":"32_CR57","doi-asserted-by":"crossref","unstructured":"Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2929\u20132936. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"32_CR58","unstructured":"McClelland, J.L., Hill, F., Rudolph, M., Baldridge, J., Sch\u00fctze, H.: Extending machine language models toward human-level language understanding. CoRR abs\/ arXiv: 1912.05877 (2019), https:\/\/arxiv.org\/abs\/1912.05877"},{"issue":"11","key":"32_CR59","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: Wordnet: a lexical database for English. Commun. ACM 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"issue":"1","key":"32_CR60","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.imavis.2007.08.013","volume":"26","author":"B Neumann","year":"2008","unstructured":"Neumann, B., M\u00f6ller, R.: On scene interpretation with description logics. Image Vis. Comput. 26(1), 82\u2013101 (2008)","journal-title":"Image Vis. Comput."},{"key":"32_CR61","doi-asserted-by":"crossref","unstructured":"Nichols, E., Botros, F.: Sprl-cww: Spatial relation classification with independent multi-class models. In: Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pp. 895\u2013901 (2015)","DOI":"10.18653\/v1\/S15-2150"},{"issue":"12","key":"32_CR62","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.tics.2007.09.009","volume":"11","author":"A Oliva","year":"2007","unstructured":"Oliva, A., Torralba, A.: The role of context in object recognition. Trends Cogn. Sci. 11(12), 520\u2013527 (2007)","journal-title":"Trends Cogn. Sci."},{"key":"32_CR63","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Temos: Generating diverse human motions from textual descriptions. arXiv preprint arXiv:2204.14109 (2022)","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"32_CR64","doi-asserted-by":"crossref","unstructured":"Pustejovsky, J., et al.: The specification language timeml. (2005)","DOI":"10.1093\/oso\/9780199268535.003.0031"},{"key":"32_CR65","doi-asserted-by":"publisher","unstructured":"Pustejovsky, J., Kordjamshidi, P., Moens, M.F., Levine, A., Dworman, S., Yocum, Z.: SemEval-2015 task 8: SpaceEval. In: Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pp. 884\u2013894. Association for Computational Linguistics, Denver, Colorado (Jun 2015). https:\/\/doi.org\/10.18653\/v1\/S15-2149, https:\/\/www.aclweb.org\/anthology\/S15-2149","DOI":"10.18653\/v1\/S15-2149"},{"key":"32_CR66","unstructured":"Pustejovsky, J., Krishnaswamy, N.: VoxML: A visualization modeling language. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), pp. 4606\u20134613. European Language Resources Association (ELRA), Portoro\u017e, Slovenia (May 2016), https:\/\/aclanthology.org\/L16-1730"},{"key":"32_CR67","unstructured":"Pustejovsky, J., Moszkowicz, J.L., Verhagen, M.: ISO-space: the annotation of spatial information in language. In: Proceedings of the Sixth Joint ISO-ACL SIGSEM Workshop on ISA, pp. 1\u20139 (2011)"},{"key":"32_CR68","doi-asserted-by":"crossref","unstructured":"Qi, P., Zhang, Y., Zhang, Y., Bolton, J., Manning, C.D.: Stanza: A Python natural language processing toolkit for many human languages. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations (2020). https:\/\/nlp.stanford.edu\/pubs\/qi2020stanza.pdf","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"key":"32_CR69","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"32_CR70","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"32_CR71","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 8821\u20138831. PMLR (18\u201324 Jul 2021)"},{"key":"32_CR72","unstructured":"Randell, D.A., Cui, Z., Cohn, A.G.: A spatial logic based on regions and connection. In: KR 1992, 165\u2013176 (1992)"},{"key":"32_CR73","doi-asserted-by":"crossref","unstructured":"Riva, G.: Virtual reality. Wiley encyclopedia of biomedical engineering (2006)","DOI":"10.1002\/9780471740360.ebs1266"},{"key":"32_CR74","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"1","key":"32_CR75","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1080\/10862969009547694","volume":"22","author":"M Sadoski","year":"1990","unstructured":"Sadoski, M., Goetz, E.T., Olivarez, A., Jr., Lee, S., Roberts, N.M.: Imagination in story reading: The role of imagery, verbal recall, story analysis, and processing levels. J. Reading Behav. 22(1), 55\u201370 (1990)","journal-title":"J. Reading Behav."},{"key":"32_CR76","doi-asserted-by":"crossref","unstructured":"Sadoski, M., Paivio, A.: Imagery and text: A dual coding theory of reading and writing. Routledge (2013)","DOI":"10.4324\/9781410605276"},{"key":"32_CR77","doi-asserted-by":"publisher","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding (2022). https:\/\/doi.org\/10.48550\/ARXIV.2205.11487, https:\/\/arxiv.org\/abs\/2205.11487","DOI":"10.48550\/ARXIV.2205.11487"},{"key":"32_CR78","doi-asserted-by":"crossref","unstructured":"Salaberri, H., Arregi, O., Zapirain, B.: Ixagroupehuspaceeval:(x-space) a wordnet-based approach towards the automatic recognition of spatial information following the iso-space annotation scheme. In: Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pp. 856\u2013861 (2015)","DOI":"10.18653\/v1\/S15-2145"},{"key":"32_CR79","doi-asserted-by":"crossref","unstructured":"Sap, M., et al.: Atomic: An atlas of machine commonsense for if-then reasoning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 3027\u20133035 (2019)","DOI":"10.1609\/aaai.v33i01.33013027"},{"key":"32_CR80","doi-asserted-by":"crossref","unstructured":"Savva, M., Chang, A.X., Hanrahan, P.: Semantically-enriched 3D models for common-sense knowledge. In: CVPR 2015 Workshop on Functionality, Physics, Intentionality and Causality (2015)","DOI":"10.1109\/CVPRW.2015.7301289"},{"key":"32_CR81","unstructured":"Settles, B.: Active learning literature survey (2009)"},{"key":"32_CR82","unstructured":"Shi, P., Lin, J.: Simple BERT models for relation extraction and semantic role labeling. CoRR abs\/ arXiv: 1904.05255 (2019). https:\/\/arxiv.org\/abs\/1904.05255"},{"key":"32_CR83","doi-asserted-by":"crossref","unstructured":"Shin, H.J., Park, J.Y., Yuk, D.B., Lee, J.S.: Bert-based spatial information extraction. In: Proceedings of the Third International Workshop on Spatial Language Understanding, pp. 10\u201317 (2020)","DOI":"10.18653\/v1\/2020.splu-1.2"},{"key":"32_CR84","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD Images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"32_CR85","doi-asserted-by":"crossref","unstructured":"Song, S., Yu, F., Zeng, A., Chang, A.X., Savva, M., Funkhouser, T.: Semantic scene completion from a single depth image. In: Proceedings of 30th IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.28"},{"key":"32_CR86","doi-asserted-by":"crossref","unstructured":"Speer, R., Chin, J., Havasi, C.: Conceptnet 5.5: An open multilingual graph of general knowledge (2017). https:\/\/aaai.org\/ocs\/index.php\/AAAI\/AAAI17\/paper\/view\/14972","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"32_CR87","unstructured":"Stubbs, A.: Mae and mai: lightweight annotation and adjudication tools. In: Proceedings of the 5th Linguistic Annotation Workshop, pp. 129\u2013133 (2011)"},{"key":"32_CR88","doi-asserted-by":"crossref","unstructured":"Tan, F., Feng, S., Ordonez, V.: Text2scene: Generating compositional scenes from textual descriptions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6710\u20136719 (2019)","DOI":"10.1109\/CVPR.2019.00687"},{"key":"32_CR89","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2019.104070","volume":"194","author":"A Tosi","year":"2020","unstructured":"Tosi, A., Pickering, M.J., Branigan, H.P.: Speakers\u2019 use of agency and visual context in spatial descriptions. Cognition 194, 104070 (2020)","journal-title":"Cognition"},{"key":"32_CR90","unstructured":"Ulinski, M., Coyne, B., Hirschberg, J.: Spatialnet: A declarative resource for spatial relations. In: Proceedings of the Combined Workshop on Spatial Language Understanding (SpLU) and Grounded Communication for Robotics (RoboNLP), pp. 61\u201370 (2019)"},{"key":"32_CR91","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"32_CR92","doi-asserted-by":"crossref","unstructured":"Wang, X., Yeshwanth, C., Nie\u00dfner, M.: Sceneformer: Indoor scene generation with transformers. In: 2021 International Conference on 3D Vision (3DV), pp. 106\u2013115. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00021"},{"key":"32_CR93","doi-asserted-by":"crossref","unstructured":"Ye, D., Lin, Y., Li, P., Sun, M.: Packed levitated marker for entity and relation extraction. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers), ACL 2022, Dublin, Ireland, 22\u201327 May 2022, pp. 4904\u20134917. Association for Computational Linguistics (2022). https:\/\/aclanthology.org\/2022.acl-long.337","DOI":"10.18653\/v1\/2022.acl-long.337"},{"key":"32_CR94","doi-asserted-by":"crossref","unstructured":"Zhang, H., Khashabi, D., Song, Y., Roth, D.: Transomcs: From linguistic graphs to commonsense knowledge. In: Proceedings of International Joint Conference on Artificial Intelligence (IJCAI) 2020 (2020)","DOI":"10.24963\/ijcai.2020\/554"},{"issue":"3","key":"32_CR95","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1007\/s11390-019-1929-5","volume":"34","author":"SH Zhang","year":"2019","unstructured":"Zhang, S.H., Zhang, S.K., Liang, Y., Hall, P.: A survey of 3d indoor scene synthesis. J. Comput. Sci. Technol. 34(3), 594\u2013608 (2019)","journal-title":"J. Comput. Sci. Technol."},{"issue":"6","key":"32_CR96","first-page":"1","volume":"35","author":"X Zhao","year":"2016","unstructured":"Zhao, X., Hu, R., Guerrero, P., Mitra, N., Komura, T.: Relationship templates for creating scene variations. ACM Trans. Graph. (TOG) 35(6), 1\u201313 (2016)","journal-title":"ACM Trans. Graph. (TOG)"}],"container-title":["Lecture Notes in Computer Science","Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-35748-0_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T22:42:17Z","timestamp":1729723337000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-35748-0_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031357473","9783031357480"],"references-count":96,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-35748-0_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"9 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HCII","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Copenhagen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Denmark","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hcii2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.hci.international\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7472","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1578","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"396","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"21% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}