{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T04:02:26Z","timestamp":1748059346608,"version":"3.41.0"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031925900","type":"print"},{"value":"9783031925917","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-92591-7_29","type":"book-chapter","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T07:24:42Z","timestamp":1747985082000},"page":"436-450","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GECO: GPT-Driven Estimation of\u00a03D Human-Scene Contact in\u00a0the\u00a0Wild"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3319-3920","authenticated-orcid":false,"given":"Chaehong","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3318-0472","authenticated-orcid":false,"given":"Simranjit","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7721-3704","authenticated-orcid":false,"given":"Michael","family":"Fore","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5821-1909","authenticated-orcid":false,"given":"Georgios","family":"Pavlakos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1682-9350","authenticated-orcid":false,"given":"Dimitrios","family":"Stamoulis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Bhatnagar, B.L., Xie, X., Petrov, I.A., Sminchisescu, C., Theobalt, C., Pons-Moll, G.: Behave: dataset and method for tracking human object interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15935\u201315946 (2022)","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"29_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1007\/978-3-030-58580-8_33","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D Bolya","year":"2020","unstructured":"Bolya, D., Foley, S., Hays, J., Hoffman, J.: TIDE: a general toolbox for identifying object detection errors. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 558\u2013573. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_33"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Z., Radosavovic, I., Kanazawa, A., Malik, J.: Reconstructing hand-object interactions in the wild. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12417\u201312426 (2021)","DOI":"10.1109\/ICCV48922.2021.01219"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dwivedi, S.K., Black, M.J., Tzionas, D.: Detecting human-object contact in images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17100\u201317110 (2023)","DOI":"10.1109\/CVPR52729.2023.01640"},{"key":"29_CR5","doi-asserted-by":"publisher","unstructured":"Delmas, G., Weinzaepfel, P., Lucas, T., Moreno-Noguer, F., Rogez, G.: Posescript: 3d human poses from natural language. In: European Conference on Computer Vision, pp. 346\u2013362. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_20","DOI":"10.1007\/978-3-031-20068-7_20"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Delmas, G., Weinzaepfel, P., Moreno-Noguer, F., Rogez, G.: Posefix: correcting 3d human poses with natural language. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15018\u201315028 (2023)","DOI":"10.1109\/ICCV51070.2023.01379"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Fan, Z., et al.: Arctic: a dataset for dexterous bimanual hand-object manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12943\u201312954 (2023)","DOI":"10.1109\/CVPR52729.2023.01244"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Feng, Y., Lin, J., Dwivedi, S.K., Sun, Y., Patel, P., Black, M.J.: Chatpose: chatting about 3d human pose. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2024)","DOI":"10.1109\/CVPR52733.2024.00204"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Fieraru, M., Zanfir, M., Oneata, E., Popa, A.I., Olaru, V., Sminchisescu, C.: Three-dimensional reconstruction of human interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7214\u20137223 (2020)","DOI":"10.1109\/CVPR42600.2020.00724"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Fieraru, M., Zanfir, M., Oneata, E., Popa, A.I., Olaru, V., Sminchisescu, C.: Learning complex 3d human self-contact. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 1343\u20131351 (2021)","DOI":"10.1609\/aaai.v35i2.16223"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Fore, M., Singh, S., Lee, C., Pandey, A., Anastasopoulos, A., Stamoulis, D.: Unlearning climate misinformation in large language models. In: Proceedings of the 1st Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2024), pp. 178\u2013192. Association for Computational Linguistics (2024)","DOI":"10.18653\/v1\/2024.climatenlp-1.14"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Fore, M., Singh, S., Stamoulis, D.: Geckopt: Llm system efficiency via intent-based tool selection. In: Proceedings of the Great Lakes Symposium on VLSI 2024, pp. 353\u2013354 (2024)","DOI":"10.1145\/3649476.3658784"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Generating diverse and natural 3d human motions from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5152\u20135161 (2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Hassan, M., Choutas, V., Tzionas, D., Black, M.J.: Resolving 3d human pose ambiguities with 3d scene constraints. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2282\u20132292 (2019)","DOI":"10.1109\/ICCV.2019.00237"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Hassan, M., Ghosh, P., Tesch, J., Tzionas, D., Black, M.J.: Populating 3d scenes by learning human-scene interaction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14708\u201314718 (2021)","DOI":"10.1109\/CVPR46437.2021.01447"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Huang, C.H.P., et al.: Capturing and inferring dense full-body human-scene contact. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13274\u201313285 (2022)","DOI":"10.1109\/CVPR52688.2022.01292"},{"issue":"3","key":"29_CR17","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","volume":"7","author":"J Johnson","year":"2019","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with gpus. IEEE Trans. Big Data 7(3), 535\u2013547 (2019)","journal-title":"IEEE Trans. Big Data"},{"key":"29_CR18","unstructured":"LangChain Documentation: LangChain. https:\/\/github.com\/langchain-ai\/langchain, Accessed July 2024"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Lassner, C., Romero, J., Kiefel, M., Bogo, F., Black, M.J., Gehler, P.V.: Unite the people: Closing the loop between 3d and 2d human representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6050\u20136059 (2017)","DOI":"10.1109\/CVPR.2017.500"},{"key":"29_CR20","unstructured":"Lewis, P., Perez, E., et al.: Retrieval-augmented generation for knowledge-intensive nlp tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Li, Z., Shimada, S., Schiele, B., Theobalt, C., Golyanik, V.: Mocapdeform: monocular 3d human motion capture in deformable scenes. In: 2022 International Conference on 3D Vision (3DV), pp. 1\u201311. IEEE (2022)","DOI":"10.1109\/3DV57658.2022.00013"},{"key":"29_CR22","unstructured":"Lin, J., Feng, Y., Liu, W., Black, M.J.: Chathuman: Language-driven 3d human understanding with retrieval-augmented tool reasoning. arXiv preprint arXiv:2405.04533 (2024)"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: Smpl: a skinned multi-person linear model. In: Seminal Graphics Papers: Pushing the Boundaries, vol. 2, pp. 851\u2013866 (2023)","DOI":"10.1145\/3596711.3596800"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Majumdar, A., et\u00a0al.: Openeqa: embodied question answering in the era of foundation models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16488\u201316498 (2024)","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Muller, L., Osman, A.A., Tang, S., Huang, C.H.P., Black, M.J.: On self-contact and human pose. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9990\u20139999 (2021)","DOI":"10.1109\/CVPR46437.2021.00986"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"M\u00fcller, L., Ye, V., Pavlakos, G., Black, M., Kanazawa, A.: Generative proxemics: a prior for 3d social interaction from images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9687\u20139697 (2024)","DOI":"10.1109\/CVPR52733.2024.00925"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Shan, D., Radosavovic, I., Kanazawa, A., Fouhey, D., Malik, J.: Reconstructing hands in 3d with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9826\u20139836 (June 2024)","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"29_CR28","doi-asserted-by":"publisher","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Temos: generating diverse human motions from textual descriptions. In: European Conference on Computer Vision, pp. 480\u2013497. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_28","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"29_CR29","unstructured":"Shen, S., et\u00a0al.: Mixture-of-experts meets instruction tuning: a winning combination for large language models. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"29_CR30","doi-asserted-by":"publisher","unstructured":"Shimada, S., Golyanik, V., Li, Z., P\u00e9rez, P., Xu, W., Theobalt, C.: Hulc: 3d human motion capture with pose manifold sampling and dense contact guidance. In: European Conference on Computer Vision, pp. 516\u2013533. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_30","DOI":"10.1007\/978-3-031-20047-2_30"},{"issue":"6","key":"29_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3618329","volume":"42","author":"S Shimada","year":"2023","unstructured":"Shimada, S., Golyanik, V., P\u00e9rez, P., Theobalt, C.: Decaf: Monocular deformation capture for face and hand interactions. ACM Trans. Graph. (ToG) 42(6), 1\u201316 (2023)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Singh, S., et al.: Llm-dcache: improving tool-augmented llms with gpt-driven localized data caching. arXiv preprint arXiv:2406.06799 (2024)","DOI":"10.1109\/ICECS61496.2024.10848749"},{"key":"29_CR33","unstructured":"Singh, S., Pavlakos, G., Stamoulis, D.: Evaluating zero-shot gpt-4v performance on 3d visual question answering benchmarks. arXiv preprint arXiv:2405.18831 (2024)"},{"key":"29_CR34","unstructured":"Subramanian, S., Ng, E., M\u00fcller, L., Klein, D., Ginosar, S., Darrell, T.: Pose priors from language models. arXiv preprint arXiv:2405.03689 (2024)"},{"key":"29_CR35","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-or, D., Bermano, A.H.: Human motion diffusion model. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"29_CR36","doi-asserted-by":"crossref","unstructured":"Tripathi, S., Chatterjee, A., Passy, J.C., Yi, H., Tzionas, D., Black, M.J.: Deco: dense estimation of 3d human-scene contact in the wild. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8001\u20138013 (2023)","DOI":"10.1109\/ICCV51070.2023.00735"},{"key":"29_CR37","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"29_CR38","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR39","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhai, W., Luo, H., Cao, Y., Zha, Z.J.: Lemon: learning 3d human-object interaction relation from 2d images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16284\u201316295 (2024)","DOI":"10.1109\/CVPR52733.2024.01541"},{"key":"29_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-030-58610-2_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"JY Zhang","year":"2020","unstructured":"Zhang, J.Y., Pepose, S., Joo, H., Ramanan, D., Malik, J., Kanazawa, A.: Perceiving 3D human-object spatial arrangements from a single image in the wild. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 34\u201351. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_3"},{"key":"29_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Generating human motion from textual descriptions with discrete representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14730\u201314740 (2023)","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"29_CR42","unstructured":"Zhang, M., et al.: Motiondiffuse: text-driven human motion generation with diffusion model. arXiv preprint arXiv:2208.15001 (2022)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92591-7_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T07:25:10Z","timestamp":1747985110000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92591-7_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031925900","9783031925917"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92591-7_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}