{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:26:55Z","timestamp":1777656415173,"version":"3.51.4"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732416","type":"print"},{"value":"9783031732423","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-73242-3_9","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"151-168","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["ScanReason: Empowering 3D Visual Grounding with\u00a0Reasoning Capabilities"],"prefix":"10.1007","author":[{"given":"Chenming","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xihui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"9_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1007\/978-3-030-58452-8_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Achlioptas","year":"2020","unstructured":"Achlioptas, P., Abdelreheem, A., Xia, F., Elhoseiny, M., Guibas, L.: ReferIt3D: neural listeners for fine-grained 3D object identification in real-world scenes. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part I. LNCS, vol. 12346, pp. 422\u2013440. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_25"},{"key":"9_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":"9_CR3","unstructured":"Bakr, E.M., Ayman, M., Ahmed, M., Slim, H., Elhoseiny, M.: CoT3Dref: chain-of-thoughts data-efficient 3D visual grounding. arXiv preprint arXiv:2310.06214 (2023)"},{"issue":"1791","key":"9_CR4","doi-asserted-by":"publisher","first-page":"20190307","DOI":"10.1098\/rstb.2019.0307","volume":"375","author":"M Baroni","year":"2020","unstructured":"Baroni, M.: Linguistic generalization and compositionality in modern artificial neural networks. Philos. Trans. R. Soc. B 375(1791), 20190307 (2020)","journal-title":"Philos. Trans. R. Soc. B"},{"key":"9_CR5","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":"9_CR6","unstructured":"Chen, C., et al.: Position-enhanced visual instruction tuning for multimodal large language models. arXiv preprint arXiv:2308.13437 (2023)"},{"key":"9_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1007\/978-3-030-58565-5_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"DZ Chen","year":"2020","unstructured":"Chen, D.Z., Chang, A.X., Nie\u00dfner, M.: ScanRefer: 3D object localization in RGB-D scans using natural language. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 202\u2013221. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_13"},{"key":"9_CR8","doi-asserted-by":"crossref","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 preprint arXiv:2112.01551 (2021)","DOI":"10.1007\/978-3-031-19824-3_29"},{"key":"9_CR9","unstructured":"Chen, F., et al.: X-LLM: bootstrapping advanced large language models by treating multi-modalities as foreign languages. arXiv preprint arXiv:2305.04160 (2023)"},{"key":"9_CR10","unstructured":"Chen, J., et al.: MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478 (2023)"},{"key":"9_CR11","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: unleashing multimodal llm\u2019s referential dialogue magic. arXiv preprint arXiv:2306.15195 (2023)"},{"key":"9_CR12","first-page":"20522","volume":"35","author":"S Chen","year":"2022","unstructured":"Chen, S., Guhur, P.L., Tapaswi, M., Schmid, C., Laptev, I.: Language conditioned spatial relation reasoning for 3D object grounding. Adv. Neural. Inf. Process. Syst. 35, 20522\u201320535 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: LL3DA: visual interactive instruction tuning for omni-3D understanding, reasoning, and planning. arXiv preprint arXiv:2311.18651 (2023)","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhu, H., Chen, X., Lei, Y., Yu, G., Chen, T.: End-to-end 3D dense captioning with vote2cap-DETR. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11124\u201311133 (2023)","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"9_CR15","unstructured":"Chen, T., Saxena, S., Li, L., Fleet, D.J., Hinton, G.: Pix2Seq: a language modeling framework for object detection. arXiv preprint arXiv:2109.10852 (2021)"},{"key":"9_CR16","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":"9_CR17","doi-asserted-by":"crossref","unstructured":"Chen, Z., Hu, R., Chen, X., Nie\u00dfner, M., Chang, A.X.: Unit3D: a unified transformer for 3D dense captioning and visual grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18109\u201318119 (2023)","DOI":"10.1109\/ICCV51070.2023.01660"},{"key":"9_CR18","unstructured":"Chung, H.W., et\u00a0al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)"},{"key":"9_CR19","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"9_CR20","unstructured":"Han, J., et\u00a0al.: ImageBind-LLM: multi-modality instruction tuning. arXiv preprint arXiv:2309.03905 (2023)"},{"key":"9_CR21","unstructured":"Hong, Y., et al.: 3D-LLM: injecting the 3D world into large language models. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"9_CR22","unstructured":"Huang, H., et al.: Chat-3D v2: Bridging 3D scene and large language models with object identifiers. arXiv preprint arXiv:2312.08168 (2023)"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Huang, S., Chen, Y., Jia, J., Wang, L.: Multi-view transformer for 3D visual grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15524\u201315533 (2022)","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"9_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/978-3-031-20059-5_24","volume-title":"Computer Vision \u2013 ECCV 2022","author":"A Jain","year":"2022","unstructured":"Jain, A., Gkanatsios, N., Mediratta, I., Fragkiadaki, K.: Bottom up top down detection transformers for language grounding in images and point clouds. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part XXXVI. Lecture Notes in Computer Science, vol. 13696, pp. 417\u2013433. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_24"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Jiao, Y., Chen, S., Jie, Z., Chen, J., Ma, L., Jiang, Y.G.: MORE: multi-order relation mining for dense captioning in 3D scenes. arXiv preprint arXiv:2203.05203 (2022)","DOI":"10.1007\/978-3-031-19833-5_31"},{"key":"9_CR26","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"9_CR27","unstructured":"Li, M., et al.: M3DBench: let\u2019s instruct large models with multi-modal 3d prompts. arXiv preprint arXiv:2312.10763 (2023)"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Luo, J., et al.: 3D-SPS: single-stage 3D visual grounding via referred point progressive selection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16454\u201316463 (2022)","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"9_CR29","unstructured":"Ma, X., Yong, S., Zheng, Z., Li, Q., Liang, Y., Zhu, S.C., Huang, S.: SQA3D: situated question answering in 3D scenes. arXiv preprint arXiv:2210.07474 (2022)"},{"key":"9_CR30","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"9_CR31","unstructured":"Roh, J., Desingh, K., Farhadi, A., Fox, D.: LanguageRefer: spatial-language model for 3d visual grounding. In: Conference on Robot Learning, pp. 1046\u20131056. PMLR (2022)"},{"key":"9_CR32","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. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"9_CR33","unstructured":"Team, I.: InterNLM: a multilingual language model with progressively enhanced capabilities (2023)"},{"key":"9_CR34","unstructured":"Touvron, H., et\u00a0al.: LLaMA 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"9_CR35","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, C., Yu, J., Cai, W.: Spatiality-guided transformer for 3D dense captioning on point clouds. arXiv preprint arXiv:2204.10688 (2022)","DOI":"10.24963\/ijcai.2022\/194"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Wang, T., et\u00a0al.: EmbodiedScan: a holistic multi-modal 3d perception suite towards embodied AI. arXiv preprint arXiv:2312.16170 (2023)","DOI":"10.1109\/CVPR52733.2024.01868"},{"key":"9_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":"9_CR39","doi-asserted-by":"crossref","unstructured":"Wu, Y., Cheng, X., Zhang, R., Cheng, Z., Zhang, J.: EDA: explicit text-decoupling and dense alignment for 3D visual and language learning. arXiv preprint arXiv:2209.14941 (2022)","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"9_CR40","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. arXiv preprint arXiv:2308.16911 (2023)","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"9_CR41","unstructured":"Yan, X., et al.: CLEVR3D: compositional language and elementary visual reasoning for question answering in 3D real-world scenes. arXiv preprint arXiv:2112.11691 (2021)"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: LLM-grounder: open-vocabulary 3D visual grounding with large language model as an agent. arXiv preprint arXiv:2309.12311 (2023)","DOI":"10.1109\/ICRA57147.2024.10610443"},{"key":"9_CR43","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhang, S., Wang, L., Luo, J.: SAT: 2D semantics assisted training for 3D visual grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1856\u20131866 (2021)","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"9_CR44","unstructured":"Ye, Q., et\u00a0al.: mPLUG-Owl: modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)"},{"key":"9_CR45","unstructured":"Ye, S., Chen, D., Han, S., Liao, J.: 3D question answering. IEEE Trans. Vis. Comput. Graph. (2022)"},{"key":"9_CR46","doi-asserted-by":"crossref","unstructured":"Yuan, Z., et al.: X-Trans2Cap: cross-modal knowledge transfer using transformer for 3D dense captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8563\u20138573 (2022)","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"9_CR47","unstructured":"Zhang, S., et\u00a0al.: OPT: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"Zhao, L., Cai, D., Sheng, L., Xu, D.: 3DVG-transformer: relation modeling for visual grounding on point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2928\u20132937 (2021)","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"9_CR49","unstructured":"Zhong, Y., Xu, L., Luo, J., Ma, L.: Contextual modeling for 3D dense captioning on point clouds. arXiv preprint arXiv:2210.03925 (2022)"},{"key":"9_CR50","unstructured":"Zhu, C., Zhang, W., Wang, T., Liu, X., Chen, K.: Object2Scene: putting objects in context for open-vocabulary 3D detection. arXiv preprint arXiv:2309.09456 (2023)"},{"key":"9_CR51","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"},{"key":"9_CR52","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"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73242-3_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:31:45Z","timestamp":1730107905000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73242-3_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031732416","9783031732423"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73242-3_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 2024","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"}}]}}