{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:19:01Z","timestamp":1777655941734,"version":"3.51.4"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732195","type":"print"},{"value":"9783031732201","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-3-031-73220-1_27","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T20:05:17Z","timestamp":1730577917000},"page":"466-482","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["PARIS3D: Reasoning-Based 3D Part Segmentation Using Large Multimodal Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2340-1953","authenticated-orcid":false,"given":"Amrin","family":"Kareem","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0315-6484","authenticated-orcid":false,"given":"Jean","family":"Lahoud","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8230-9065","authenticated-orcid":false,"given":"Hisham","family":"Cholakkal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Aminabadi, R.Y., et al.: DeepSpeed inference: enabling efficient inference of transformer models at unprecedented scale (2022)","DOI":"10.1109\/SC41404.2022.00051"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval (2022)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12m: pushing web-scale image-text pre-training to recognize long-tail visual concepts (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: LL3DA: visual interactive instruction tuning for omni-3D understanding, reasoning, and planning (2023)","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"27_CR5","doi-asserted-by":"publisher","unstructured":"Choy, C., Gwak, J., Savarese, S.: 4D spatio-temporal convnets: Minkowski convolutional neural networks. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Los Alamitos, CA, USA, pp. 3070\u20133079. IEEE Computer Society (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00319. https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR.2019.00319","DOI":"10.1109\/CVPR.2019.00319"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Ding, R., Yang, J., Xue, C., Zhang, W., Bai, S., Qi, X.: PLA: language-driven open-vocabulary 3D scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7010\u20137019 (2023)","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"27_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1007\/978-3-030-58607-2_28","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Gadelha","year":"2020","unstructured":"Gadelha, M., et al.: Label-efficient learning on point clouds using approximate convex decompositions. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 473\u2013491. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_28"},{"key":"27_CR8","doi-asserted-by":"publisher","unstructured":"Graham, B., Engelcke, M., van der Maaten, L.: 3D semantic segmentation with submanifold sparse convolutional networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9224\u20139232 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00961","DOI":"10.1109\/CVPR.2018.00961"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Graham, B., van\u00a0der Maaten, L.: Submanifold sparse convolutional networks (2017)","DOI":"10.1109\/CVPR.2018.00961"},{"key":"27_CR10","unstructured":"Guo, Z., et al.: Point-bind & point-LLM: aligning point cloud with multi-modality for 3D understanding, generation, and instruction following (2023)"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Guo, Z., et al.: ViewRefer: grasp the multi-view knowledge for 3D visual grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15372\u201315383 (2023)","DOI":"10.1109\/ICCV51070.2023.01410"},{"key":"27_CR12","unstructured":"Hong, Y., Du, Y., Lin, C., Tenenbaum, J.B., Gan, C.: 3D concept grounding on neural fields. In: NeurIPS (2022)"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Hong, Y., Lin, C., Du, Y., Chen, Z., Tenenbaum, J.B., Gan, C.: 3D concept learning and reasoning from multi-view images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00888"},{"key":"27_CR14","unstructured":"Hong, Y., et al.: 3D-LLM: injecting the 3D world into large language models. In: NeurIPS (2023)"},{"key":"27_CR15","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"27_CR16","doi-asserted-by":"publisher","unstructured":"Huang, Q., Wang, W., Neumann, U.: Recurrent slice networks for 3D segmentation of point clouds. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2626\u20132635 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00278","DOI":"10.1109\/CVPR.2018.00278"},{"key":"27_CR17","doi-asserted-by":"publisher","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferItGame: referring to objects in photographs of natural scenes. In: Moschitti, A., Pang, B., Daelemans, W. (eds.) Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, pp. 787\u2013798. Association for Computational Linguistics (2014). https:\/\/doi.org\/10.3115\/v1\/D14-1086. https:\/\/aclanthology.org\/D14-1086","DOI":"10.3115\/v1\/D14-1086"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"27_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1007\/978-3-030-58586-0_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Kundu","year":"2020","unstructured":"Kundu, A., et al.: Virtual multi-view fusion for 3D semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 518\u2013535. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_31"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: Stratified transformer for 3D point cloud segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8500\u20138509 (2022)","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: LISA: reasoning segmentation via large language model. arXiv preprint arXiv:2308.00692 (2023)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Landrieu, L., Simonovsky, M.: Large-scale point cloud semantic segmentation with superpoint graphs (2018)","DOI":"10.1109\/CVPR.2018.00479"},{"key":"27_CR23","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models (2023)"},{"key":"27_CR24","unstructured":"Li, M., et al.: M3DBench: let\u2019s instruct large models with multi-modal 3D prompts (2023)"},{"key":"27_CR25","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":"27_CR26","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)"},{"key":"27_CR27","unstructured":"Liu, K., et al.: Weakly supervised 3D open-vocabulary segmentation. In: Oh, A., Neumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol.\u00a036, pp. 53433\u201353456. Curran Associates, Inc. (2023). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/a76b693f36916a5ed84d6e5b39a0dc03-Paper-Conference.pdf"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Liu, M., et al.: PartSLIP: low-shot part segmentation for 3D point clouds via pretrained image-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21736\u201321746 (2023)","DOI":"10.1109\/CVPR52729.2023.02082"},{"key":"27_CR29","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2019)"},{"key":"27_CR30","unstructured":"Ma, X., et al.: SQA3D: situated question answering in 3D scenes. In: International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=IDJx97BC38"},{"key":"27_CR31","doi-asserted-by":"publisher","unstructured":"Mascaro, R., Teixeira, L., Chli, M.: Diffuser: multi-view 2D-to-3D label diffusion for semantic scene segmentation. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 13589\u201313595 (2021). https:\/\/doi.org\/10.1109\/ICRA48506.2021.9561801","DOI":"10.1109\/ICRA48506.2021.9561801"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: Howto100m: learning a text-video embedding by watching hundred million narrated video clips (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"27_CR33","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Peng, S., Genova, K., Jiang, C.M., Tagliasacchi, A., Pollefeys, M., Funkhouser, T.: OpenScene: 3D scene understanding with open vocabularies. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"27_CR35","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation (2017)"},{"key":"27_CR36","unstructured":"Qian, G., et al.: PointNext: revisiting pointnet++ with improved training and scaling strategies. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"27_CR37","unstructured":"Ravi, N., et al.: Accelerating 3D deep learning with PyTorch3D (2020)"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Robert, D., Vallet, B., Landrieu, L.: Learning multi-view aggregation in the wild for large-scale 3D semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5575\u20135584 (2022)","DOI":"10.1109\/CVPR52688.2022.00549"},{"key":"27_CR39","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models (2022)"},{"key":"27_CR40","unstructured":"Schuhmann, C., et al.: LAION-400m: open dataset of clip-filtered 400 million image-text pairs (2021)"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"27_CR42","unstructured":"Takmaz, A., Fedele, E., Sumner, R.W., Pollefeys, M., Tombari, F., Engelmann, F.: OpenMask3D: open-vocabulary 3D instance segmentation. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., Guibas, L.J.: KPConv: flexible and deformable convolution for point clouds. In: Proceedings of the IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00651"},{"key":"27_CR44","doi-asserted-by":"crossref","unstructured":"Vu, T., Kim, K., Luu, T.M., Nguyen, X.T., Yoo, C.D.: SoftGroup for 3D instance segmentation on 3D point clouds. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"27_CR45","unstructured":"Wang, W., et al.: VisionLLM: large language model is also an open-ended decoder for vision-centric tasks (2023)"},{"key":"27_CR46","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":"27_CR47","doi-asserted-by":"crossref","unstructured":"Xu, M., Ding, R., Zhao, H., Qi, X.: PAConv: position adaptive convolution with dynamic kernel assembling on point clouds. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00319"},{"key":"27_CR48","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 (2023)","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"27_CR49","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: LLM-grounder: open-vocabulary 3D visual grounding with large language model as an agent (2023)","DOI":"10.1109\/ICRA57147.2024.10610443"},{"key":"27_CR50","unstructured":"Zhang, S., et al.: GPT4RoI: instruction tuning large language model on region-of-interest (2023)"},{"key":"27_CR51","doi-asserted-by":"crossref","unstructured":"Zhao, N., Chua, T.S., Lee, G.H.: Few-shot 3D point cloud semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00876"},{"key":"27_CR52","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models (2023)"},{"key":"27_CR53","unstructured":"Ziyu, Z., Xiaojian, M., Yixin, C., Zhidong, D., Siyuan, H., Qing, L.: 3D-vista: pre-trained transformer for 3D vision and text alignment. In: ICCV (2023)"}],"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\/978-3-031-73220-1_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T20:08:30Z","timestamp":1730578110000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73220-1_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031732195","9783031732201"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73220-1_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 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"}}]}}