{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T10:57:49Z","timestamp":1765018669281,"version":"3.46.0"},"publisher-location":"Cham","reference-count":76,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031736353"},{"type":"electronic","value":"9783031736360"}],"license":[{"start":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T00:00:00Z","timestamp":1730764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T00:00:00Z","timestamp":1730764800000},"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\/978-3-031-73636-0_3","type":"book-chapter","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T15:02:39Z","timestamp":1730732559000},"page":"41-59","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["M3DBench: Towards Omni 3D Assistant with\u00a0Interleaved Multi-modal Instructions"],"prefix":"10.1007","author":[{"given":"Mingsheng","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sijin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyuan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fukun","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuoyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,5]]},"reference":[{"key":"3_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. LNCS, vol. 12346, pp. 422\u2013440. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_25"},{"key":"3_CR2","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3674\u20133683 (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"3_CR4","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":"3_CR5","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation AND\/OR Summarization, pp. 65\u201372 (2005)"},{"key":"3_CR6","unstructured":"Bianco, S., Celona, L., Donzella, M., Napoletano, P.: Improving image captioning descriptiveness by ranking and LLM-based fusion. arXiv preprint arXiv:2306.11593 (2023)"},{"key":"3_CR7","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR8","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":"3_CR9","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. arXiv preprint arXiv:1709.06158 (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"3_CR10","unstructured":"Chang, A.X., et\u00a0al.: ShapeNet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"3_CR11","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":"3_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/978-3-031-19824-3_29","volume-title":"Computer Vision \u2013 ECCV 2022","author":"DZ Chen","year":"2022","unstructured":"Chen, D.Z., Wu, Q., Nie\u00dfner, M., Chang, A.X.: D$$^{3}$$ net: a unified speaker-listener architecture for 3d dense captioning and visual grounding. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13692, pp. 487\u2013505. Springer, Cham (2022)"},{"key":"3_CR13","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":"3_CR14","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":"3_CR15","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":"3_CR16","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Vote2Cap-DETR++: decoupling localization and describing for end-to-end 3D dense captioning (2023)","DOI":"10.1109\/TPAMI.2024.3387838"},{"key":"3_CR17","unstructured":"Chen, X., Fang, H., Lin, T.Y., Vedantam, R., Gupta, S., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"3_CR18","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":"3_CR19","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":"3_CR20","unstructured":"Chiang, W.L., et\u00a0al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* ChatGPT quality (2023). https:\/\/vicuna.lmsys.org. Accessed 14 Apr 2023"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"3_CR22","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: From images to textual prompts: zero-shot visual question answering with frozen large language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10867\u201310877 (2023)","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"3_CR24","unstructured":"Guo, Z., et\u00a0al.: Point-bind & point-LLM: aligning point cloud with multi-modality for 3D understanding, generation, and instruction following. arXiv preprint arXiv:2309.00615 (2023)"},{"key":"3_CR25","unstructured":"Hong, Y., et al.: 3D-LLM: injecting the 3D world into large language models. arXiv preprint arXiv:2307.12981 (2023)"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Hu, W., Xu, Y., Li, Y., Li, W., Chen, Z., Tu, Z.: BLIVA: a simple multimodal LLM for better handling of text-rich visual questions. arXiv preprint arXiv:2308.09936 (2023)","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"3_CR27","unstructured":"Huang, J., et al.: An embodied generalist agent in 3D world. arXiv preprint arXiv:2311.12871 (2023)"},{"key":"3_CR28","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":"3_CR29","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., Chen, T.: MotionGPT: human motion as a foreign language. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Jiang, B., et al.: MotionChain: conversational motion controllers via multimodal prompts. arXiv preprint arXiv:2404.01700 (2024)","DOI":"10.1007\/978-3-031-73347-5_4"},{"key":"3_CR31","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594. PMLR (2021)"},{"key":"3_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58604-1_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Krantz","year":"2020","unstructured":"Krantz, J., Wijmans, E., Majumdar, A., Batra, D., Lee, S.: Beyond the nav-graph: vision-and-language navigation in continuous environments. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_7"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373 (2017)","DOI":"10.1007\/s11263-016-0981-7"},{"key":"3_CR34","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)"},{"key":"3_CR35","unstructured":"Li, B., et al.: MIMIC-IT: multi-modal in-context instruction tuning. arXiv preprint arXiv:2306.05425 (2023)"},{"key":"3_CR36","unstructured":"Li, B., Zhang, Y., Chen, L., Wang, J., Yang, J., Liu, Z.: Otter: a multi-modal model with in-context instruction tuning. arXiv preprint arXiv:2305.03726 (2023)"},{"key":"3_CR37","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":"3_CR38","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"3_CR39","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"3_CR40","unstructured":"Liu, F., Lin, K., Li, L., Wang, J., Yacoob, Y., Wang, L.: Mitigating hallucination in large multi-modal models via robust instruction tuning (2023)"},{"key":"3_CR41","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"3_CR42","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"3_CR43","unstructured":"Ma, X., et al.: SQA3D: situated question answering in 3D scenes. arXiv preprint arXiv:2210.07474 (2022)"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2906\u20132917 (2021)","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"3_CR45","unstructured":"OpenAI, R.: GPT-4 technical report. arxiv:2303.08774. View in Article 2 (2023)"},{"key":"3_CR46","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Pan, X., Xia, Z., Song, S., Li, L.E., Huang, G.: 3D object detection with pointformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7463\u20137472 (2021)","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"3_CR48","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"3_CR49","doi-asserted-by":"crossref","unstructured":"Parelli, M., et al.: CLIP-guided vision-language pre-training for question answering in 3D scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5606\u20135611 (2023)","DOI":"10.1109\/CVPRW59228.2023.00593"},{"key":"3_CR50","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"3_CR51","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep hough voting for 3D object detection in point clouds. In: proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"3_CR52","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"3_CR53","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"3_CR54","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)"},{"key":"3_CR55","doi-asserted-by":"crossref","unstructured":"Rotstein, N., Bensaid, D., Brody, S., Ganz, R., Kimmel, R.: FuseCap: leveraging large language models to fuse visual data into enriched image captions. arXiv preprint arXiv:2305.17718 (2023)","DOI":"10.1109\/WACV57701.2024.00559"},{"key":"3_CR56","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR57","unstructured":"Schulman, J., et\u00a0al.: ChatGPT: optimizing language models for dialogue. OpenAI blog (2022)"},{"key":"3_CR58","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: a RGB-D scene understanding benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"3_CR59","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"3_CR60","unstructured":"Touvron, H., et\u00a0al.: LLaMA 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"3_CR61","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"3_CR62","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: CiDER: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"3_CR63","unstructured":"Wang, T., et\u00a0al.: Caption anything: interactive image description with diverse multimodal controls. arXiv preprint arXiv:2305.02677 (2023)"},{"key":"3_CR64","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":"3_CR65","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 grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19231\u201319242 (2023)","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"3_CR66","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":"3_CR67","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":"3_CR68","unstructured":"Yin, F., et al.: ShapeGPT: 3D shape generation with a unified multi-modal language model. arXiv preprint arXiv:2311.17618 (2023)"},{"key":"3_CR69","unstructured":"Yin, Z., et\u00a0al.: LAMM: language-assisted multi-modal instruction-tuning dataset, framework, and benchmark. arXiv preprint arXiv:2306.06687 (2023)"},{"key":"3_CR70","unstructured":"Yuan, Z., et al.: Toward explainable and fine-grained 3D grounding through referring textual phrases. arXiv preprint arXiv:2207.01821 (2022)"},{"key":"3_CR71","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":"3_CR72","doi-asserted-by":"crossref","unstructured":"Yuan, Z., et al.: InstanceRefer: cooperative holistic understanding for visual grounding on point clouds through instance multi-level contextual referring. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1791\u20131800 (2021)","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"3_CR73","unstructured":"Zhang, S., et\u00a0al.: OPT: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"3_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Girdhar, R., Joulin, A., Misra, I.: Self-supervised pretraining of 3D features on any point-cloud. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10252\u201310263 (2021)","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"3_CR75","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":"3_CR76","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\/978-3-031-73636-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T10:53:23Z","timestamp":1765018403000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73636-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,5]]},"ISBN":["9783031736353","9783031736360"],"references-count":76,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73636-0_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,5]]},"assertion":[{"value":"5 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"}}]}}