{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:56:29Z","timestamp":1784300189662,"version":"3.55.0"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726972","type":"print"},{"value":"9783031726989","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72698-9_8","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T04:45:57Z","timestamp":1729831557000},"page":"131-147","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":88,"title":["PointLLM: Empowering Large Language Models to\u00a0Understand Point Clouds"],"prefix":"10.1007","author":[{"given":"Runsen","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangmiao","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"8_CR1","unstructured":"Alayrac, J.B., et\u00a0al.: Flamingo: a visual language model for few-shot learning (2022)"},{"key":"8_CR2","unstructured":"Awadalla, A., et\u00a0al.: Openflamingo: an open-source framework for training large autoregressive vision-language models. arXiv:2308.01390 (2023)"},{"key":"8_CR3","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: ACL Workshop (2005)"},{"key":"8_CR4","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners (2020)"},{"key":"8_CR5","unstructured":"Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* ChatGPT quality (2023). https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"8_CR6","unstructured":"Chowdhery, A., et\u00a0al.: PaLM: scaling language modeling with pathways. arXiv:2204.02311 (2022)"},{"key":"8_CR7","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"8_CR8","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. NeurIPS (20243)"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3D objects. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"8_CR10","unstructured":"Driess, D., et\u00a0al.: PaLM-E: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"key":"8_CR11","unstructured":"Gao, P., et al.: LLaMA-adapter V2: parameter-efficient visual instruction model. arXiv:2304.15010 (2023)"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Gao, T., Yao, X., Chen, D.: SimCSE: simple contrastive learning of sentence embeddings. arXiv:2104.08821 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: ImageBind: one embedding space to bind them all. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"8_CR14","unstructured":"Gong, T., et al.: Multimodal-GPT: a vision and language model for dialogue with humans. arXiv:2305.04790 (2023)"},{"key":"8_CR15","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":"8_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, T., Kembhavi, A.: Visual programming: compositional visual reasoning without training. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"8_CR17","unstructured":"Han, J., et\u00a0al.: ImageBind-LLM: multi-modality instruction tuning. arXiv:2309.03905 (2023)"},{"key":"8_CR18","unstructured":"Hao, Y., et al.: Language models are general-purpose interfaces. arXiv:2206.06336 (2022)"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Hegde, D., Valanarasu, J.M.J., Patel, V.: Clip goes 3D: leveraging prompt tuning for language grounded 3D recognition. In: ICCV (2023)","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"8_CR20","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs). arXiv:1606.08415 (2016)"},{"key":"8_CR21","unstructured":"Hong, Y., et al.: 3D-LLM: injecting the 3D world into large language models (2023)"},{"key":"8_CR22","unstructured":"Huang, R., et\u00a0al.: AudioGPT: understanding and generating speech, music, sound, and talking head. arXiv:2304.12995 (2023)"},{"key":"8_CR23","unstructured":"Huang, S., et\u00a0al.: Language is not all you need: aligning perception with language models. arXiv:2302.14045 (2023)"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Huang, T., et al.: CLIP2Point: transfer clip to point cloud classification with image-depth pre-training. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.02025"},{"key":"8_CR25","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., Chen, T.: MotionGPT: human motion as a foreign language. arXiv:2306.14795 (2023)"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"8_CR27","unstructured":"Li, B., et al.: MIMIC-IT: multi-modal in-context instruction tuning. arXiv:2306.05425 (2023)"},{"key":"8_CR28","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)"},{"key":"8_CR29","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)"},{"key":"8_CR30","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out (2004)"},{"key":"8_CR31","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)"},{"key":"8_CR32","unstructured":"Liu, M., et al.: OpenShape: scaling up 3D shape representation towards open-world understanding. arXiv preprint arXiv:2305.10764 (2023)"},{"key":"8_CR33","unstructured":"Luo, T., Rockwell, C., Lee, H., Johnson, J.: Scalable 3D captioning with pretrained models. arXiv:2306.07279 (2023)"},{"key":"8_CR34","unstructured":"OpenAI: ChatGPT. https:\/\/openai.com\/blog\/chatgpt (2022)"},{"key":"8_CR35","unstructured":"OpenAI: GPT-4 technical report. arXiv:2303.08774 (2023)"},{"key":"8_CR36","unstructured":"Ouyang, L., et\u00a0al.: Training language models to follow instructions with human feedback (2022)"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: ACL (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"8_CR38","unstructured":"Patil, S.G., Zhang, T., Wang, X., Gonzalez, J.E.: Gorilla: large language model connected with massive APIs. arXiv preprint arXiv:2305.15334 (2023)"},{"key":"8_CR39","unstructured":"Peng, Z., et al.: Kosmos-2: grounding multimodal large language models to the world. arXiv:2306.14824 (2023)"},{"key":"8_CR40","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: CVPR (2017)"},{"key":"8_CR41","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"8_CR42","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. In: JMLR (2020)"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"8_CR44","unstructured":"Su, Y., Lan, T., Li, H., Xu, J., Wang, Y., Cai, D.: PandaGPT: one model to instruction-follow them all. arXiv:2305.16355 (2023)"},{"key":"8_CR45","unstructured":"Sun, Q., et al.: UniG3D: a unified 3D object generation dataset. arXiv:2306.10730 (2023)"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Sur\u00eds, D., Menon, S., Vondrick, C.: ViperGPT: visual inference via python execution for reasoning. arXiv:2303.08128 (2023)","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"8_CR47","unstructured":"Team, I.: InternLM: a multilingual language model with progressively enhanced capabilities. https:\/\/github.com\/InternLM\/InternLM (2023)"},{"key":"8_CR48","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv:2302.13971 (2023)"},{"key":"8_CR49","unstructured":"Vaswani, A., et al.: Attention is all you need (2017)"},{"key":"8_CR50","doi-asserted-by":"crossref","unstructured":"Wang, H., et\u00a0al.: Beyond first impressions: integrating joint multi-modal cues for comprehensive 3D representation. In: ACM MM (2023)","DOI":"10.1145\/3581783.3611767"},{"key":"8_CR51","unstructured":"Wang, W., et\u00a0al.: VisionLLM: large language model is also an open-ended decoder for vision-centric tasks. arXiv:2305.11175 (2023)"},{"key":"8_CR52","unstructured":"Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., Duan, N.: Visual ChatGPT: talking, drawing and editing with visual foundation models. arXiv:2303.04671 (2023)"},{"key":"8_CR53","unstructured":"Wu, Z., et al.: 3D shapeNets: a deep representation for volumetric shapes. In: CVPR (2015)"},{"key":"8_CR54","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: ULIP: learning a unified representation of language, images, and point clouds for 3D understanding. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"8_CR55","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: ULIP-2: towards scalable multimodal pre-training for 3D understanding. arXiv:2305.08275 (2023)","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"8_CR56","doi-asserted-by":"crossref","unstructured":"Yin, S., et al.: A survey on multimodal large language models. arXiv:2306.13549 (2023)","DOI":"10.1093\/nsr\/nwae403"},{"key":"8_CR57","doi-asserted-by":"crossref","unstructured":"Yu, X., Tang, L., Rao, Y., Huang, T., Zhou, J., Lu, J.: Point-BERT: re-training 3D point cloud transformers with masked point modeling. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"8_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: PointCLIP: point cloud understanding by clip. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"8_CR59","unstructured":"Zhang, R., et al.: LLaMA-Adapter: efficient fine-tuning of language models with zero-init attention. arXiv:2303.16199 (2023)"},{"key":"8_CR60","unstructured":"Zhang, S., et al.: GPT4RoI: Instruction tuning large language model on region-of-interest. arXiv:2307.03601 (2023)"},{"key":"8_CR61","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv:2304.10592 (2023)"},{"key":"8_CR62","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: PointCLIP V2: prompting clip and GPT for powerful 3D open-world learning. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00249"}],"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\/978-3-031-72698-9_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T07:22:56Z","timestamp":1732951376000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72698-9_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726972","9783031726989"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72698-9_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 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"}}]}}