{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:26:11Z","timestamp":1780053971731,"version":"3.54.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727740","type":"print"},{"value":"9783031727757","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72775-7_2","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"19-35","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":51,"title":["LLaVA-Grounding: Grounded Visual Chat with\u00a0Large Multimodal Models"],"prefix":"10.1007","author":[{"given":"Hao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhe","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueyan","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shilong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shijia","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfeng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Leizhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jainwei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"2_CR1","unstructured":"Chen, C., et al.: Position-enhanced visual instruction tuning for multimodal large language models (2023)"},{"key":"2_CR2","unstructured":"Chen, J., et al.: MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning. arXiv:2310.09478 (2023)"},{"key":"2_CR3","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":"2_CR4","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: MDETR \u2013 modulated detection for end-to-end multi-modal understanding (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferitGame: referring to objects in photographs of natural scenes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"2_CR6","unstructured":"Krishna, R., et al.: Visual Genome: connecting language and vision using crowdsourced dense image annotations (2016)"},{"key":"2_CR7","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":"2_CR8","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":"2_CR9","unstructured":"Li, C., et al.: LLaVA-Med: training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890 (2023)"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Jiang, X.: GRES: generalized referring expression segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23592\u201323601 (2023)","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"2_CR14","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: PolyFormer: referring image segmentation as sequential polygon generation (2023)","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: LLaVA-Plus: learning to use tools for creating multimodal agents (2023)","DOI":"10.1007\/978-3-031-72970-6_8"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"2_CR18","unstructured":"Liu, Z., et al.: InternGPT: solving vision-centric tasks by interacting with ChatGPT beyond language (2023)"},{"key":"2_CR19","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"2_CR20","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"2_CR21","unstructured":"OpenAI: GPT-4v(ision) system card (2023). https:\/\/cdn.openai.com\/papers\/GPTV_System_Card.pdf"},{"key":"2_CR22","unstructured":"Peng, Z., et al.: Kosmos-2: grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824 (2023)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k Entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"2_CR24","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"2_CR25","unstructured":"Wang, W., et al.: CogVLM: visual expert for pretrained language models (2023)"},{"key":"2_CR26","unstructured":"Wang, W., et al.: VisionLLM: large language model is also an open-ended decoder for vision-centric tasks (2023)"},{"key":"2_CR27","unstructured":"Yang, J., Zhang, H., Li, F., Zou, X., Li, C., Gao, J.: Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4V (2023)"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: UniTAB: unifying text and box outputs for grounded vision-language modeling (2022)","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"2_CR29","unstructured":"Ye, J., et\u00a0al.: mPLUG-DocOwl: modularized multimodal large language model for document understanding. arXiv preprint arXiv:2307.02499 (2023)"},{"key":"2_CR30","unstructured":"You, H., et al.: Ferret: refer and ground anything anywhere at any granularity (2023)"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions (2016)","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"2_CR32","unstructured":"Zhang, H., et al.: A simple framework for open-vocabulary segmentation and detection. arXiv preprint arXiv:2303.08131 (2023)"},{"key":"2_CR33","unstructured":"Zhang, R., et al.: LLaMA-Adapter: efficient fine-tuning of language models with zero-init attention (2023)"},{"key":"2_CR34","unstructured":"Zhang, S., et al.: GPT4Roi: instruction tuning large language model on region-of-interest. arXiv preprint arXiv:2307.03601 (2023)"},{"key":"2_CR35","unstructured":"Zhao, Y., Lin, Z., Zhou, D., Huang, Z., Feng, J., Kang, B.: BuboGPT: enabling visual grounding in multi-modal LLMs. arXiv preprint arXiv:2307.08581 (2023)"},{"key":"2_CR36","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)"}],"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\/978-3-031-72775-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:21:11Z","timestamp":1732828871000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72775-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031727740","9783031727757"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72775-7_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}