{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:17:28Z","timestamp":1780053448718,"version":"3.54.0"},"publisher-location":"Cham","reference-count":67,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726576","type":"print"},{"value":"9783031726583","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"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\/978-3-031-72658-3_24","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T03:32:37Z","timestamp":1727839957000},"page":"417-435","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":41,"title":["Groma: Localized Visual Tokenization for\u00a0Grounding Multimodal Large Language Models"],"prefix":"10.1007","author":[{"given":"Chuofan","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiannan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehuan","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,2]]},"reference":[{"key":"24_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"24_CR2","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 35, pp. 23716\u201323736 (2022)"},{"key":"24_CR3","unstructured":"Bai, J., et al.: Qwen-VL: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"24_CR4","unstructured":"Bai, J., et al.: Qwen-VL: a versatile vision-language model for understanding, localization, text reading, and beyond (2023)"},{"key":"24_CR5","unstructured":"Bubeck, S., et al.: Sparks of artificial general intelligence: early experiments with GPT-4. arXiv preprint arXiv:2303.12712 (2023)"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Cai, M., et al.: Making large multimodal models understand arbitrary visual prompts. arXiv preprint arXiv:2312.00784 (2023)","DOI":"10.1109\/CVPR52733.2024.01227"},{"key":"24_CR7","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":"24_CR8","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":"24_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Sharegpt4v: improving large multi-modal models with better captions. arXiv preprint arXiv:2311.12793 (2023)","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. arXiv preprint arXiv:2312.14238 (2023)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"24_CR12","unstructured":"Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* chatgpt quality (2023). https:\/\/vicuna.lmsys.org. Accessed 14 Apr 2023"},{"key":"24_CR13","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. In: Thirty-Seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=vvoWPYqZJA"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Guo, Q., et al.: Regiongpt: towards region understanding vision language model (2024)","DOI":"10.1109\/CVPR52733.2024.01309"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"24_CR17","unstructured":"Ilharco, G., et al.: Openclip (2021). https:\/\/doi.org\/10.5281\/zenodo.5143773"},{"key":"24_CR18","unstructured":"Jiang, D., et al.: From clip to dino: visual encoders shout in multi-modal large language models (2023)"},{"key":"24_CR19","unstructured":"Junfeng, W., Yi, J., Qihao, L., Zehuan, Y., Xiang, B., Song, B.: General object foundation model for images and videos at scale. arXiv preprint arXiv:2312.09158 (2023)"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: MDETR-modulated detection for end-to-end multi-modal understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1780\u20131790 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"24_CR21","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":"24_CR22","unstructured":"Kirillov, A., et al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"24_CR23","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"issue":"7","key":"24_CR24","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset V4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vision 128(7), 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"24_CR25","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":"24_CR26","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":"24_CR27","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":"24_CR28","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-031-20077-9_17","volume-title":"ECCV 2022","author":"Y Li","year":"2022","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 280\u2013296. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_17"},{"key":"24_CR29","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":"24_CR30","doi-asserted-by":"crossref","unstructured":"Lin, Z., et al.: Sphinx: the joint mixing of weights, tasks, and visual embeddings for multi-modal large language models. arXiv preprint arXiv:2311.07575 (2023)","DOI":"10.1007\/978-3-031-73033-7_3"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"24_CR32","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: 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":"24_CR34","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"24_CR35","unstructured":"OpenAI: Chatgpt (2023). https:\/\/openai.com\/blog\/chatgpt\/"},{"key":"24_CR36","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"24_CR37","unstructured":"Oquab, M., et\u00a0al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"24_CR38","unstructured":"Peng, Z., et al.: Kosmos-2: grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824 (2023)"},{"key":"24_CR39","doi-asserted-by":"crossref","unstructured":"Pi, R., et al.: Detgpt: detect what you need via reasoning. arXiv preprint arXiv:2305.14167 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.876"},{"key":"24_CR40","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"24_CR41","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Rasheed, H., et al.: GLaMM: pixel grounding large multimodal model. arXiv preprint arXiv:2311.03356 (2023)","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8430\u20138439 (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"24_CR44","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"24_CR45","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"24_CR46","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: V3det: vast vocabulary visual detection dataset. arXiv preprint arXiv:2304.03752 (2023)","DOI":"10.1109\/ICCV51070.2023.01817"},{"key":"24_CR47","unstructured":"Wang, J., Meng, L., Weng, Z., He, B., Wu, Z., Jiang, Y.G.: To see is to believe: prompting GPT-4V for better visual instruction tuning. arXiv preprint arXiv:2311.07574 (2023)"},{"key":"24_CR48","unstructured":"Wang, P., et al.: OFA: unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In: International Conference on Machine Learning, pp. 23318\u201323340. PMLR (2022)"},{"key":"24_CR49","unstructured":"Wang, W., et al.: Cogvlm: visual expert for pretrained language models. arXiv preprint arXiv:2311.03079 (2023)"},{"key":"24_CR50","unstructured":"Wang, W., et al.: The all-seeing project: towards panoptic visual recognition and understanding of the open world. arXiv preprint arXiv:2308.01907 (2023)"},{"key":"24_CR51","unstructured":"Wang, W., et al.: Visionllm: large language model is also an open-ended decoder for vision-centric tasks. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"24_CR52","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 24824\u201324837 (2022)"},{"key":"24_CR53","unstructured":"Wu, J., et al.: Grit: a generative region-to-text transformer for object understanding. arXiv preprint arXiv:2212.00280 (2022)"},{"key":"24_CR54","doi-asserted-by":"crossref","unstructured":"Yan, B., et al.: Universal instance perception as object discovery and retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15325\u201315336 (2023)","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"24_CR55","unstructured":"Yang, J., Zhang, H., Li, F., Zou, X., Li, C., Gao, J.: Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4V. arXiv preprint arXiv:2310.11441 (2023)"},{"key":"24_CR56","unstructured":"Ye, Q., et al.: mPLUG-Owl: modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)"},{"key":"24_CR57","unstructured":"You, H., et al.: Ferret: refer and ground anything anywhere at any granularity. arXiv preprint arXiv:2310.07704 (2023)"},{"key":"24_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"24_CR59","doi-asserted-by":"crossref","unstructured":"Yuan, Y., et al.: Osprey: pixel understanding with visual instruction tuning. arXiv preprint arXiv:2312.10032 (2023)","DOI":"10.1109\/CVPR52733.2024.02664"},{"key":"24_CR60","unstructured":"Zhang, H., et al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"24_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Llava-grounding: grounded visual chat with large multimodal models. arXiv preprint arXiv:2312.02949 (2023)","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"24_CR62","unstructured":"Zhang, S., et al.: GPT4RoI: instruction tuning large language model on region-of-interest. arXiv preprint arXiv:2307.03601 (2023)"},{"key":"24_CR63","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":"24_CR64","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1007\/978-3-031-20077-9_21","volume-title":"ECCV 2022","author":"X Zhou","year":"2022","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 350\u2013368. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_21"},{"key":"24_CR65","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":"24_CR66","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"24_CR67","unstructured":"Zou, X., et al.: Segment everything everywhere all at once. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"}],"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\/978-3-031-72658-3_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T23:54:45Z","timestamp":1732838085000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72658-3_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,2]]},"ISBN":["9783031726576","9783031726583"],"references-count":67,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72658-3_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,2]]},"assertion":[{"value":"2 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"}}]}}