{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:51:15Z","timestamp":1784389875936,"version":"3.55.0"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729690","type":"print"},{"value":"9783031729706","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"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\/978-3-031-72970-6_3","type":"book-chapter","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T10:50:43Z","timestamp":1732272643000},"page":"38-55","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1558,"title":["Grounding DINO: Marrying DINO with\u00a0Grounded Pre-training for\u00a0Open-Set Object Detection"],"prefix":"10.1007","author":[{"given":"Shilong","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoyang","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhe","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianwei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"3_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Chen, K., et\u00a0al.: Hybrid task cascade for instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4974\u20134983 (2019)","DOI":"10.1109\/CVPR.2019.00511"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Q., et al.: Group DETR: fast DETR training with group-wise one-to-many assignment (2022)","DOI":"10.1109\/ICCV51070.2023.00610"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Dai, X., et al.: Dynamic head: unifying object detection heads with attentions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7373\u20137382 (2021)","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Yang, Z., Chen, T., Zhou, W., Li, H.: TransVG: end-to-end visual grounding with transformers. arXiv, Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"3_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Dong, N., Zhang, Y., Ding, M., Lee, G.H.: Boosting long-tailed object detection via step-wise learning on smooth-tail data (2023). https:\/\/arxiv.org\/abs\/2305.12833","DOI":"10.1109\/ICCV51070.2023.00639"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Du, Y., Fu, Z., Liu, Q., Wang, Y.: Visual grounding with transformers (2021)","DOI":"10.1109\/ICME52920.2022.9859880"},{"key":"3_CR10","unstructured":"Gan, Z., Chen, Y.C., Li, L., Zhu, C., Cheng, Y., Liu, J.: Large-scale adversarial training for vision-and-language representation learning. In: Neural Information Processing Systems (2020)"},{"key":"3_CR11","unstructured":"Gao, P., et al.: Clip-adapter: better vision-language models with feature adapters. arXiv preprint arXiv:2110.04544 (2021)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Gao, P., Zheng, M., Wang, X., Dai, J., Li, H.: Fast convergence of DETR with spatially modulated co-attention. arXiv preprint arXiv:2101.07448 (2021)","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"3_CR13","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. Learning (2021)"},{"key":"3_CR14","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":"3_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Jia, D., et al.: DETRs with hybrid matching (2022)","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"3_CR17","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":"3_CR18","unstructured":"Krasin, I., et\u00a0al.: Openimages: a public dataset for large-scale multi-label and multi-class image classification. Dataset https:\/\/github.com\/openimages, 2(3), 18 (2017)"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. (2017)","DOI":"10.1007\/s11263-016-0981-7"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Kuo, W., Bertsch, F., Li, W., Piergiovanni, A., Saffar, M., Angelova, A.: Findit: generalized localization with natural language queries (2022)","DOI":"10.1007\/978-3-031-20059-5_29"},{"key":"3_CR21","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. arXiv, Computer Vision and Pattern Recognition (2018)"},{"key":"3_CR22","unstructured":"Li, C., et al.: Elevater: a benchmark and toolkit for evaluating language-augmented visual models (2022)"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: DN-DETR: accelerate DETR training by introducing query denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"3_CR24","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. arXiv preprint arXiv:2112.03857 (2021)"},{"key":"3_CR25","unstructured":"Li, M., Sigal, L.: Referring transformer: a one-step approach to multi-task visual grounding. arXiv, Computer Vision and Pattern Recognition (2021)"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GLIGEN: open-set grounded text-to-image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"3_CR28","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":"3_CR29","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, L., Yang, M.H.: Referring expression generation and comprehension via attributes. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.520"},{"key":"3_CR30","unstructured":"Liu, S., et al.: DAB-DETR: dynamic anchor boxes are better queries for DETR. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=oMI9PjOb9Jl"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional DETR for fast training convergence. arXiv preprint arXiv:2108.06152 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"3_CR33","unstructured":"Miao, P., Su, W., Wang, L., Fu, Y., Li, X.: Referring expression comprehension via cross-level multi-modal fusion. arXiv abs\/2204.09957 (2022)"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Minderer, M., et al.: Simple open-vocabulary object detection with vision transformers (2022)","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"3_CR35","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.L.: Im2text: describing images using 1 million captioned photographs. In: Neural Information Processing Systems (2011)"},{"key":"3_CR36","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":"3_CR37","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. Int. J. Comput. Vis. (2015)","DOI":"10.1109\/ICCV.2015.303"},{"issue":"6","key":"3_CR38","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR39","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Meeting of the Association for Computational Linguistics (2015)","DOI":"10.18653\/v1\/P16-1162"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8430\u20138439 (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"3_CR43","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: Meeting of the Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"3_CR44","unstructured":"Shilong, L., et al.: DQ-DETR: dual query detection transformer for phrase extraction and grounding. In: Proceedings of the AAAI Conference on Artificial Intelligence (2023)"},{"key":"3_CR45","unstructured":"Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning (2019)"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Thomee, B., et al.: YFCC100M: the new data in multimedia research. Commun. ACM (2016)","DOI":"10.1145\/2812802"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor DETR: query design for transformer-based detector. In: National Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"3_CR48","unstructured":"Wolf, T., et\u00a0al.: Huggingface\u2019s transformers: state-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)"},{"key":"3_CR49","doi-asserted-by":"crossref","unstructured":"Xu, M., et al.: End-to-end semi-supervised object detection with soft teacher. arXiv preprint arXiv:2106.09018 (2021)","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"3_CR50","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: DetCLIPv2: scalable open-vocabulary object detection pre-training via word-region alignment (2023)","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"3_CR51","unstructured":"Yao, L., et al.: Detclip: dictionary-enriched visual-concept paralleled pre-training for open-world detection (2022)"},{"key":"3_CR52","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: Mattnet: modular attention network for referring expression comprehension. In: Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"3_CR53","unstructured":"Yuan, L., et al.: Florence: a new foundation model for computer vision (2022)"},{"key":"3_CR54","doi-asserted-by":"crossref","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., Loy, C.C.: Open-vocabulary DETR with conditional matching (2022)","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"3_CR55","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14393\u201314402 (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"3_CR56","unstructured":"Zhang, H., et al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection (2022)"},{"key":"3_CR57","unstructured":"Zhang, H., et al.: GLIPv2: unifying localization and vision-language understanding (2022)"},{"key":"3_CR58","unstructured":"Zhao, T., Liu, P., Lu, X., Lee, K.: OmDet: language-aware object detection with large-scale vision-language multi-dataset pre-training (2022)"},{"key":"3_CR59","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et al.: Regionclip: region-based language-image pretraining (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"3_CR60","doi-asserted-by":"crossref","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"3_CR61","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"3_CR62","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: ICLR 2021: The Ninth International Conference on Learning Representations (2021)"}],"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\/978-3-031-72970-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T11:10:24Z","timestamp":1732273824000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72970-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"ISBN":["9783031729690","9783031729706"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72970-6_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"23 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"}}]}}