{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:36:15Z","timestamp":1780418175121,"version":"3.54.1"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200762","type":"print"},{"value":"9783031200779","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20077-9_7","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:21:52Z","timestamp":1667665312000},"page":"106-122","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":183,"title":["Open-Vocabulary DETR with\u00a0Conditional Matching"],"prefix":"10.1007","author":[{"given":"Yuhang","family":"Zang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiyang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"key":"7_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1007\/978-3-030-01246-5_24","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Bansal","year":"2018","unstructured":"Bansal, A., Sikka, K., Sharma, G., Chellappa, R., Divakaran, A.: Zero-shot object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 397\u2013414. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_24"},{"key":"7_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":"7_CR3","doi-asserted-by":"crossref","unstructured":"Chen, K., Kovvuri, R., Nevatia, R.: Query-guided regression network with context policy for phrase grounding. In: ICCV, pp. 824\u2013832 (2017)","DOI":"10.1109\/ICCV.2017.95"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., Chen, J.: UP-DETR: unsupervised pre-training for object detection with transformers. In: CVPR, pp. 1601\u20131610 (2021)","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Deng, C., Wu, Q., Wu, Q., Hu, F., Lyu, F., Tan, M.: Visual grounding via accumulated attention. In: CVPR, pp. 7746\u20137755 (2018)","DOI":"10.1109\/CVPR.2018.00808"},{"key":"7_CR6","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":"7_CR7","doi-asserted-by":"crossref","unstructured":"Du, Y., Wei, F., Zhang, Z., Shi, M., Gao, Y., Li, G.: Learning to prompt for open-vocabulary object detection with vision-language model. In: CVPR, pp. 14084\u201314093 (2022)","DOI":"10.1109\/CVPR52688.2022.01369"},{"issue":"2","key":"7_CR8","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV 88(2), 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR, pp. 1\u20138. Ieee (2008)","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"7_CR10","unstructured":"Frome, A., et al.: Devise: A deep visual-semantic embedding model. In: NeurIPS (2013)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Gao, P., Zheng, M., Wang, X., Dai, J., Li, H.: Fast convergence of DETR with spatially modulated co-attention. In: ICCV, pp. 3621\u20133630 (2021)","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"7_CR12","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS, vol. 27 (2014)"},{"key":"7_CR13","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. In: ICLR (2022)"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: CVPR, pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: ICCV. pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"7_CR16","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: ICCV. pp. 1780\u20131790 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Kim, D., Lin, T.Y., Angelova, A., Kweon, I.S., Kuo, W.: Learning open-world object proposals without learning to classify. Rob. Autom. Lett. 7(2), :1-1 (2022)","DOI":"10.1109\/LRA.2022.3146922"},{"issue":"1\u20132","key":"7_CR18","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist Q."},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Zhou, B., Yue, D., Wang, X.: Person search with natural language description. In: CVPR, pp. 1970\u20131979 (2017)","DOI":"10.1109\/CVPR.2017.551"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., Yao, L., Zhang, X., Wang, X., Kanhere, S., Zhang, H.: Zero-shot object detection with textual descriptions. In: AAAI, pp. 8690\u20138697 (2019)","DOI":"10.1609\/aaai.v33i01.33018690"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2999\u20133007 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"7_CR22","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":"TY Liu","year":"2014","unstructured":"Liu, 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":"7_CR23","doi-asserted-by":"publisher","unstructured":"Lin, T., 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","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional DETR for fast training convergence. In: ICCV, pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"issue":"1","key":"7_CR25","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1023\/A:1008162616689","volume":"38","author":"C Papageorgiou","year":"2000","unstructured":"Papageorgiou, C., Poggio, T.: A trainable system for object detection. Int. J. Comput. Vis. 38(1), 15\u201333 (2000)","journal-title":"Int. J. Comput. Vis."},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: Global vectors for word representation. In: EMNLP, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"7_CR27","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv preprint arXiv:2103.00020 (2021)"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Rahman, T., Chou, S.H., Sigal, L., Carenini, G.: An improved attention for visual question answering. In: CVPR, pp. 1653\u20131662 (2021)","DOI":"10.1109\/CVPRW53098.2021.00181"},{"key":"7_CR29","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-CNN: towards real-time object detection with region proposal networks. In: NeurIPS, vol. 28, 91\u201399 (2015)"},{"key":"7_CR30","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: CVPR, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"7_CR31","unstructured":"Shizhen, Z., et al.: GtNet: generative transfer network for zero-shot object detection. In: AAAI (2020)"},{"key":"7_CR32","unstructured":"Szegedy, C., Toshev, A., Erhan, D.: Deep neural networks for object detection. In: NeurIPS, vol. 26 (2013)"},{"key":"7_CR33","unstructured":"Tay, Y., Bahri, D., Yang, L., Metzler, D., Juan, D.C.: Sparse sinkhorn attention. In: ICML, pp. 9438\u20139447. PMLR (2020)"},{"key":"7_CR34","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020)"},{"key":"7_CR35","unstructured":"Xie, J., Zheng, S.: ZSD-yolo: zero-shot yolo detection using vision-language knowledgedistillationa. arXiv preprint arXiv:2109.12066 (2021)"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: CVPR, pp. 14393\u201314402 (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"7_CR37","unstructured":"Zhang, Y., Zhou, K., Liu, Z.: Neural prompt search. arXiv (2022)"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. In: IJCV (2022)","DOI":"10.1007\/s11263-022-01653-1"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Zhu, P., Wang, H., Saligrama, V.: Don\u2019t even look once: Synthesizing features for zero-shot detection. In: CVPR, pp. 11693\u201311702 (2020)","DOI":"10.1109\/CVPR42600.2020.01171"},{"key":"7_CR41","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 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20077-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T00:07:44Z","timestamp":1667866064000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20077-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200762","9783031200779"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20077-9_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"6 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}