{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T13:20:17Z","timestamp":1773840017171,"version":"3.50.1"},"publisher-location":"Cham","reference-count":36,"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_41","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:21:52Z","timestamp":1667665312000},"page":"701-717","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":124,"title":["PromptDet: Towards Open-Vocabulary Detection Using Uncurated Images"],"prefix":"10.1007","author":[{"given":"Chengjian","family":"Feng","sequence":"first","affiliation":[]},{"given":"Yujie","family":"Zhong","sequence":"additional","affiliation":[]},{"given":"Zequn","family":"Jie","sequence":"additional","affiliation":[]},{"given":"Xiangxiang","family":"Chu","sequence":"additional","affiliation":[]},{"given":"Haibing","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Xiaolin","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Weidi","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Lin","family":"Ma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"key":"41_CR1","doi-asserted-by":"crossref","unstructured":"Akata, Z., Malinowski, M., Fritz, M., Schiele, B.: Multi-cue zero-shot learning with strong supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 59\u201368 (2016)","DOI":"10.1109\/CVPR.2016.14"},{"key":"41_CR2","doi-asserted-by":"crossref","unstructured":"Bansal, A., Sikka, K., Sharma, G., Chellappa, R., Divakaran, A.: Zero-shot object detection. In: Proceedings of the European Conference on Computer Vision. pp. 384\u2013400 (2018)","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"41_CR3","doi-asserted-by":"crossref","unstructured":"Bilen, H., Vedaldi, A.: Weakly supervised deep detection networks. In: CVPR, pp. 2846\u20132854 (2016)","DOI":"10.1109\/CVPR.2016.311"},{"key":"41_CR4","doi-asserted-by":"crossref","unstructured":"Cacheux, Y.L., Borgne, H.L., Crucianu, M.: Modeling inter and intra-class relations in the triplet loss for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10333\u201310342 (2019)","DOI":"10.1109\/ICCV.2019.01043"},{"key":"41_CR5","doi-asserted-by":"crossref","unstructured":"Elhoseiny, M., Zhu, Y., Zhang, H., Elgammal, A.: Link the head to the \u201c beak\": zero shot learning from noisy text description at part precision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5640\u20135649 (2017)","DOI":"10.1109\/CVPR.2017.666"},{"issue":"1","key":"41_CR6","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vision 111(1), 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Fan, Q., Zhuo, W., Tang, C.K., Tai, Y.W.: Few-shot object detection with attention-rpn and multi-relation detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4013\u20134022 (2020)","DOI":"10.1109\/CVPR42600.2020.00407"},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M.R., Huang, W.: Tood: task-aligned one-stage object detection. In: Proceedings of the International Conference on Computer Vision, pp. 3490\u20133499. IEEE Computer Society (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Huang, W.: Exploring classification equilibrium in long-tailed object detection. In: Proceedings of the International Conference on Computer Vision, pp. 3417\u20133426 (2021)","DOI":"10.1109\/ICCV48922.2021.00340"},{"key":"41_CR10","unstructured":"Frome, A., et al.: Devise: a deep visual-semantic embedding model. In: Advances in Neural Information Processing Systems 26 (2013)"},{"key":"41_CR11","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)"},{"key":"41_CR12","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: Lvis: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"41_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"41_CR14","unstructured":"Ji, Z., Fu, Y., Guo, J., Pang, Y., Zhang, Z.M., et al.: Stacked semantics-guided attention model for fine-grained zero-shot learning. In: Advances in Neural Information Processing Systems 31 (2018)"},{"key":"41_CR15","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: Proceedings of the International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"41_CR16","doi-asserted-by":"crossref","unstructured":"Kang, B., Liu, Z., Wang, X., Yu, F., Feng, J., Darrell, T.: Few-shot object detection via feature reweighting. In: Proceedings of the International Conference on Computer Vision, pp. 8420\u20138429 (2019)","DOI":"10.1109\/ICCV.2019.00851"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"Kaul, P., Xie, W., Zisserman, A.: Label, verify, correct: a simple few shot object detection method. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01384"},{"key":"41_CR18","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: Proceedings of the AAAI Conference on Artificial Intelligence (2019)","DOI":"10.1609\/aaai.v33i01.33018690"},{"key":"41_CR19","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 International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"41_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: Proceedings of the European Conference on Computer Vision, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"41_CR21","unstructured":"Mori, Y., Takahashi, H., Oka, R.: Image-to-word transformation based on dividing and vector quantizing images with words. In: MISRM (1999)"},{"key":"41_CR22","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"41_CR23","doi-asserted-by":"crossref","unstructured":"Rahman, S., Khan, S., Barnes, N.: Improved visual-semantic alignment for zero-shot object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i07.6868"},{"key":"41_CR24","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., Wang, R., Mahajan, D.: Dlwl: improving detection for lowshot classes with weakly labelled data. In: CVPR, pp. 9342\u20139352 (2020)","DOI":"10.1109\/CVPR42600.2020.00936"},{"key":"41_CR25","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: CVPR, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"41_CR26","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497 (2015)"},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Stark, M., Schiele, B.: Evaluating knowledge transfer and zero-shot learning in a large-scale setting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2011)","DOI":"10.1109\/CVPR.2011.5995627"},{"key":"41_CR28","unstructured":"Schuhmann, C., et al.: Laion-400m: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"41_CR29","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: Fcos: fully convolutional one-stage object detection. In: Proceedings of the International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"41_CR30","unstructured":"Weston, J., Bengio, S., Usunier, N.: Wsabie: scaling up to large vocabulary image annotation. In: IJCAI (2011)"},{"key":"41_CR31","unstructured":"Xie, J., Zheng, S.: Zsd-yolo: zero-shot yolo detection using vision-language knowledgedistillation. arXiv preprint arXiv:2109.12066 (2021)"},{"key":"41_CR32","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 Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"41_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, H., Puig, X., Zhou, B., Fidler, S., Torralba, A.: Open vocabulary scene parsing. In: Proceedings of the International Conference on Computer Vision, pp. 2002\u20132010 (2017)","DOI":"10.1109\/ICCV.2017.221"},{"key":"41_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1007\/978-3-030-58529-7_28","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Zhong","year":"2020","unstructured":"Zhong, Y., Deng, Z., Guo, S., Scott, M.R., Huang, W.: Representation sharing for fast object detector search and beyond. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 471\u2013487. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_28"},{"key":"41_CR35","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. arXiv preprint arXiv:2109.01134 (2021)"},{"key":"41_CR36","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. arXiv preprint arXiv:2201.02605 (2022)","DOI":"10.1007\/978-3-031-20077-9_21"}],"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_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T00:23:01Z","timestamp":1667866981000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20077-9_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200762","9783031200779"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20077-9_41","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)"}}]}}