{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:27:55Z","timestamp":1791304075899,"version":"4.3.1"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200526","type":"print"},{"value":"9783031200533","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\/978-3-031-20053-3_16","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:21:52Z","timestamp":1667665312000},"page":"268-284","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":40,"title":["Learning to\u00a0Detect Every Thing in\u00a0an\u00a0Open World"],"prefix":"10.1007","author":[{"given":"Kuniaki","family":"Saito","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kate","family":"Saenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"issue":"11","key":"16_CR1","doi-asserted-by":"publisher","first-page":"2189","DOI":"10.1109\/TPAMI.2012.28","volume":"34","author":"B Alexe","year":"2012","unstructured":"Alexe, B., Deselaers, T., Ferrari, V.: Measuring the objectness of image windows. IEEE TPAMI 34(11), 2189\u20132202 (2012)","journal-title":"IEEE TPAMI"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Arbel\u00e1ez, P., Pont-Tuset, J., Barron, J.T., Marques, F., Malik, J.: Multiscale combinatorial grouping. In: CVPR, pp. 328\u2013335 (2014)","DOI":"10.1109\/CVPR.2014.49"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Bansal, A., Sikka, K., Sharma, G., Chellappa, R., Divakaran, A.: Zero-shot object detection. In: ECCV, pp. 384\u2013400 (2018)","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Bendale, A., Boult, T.E.: Towards open set deep networks. In: CVPR, pp. 1563\u20131572 (2016)","DOI":"10.1109\/CVPR.2016.173"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In: CVPR, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Cen, J., Yun, P., Cai, J., Wang, M.Y., Liu, M.: Deep metric learning for open world semantic segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01505"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Girshick, R., He, K., Dollar, P.: Tensormask: a foundation for dense object segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00215"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: CVPR, pp. 3606\u20133613 (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: ICCV, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Dhamija, A., Gunther, M., Ventura, J., Boult, T.: The overlooked elephant of object detection: open set. In: WACV, pp. 1021\u20131030 (2020)","DOI":"10.1109\/WACV45572.2020.9093355"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: Flownet: learning optical flow with convolutional networks. In: ICCV, pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Dvornik, N., Mairal, J., Schmid, C.: Modeling visual context is key to augmenting object detection datasets. In: ECCV, pp. 364\u2013380 (2018)","DOI":"10.1007\/978-3-030-01258-8_23"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Dwibedi, D., Misra, I., Hebert, M.: Cut, paste and learn: surprisingly easy synthesis for instance detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1301\u20131310 (2017)","DOI":"10.1109\/ICCV.2017.146"},{"issue":"2","key":"16_CR15","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":"16_CR16","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D.: Cascade object detection with deformable part models. In: CVPR, pp. 2241\u20132248. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539906"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., et al.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: CVPR, pp. 2918\u20132928 (2021)","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: ICCV, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Hu, R., Doll\u00e1r, P., He, K., Darrell, T., Girshick, R.: Learning to segment every thing. In: CVPR, pp. 4233\u20134241 (2018)","DOI":"10.1109\/CVPR.2018.00445"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Jaiswal, A., Wu, Y., Natarajan, P., Natarajan, P.: Class-agnostic object detection. In: WACV, pp. 919\u2013928 (2021)","DOI":"10.1109\/WACV48630.2021.00096"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Joseph, K., Khan, S., Khan, F.S., Balasubramanian, V.N.: Towards open world object detection. In: CVPR, pp. 5830\u20135840 (2021)","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"16_CR25","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: ICCV, pp. 8420\u20138429 (2019)","DOI":"10.1109\/ICCV.2019.00851"},{"key":"16_CR26","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. arXiv preprint arXiv:2108.06753 (2021)","DOI":"10.1109\/LRA.2022.3146922"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Kuo, W., Angelova, A., Malik, J., Lin, T.Y.: Shapemask: learning to segment novel objects by refining shape priors. In: ICCV, pp. 9207\u20139216 (2019)","DOI":"10.1109\/ICCV.2019.00930"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"16_CR30","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":"16_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., Yu, S.X.: Large-scale long-tailed recognition in an open world. In: CVPR, pp. 2537\u20132546 (2019)","DOI":"10.1109\/CVPR.2019.00264"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Neuhold, G., Ollmann, T., Rota Bulo, S., Kontschieder, P.: The mapillary vistas dataset for semantic understanding of street scenes. In: ICCV, pp. 4990\u20134999 (2017)","DOI":"10.1109\/ICCV.2017.534"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Perera, P., et al.: Generative-discriminative feature representations for open-set recognition. In: CVPR, pp. 11814\u201311823 (2020)","DOI":"10.1109\/CVPR42600.2020.01183"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"16_CR36","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: ICCV, pp. 8430\u20138439 (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"16_CR38","unstructured":"Tack, J., Mo, S., Jeong, J., Shin, J.: Csi: novelty detection via contrastive learning on distributionally shifted instances. arXiv preprint arXiv:2007.08176 (2020)"},{"issue":"2","key":"16_CR39","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. IJCV 104(2), 154\u2013171 (2013)","journal-title":"IJCV"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Varol, G., et al.: Learning from synthetic humans. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.492"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Wang, W., Feiszli, M., Wang, H., Tran, D.: Unidentified video objects: a benchmark for dense, open-world segmentation. arXiv preprint arXiv:2104.04691 (2021)","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"16_CR42","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Yoshihashi, R., Shao, W., Kawakami, R., You, S., Iida, M., Naemura, T.: Classification-reconstruction learning for open-set recognition. In: CVPR, pp. 4016\u20134025 (2019)","DOI":"10.1109\/CVPR.2019.00414"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: CVPR, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"16_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"CL Zitnick","year":"2014","unstructured":"Zitnick, C.L., Doll\u00e1r, P.: Edge boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 391\u2013405. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_26"}],"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\/978-3-031-20053-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:26:02Z","timestamp":1667665562000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20053-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200526","9783031200533"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20053-3_16","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)"}}]}}