{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T19:47:15Z","timestamp":1785181635428,"version":"3.55.0"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030584511","type":"print"},{"value":"9783030584528","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58452-8_13","type":"book-chapter","created":{"date-parts":[[2020,11,3]],"date-time":"2020-11-03T00:34:03Z","timestamp":1604363643000},"page":"213-229","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13326,"title":["End-to-End Object Detection with Transformers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2308-9680","authenticated-orcid":false,"given":"Nicolas","family":"Carion","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0697-6664","authenticated-orcid":false,"given":"Francisco","family":"Massa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1715-3356","authenticated-orcid":false,"given":"Gabriel","family":"Synnaeve","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9324-1457","authenticated-orcid":false,"given":"Nicolas","family":"Usunier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3169-3199","authenticated-orcid":false,"given":"Alexander","family":"Kirillov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9684-5240","authenticated-orcid":false,"given":"Sergey","family":"Zagoruyko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,3]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Al-Rfou, R., Choe, D., Constant, N., Guo, M., Jones, L.: Character-level language modeling with deeper self-attention. In: AAAI Conference on Artificial Intelligence (2019)","DOI":"10.1609\/aaai.v33i01.33013159"},{"key":"13_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Vaswani, A., Shlens, J., Le, Q.V.: Attention augmented convolutional networks. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00338"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS\u2014improving object detection with one line of code. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.593"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: high quality object detection and instance segmentation. PAMI (2019)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"13_CR6","unstructured":"Chan, W., Saharia, C., Hinton, G., Norouzi, M., Jaitly, N.: Imputer: sequence modelling via imputation and dynamic programming. arXiv:2002.08926 (2020)"},{"key":"13_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2019)"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Erhan, D., Szegedy, C., Toshev, A., Anguelov, D.: Scalable object detection using deep neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.276"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Ghazvininejad, M., Levy, O., Liu, Y., Zettlemoyer, L.: Mask-predict: parallel decoding of conditional masked language models. arXiv:1904.09324 (2019)","DOI":"10.18653\/v1\/D19-1633"},{"key":"13_CR10","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: AISTATS (2010)"},{"key":"13_CR11","unstructured":"Gu, J., Bradbury, J., Xiong, C., Li, V.O., Socher, R.: Non-autoregressive neural machine translation. In: ICLR (2018)"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Girshick, R., Doll\u00e1r, P.: Rethinking imagenet pre-training. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00502"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"13_CR14","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":"13_CR15","doi-asserted-by":"crossref","unstructured":"Hosang, J.H., Benenson, R., Schiele, B.: Learning non-maximum suppression. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.685"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R., Rother, C., Dollar, P.: Panoptic segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00963"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem (1955)","DOI":"10.1002\/nav.3800020109"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, H., Dai, J., Ji, X., Wei, Y.: Fully convolutional instance-aware semantic segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.472"},{"key":"13_CR21","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 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"13_CR22","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 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"13_CR23","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":"13_CR24","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., et al.: 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":"13_CR25","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2017)"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"L\u00fcscher, C., et al.: RWTH ASR systems for LibriSpeech: hybrid vs attention - w\/o data augmentation. arXiv:1905.03072 (2019)","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 3DV (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"13_CR28","unstructured":"Oord, A., et al.: Parallel wavenet: fast high-fidelity speech synthesis. arXiv:1711.10433 (2017)"},{"key":"13_CR29","unstructured":"Park, E., Berg, A.C.: Learning to decompose for object detection and instance segmentation. arXiv:1511.06449 (2015)"},{"key":"13_CR30","unstructured":"Parmar, N., et al.: Image transformer. In: ICML (2018)"},{"key":"13_CR31","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)"},{"key":"13_CR32","unstructured":"Pineda, L., Salvador, A., Drozdzal, M., Romero, A.: Elucidating image-to-set prediction: an analysis of models, losses and datasets. arXiv:1904.05709 (2019)"},{"key":"13_CR33","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)"},{"key":"13_CR34","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":"13_CR35","doi-asserted-by":"crossref","unstructured":"Ren, M., Zemel, R.S.: End-to-end instance segmentation with recurrent attention. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.39"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. PAMI 39 (2015)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"13_CR37","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union. In: CVPR (2019)"},{"key":"13_CR38","unstructured":"Rezatofighi, S.H., et al.: Deep perm-set net: learn to predict sets with unknown permutation and cardinality using deep neural networks. arXiv:1805.00613 (2018)"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Rezatofighi, S.H., et al.: Deepsetnet: predicting sets with deep neural networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.561"},{"key":"13_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1007\/978-3-319-46466-4_19","volume-title":"Computer Vision \u2013 ECCV 2016","author":"B Romera-Paredes","year":"2016","unstructured":"Romera-Paredes, B., Torr, P.H.S.: Recurrent instance segmentation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 312\u2013329. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_19"},{"key":"13_CR41","unstructured":"Salvador, A., Bellver, M., Baradad, M., Marqu\u00e9s, F., Torres, J., Gir\u00f3, X.: Recurrent neural networks for semantic instance segmentation. arXiv:1712.00617 (2017)"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Stewart, R.J., Andriluka, M., Ng, A.Y.: End-to-end people detection in crowded scenes. In: CVPR (2015)","DOI":"10.1109\/CVPR.2016.255"},{"key":"13_CR43","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NeurIPS (2014)"},{"key":"13_CR44","unstructured":"Synnaeve, G., et al.: End-to-end ASR: from supervised to semi-supervised learning with modern architectures. arXiv:1911.08460 (2019)"},{"key":"13_CR45","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"13_CR46","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"13_CR47","unstructured":"Vinyals, O., Bengio, S., Kudlur, M.: Order matters: sequence to sequence for sets. In: ICLR (2016)"},{"key":"13_CR48","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R.B., Gupta, A., He, K.: Non-local neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"13_CR49","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"13_CR50","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et al.: Upsnet: a unified panoptic segmentation network. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00902"},{"key":"13_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. arXiv:1912.02424 (2019)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"13_CR52","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv:1904.07850 (2019)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58452-8_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:08:22Z","timestamp":1730592502000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58452-8_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030584511","9783030584528"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"3 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}