{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T15:30:51Z","timestamp":1781710251475,"version":"3.54.5"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200793","type":"print"},{"value":"9783031200809","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\/978-3-031-20080-9_5","type":"book-chapter","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T19:59:12Z","timestamp":1667419152000},"page":"70-86","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Efficient Decoder-Free Object Detection with\u00a0Transformers"],"prefix":"10.1007","author":[{"given":"Peixian","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengdan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunhang","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kekai","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuting","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"5_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":"5_CR3","unstructured":"Chen, K., et al.: MMDetection: open MMLAB detection toolbox and benchmark. arXiv (2019)"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Q., Wang, Y., Yang, T., Zhang, X., Cheng, J., Sun, J.: You only look one-level feature. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13039\u201313048 (2021)","DOI":"10.1109\/CVPR46437.2021.01284"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Mobile-former: bridging MobileNet and transformer. arXiv (2021)","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"5_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1007\/978-3-030-01267-0_28","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Cheng","year":"2018","unstructured":"Cheng, B., Wei, Y., Shi, H., Feris, R., Xiong, J., Huang, T.: Revisiting RCNN: on awakening the classification power of faster RCNN. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 473\u2013490. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_28"},{"key":"5_CR7","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":"5_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet: keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6569\u20136578 (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"5_CR10","unstructured":"El-Nouby, A., et al.: XCiT: cross-covariance image transformers. arXiv (2021)"},{"key":"5_CR11","unstructured":"Fang, Y., et al.: You only look at one sequence: rethinking transformer in vision through object detection. arXiv (2021)"},{"key":"5_CR12","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 IEEE\/CVF International Conference on Computer Vision, pp. 3510\u20133519 (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"5_CR13","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 (2021)","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Gao, Z., Wang, L., Wu, G.: Mutual supervision for dense object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3641\u20133650 (2021)","DOI":"10.1109\/ICCV48922.2021.00362"},{"key":"5_CR15","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding YOLO series in 2021. arXiv (2021)"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., Le, Q.V.: NAS-FPN: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7036\u20137045 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference On Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"5_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv (2014)"},{"key":"5_CR19","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"5_CR20","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":"5_CR21","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":"5_CR22","doi-asserted-by":"crossref","unstructured":"Liu, F., Wei, H., Zhao, W., Li, G., Peng, J., Li, Z.: WB-DETR: transformer-based detector without backbone. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2979\u20132987 (2021)","DOI":"10.1109\/ICCV48922.2021.00297"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional DETR for fast training convergence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"5_CR26","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Song, G., Liu, Y., Wang, X.: Revisiting the sibling head in object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11563\u201311572 (2020)","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Sun, Z., Cao, S., Yang, Y., Kitani, K.M.: Rethinking transformer-based set prediction for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3611\u20133620 (2021)","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"5_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 IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. arXiv (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor DETR: query design for transformer-based detector. arXiv (2021)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Xu, H., Yao, L., Zhang, W., Liang, X., Li, Z.: Auto-FPN: automatic network architecture adaptation for object detection beyond classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6649\u20136658 (2019)","DOI":"10.1109\/ICCV.2019.00675"},{"key":"5_CR33","unstructured":"Yang, J., et al.: Focal self-attention for local-global interactions in vision transformers. arXiv (2021)"},{"key":"5_CR34","unstructured":"Yao, Z., Ai, J., Li, B., Zhang, C.: Efficient DETR: improving end-to-end object detector with dense prior. arXiv (2021)"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, Q., et al.: M2Det: a single-shot object detector based on multi-level feature pyramid network. In: Proceedings of the AAAI, vol. 33, pp. 9259\u20139266 (2019)","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"5_CR36","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv (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\/978-3-031-20080-9_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T00:23:28Z","timestamp":1667780608000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20080-9_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200793","9783031200809"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20080-9_5","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":"3 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)"}}]}}