{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T03:08:16Z","timestamp":1773976096233,"version":"3.50.1"},"publisher-location":"Cham","reference-count":53,"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_4","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:21:52Z","timestamp":1667665312000},"page":"51-67","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":69,"title":["Point-to-Box Network for\u00a0Accurate Object Detection via\u00a0Single Point Supervision"],"prefix":"10.1007","author":[{"given":"Pengfei","family":"Chen","sequence":"first","affiliation":[]},{"given":"Xuehui","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Xumeng","family":"Han","sequence":"additional","affiliation":[]},{"given":"Najmul","family":"Hassan","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jiachen","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Humphrey","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Zhenjun","family":"Han","sequence":"additional","affiliation":[]},{"given":"Qixiang","family":"Ye","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Arbel\u00e1ez, P.A., Pont-Tuset, J., et al.: Multiscale combinatorial grouping. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.49"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Bilen, H., Vedaldi, A.: Weakly supervised deep detection networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.311"},{"key":"4_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/978-3-642-35289-8_25","volume-title":"Neural Networks: Tricks of the Trade","author":"L Bottou","year":"2012","unstructured":"Bottou, L.: Stochastic gradient descent tricks. In: Montavon, G., Orr, G.B., M\u00fcller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 421\u2013436. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-35289-8_25"},{"key":"4_CR4","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":"4_CR5","unstructured":"Chen, K., Wang, J., Pang, J.E.: MMDetection: open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Fu, Z., et al.: SLV: spatial likelihood voting for weakly supervised object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01301"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, B., Parkhi, O., Kirillov, A.: Pointly-supervised instance segmentation. CoRR (2021)","DOI":"10.1109\/CVPR52688.2022.00264"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., et al.: Weakly supervised cascaded convolutional networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.545"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Long, Y., Xia, G., Lu, Q.: Learning RoI transformer for oriented object detection in aerial images. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00296"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Everingham, M., Gool, L.V., et al.: The pascal visual object classes (VOC) challenge. In: IJCV (2010)","DOI":"10.1007\/s11263-009-0275-4"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Gao, M., Li, A., et al.: C-WSL: count-guided weakly supervised localization. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01246-5_10"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Ge, W., Yang, S., Yu, Y.: Multi-evidence filtering and fusion for multi-label classification, object detection and semantic segmentation based on weakly supervised learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00139"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R.B.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Guo, Z., Liu, C., Zhang, X., Jiao, J., Ji, X., Ye, Q.: Beyond bounding-box: convex-hull feature adaptation for oriented and densely packed object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00868"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., et al.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., et al.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR17","unstructured":"Huang, Z., Zou, Y., et al.: Comprehensive attention self-distillation for weakly-supervised object detection. In: NeurIPS (2020)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Jia, Q., Wei, S., et al.: Gradingnet: towards providing reliable supervisions for weakly supervised object detection by grading the box candidates. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i2.16261"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, N., et al.: Anti-UAV: a large multi-modal benchmark for UAV tracking. IEEE TMM (2021)","DOI":"10.1109\/TMM.2021.3128047"},{"key":"4_CR20","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Lee, P., Byun, H.: Learning action completeness from points for weakly-supervised temporal action localization. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01339"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., et al.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., et al.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"4_CR24","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":"4_CR25","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":"4_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"4_CR27","first-page":"1774","volume":"31","author":"M Meng","year":"2022","unstructured":"Meng, M., Zhang, T., Yang, W., Zhao, J., Zhang, Y., Wu, F.: Diverse complementary part mining for weakly supervised object localization. IEEE TIP 31, 1774\u20131788 (2022)","journal-title":"IEEE TIP"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Papadopoulos, D.P., Uijlings, J.R.R., et al.: Training object class detectors with click supervision. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.27"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., et al.: You only look once: unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"4_CR30","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE TPAMI 39(6), 1137\u20131149 (2017)","journal-title":"IEEE TPAMI"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Ren, Z., Yu, Z., et al.: Instance-aware, context-focused, and memory-efficient weakly supervised object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01061"},{"key":"4_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1007\/978-3-030-58529-7_18","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Ren","year":"2020","unstructured":"Ren, Z., Yu, Z., Yang, X., Liu, M.-Y., Schwing, A.G., Kautz, J.: UFO$$^2$$: a unified framework towards omni-supervised object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 288\u2013313. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_18"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Ribera, J., Guera, D., Chen, Y., Delp, E.J.: Locating objects without bounding boxes. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00664"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"van de Sande, K.E.A., Uijlings, J.R.R., et al.: Segmentation as selective search for object recognition. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126456"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Shen, Y., Ji, R., Chen, Z., Wu, Y., Huang, F.: UWSOD: toward fully-supervised-level capacity weakly supervised object detection. In: NeurIPS (2020)","DOI":"10.1109\/CVPR42600.2020.01134"},{"key":"4_CR36","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Song, Q., et al.: Rethinking counting and localization in crowds: a purely point-based framework. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., et al.: Sparse R-CNN: end-to-end object detection with learnable proposals. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Tang, P., et al.: Multiple instance detection network with online instance classifier refinement. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.326"},{"issue":"1","key":"4_CR40","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1109\/TPAMI.2018.2876304","volume":"42","author":"P Tang","year":"2020","unstructured":"Tang, P., Wang, X., et al.: PCL: proposal cluster learning for weakly supervised object detection. IEEE TPAMI 42(1), 176\u2013191 (2020)","journal-title":"IEEE TPAMI"},{"issue":"10","key":"4_CR41","doi-asserted-by":"publisher","first-page":"2395","DOI":"10.1109\/TPAMI.2019.2898858","volume":"41","author":"F Wan","year":"2019","unstructured":"Wan, F., Wei, P., et al.: Min-entropy latent model for weakly supervised object detection. IEEE TPAMI 41(10), 2395\u20132409 (2019)","journal-title":"IEEE TPAMI"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Yan, G., Liu, B., et al.: C-MIDN: coupled multiple instance detection network with segmentation guidance for weakly supervised object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00993"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Yang, X., Yan, J., Feng, Z., He, T.: R3Det: refined single-stage detector with feature refinement for rotating object. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i4.16426"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Yang, Z., Liu, S., et al.: Reppoints: point set representation for object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00975"},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Yu, X., Chen, P., et al.: Object localization under single coarse point supervision. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00482"},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Yu, X., Gong, Y., et al.: Scale match for tiny person detection. In: IEEE WACV (2020)","DOI":"10.1109\/WACV45572.2020.9093394"},{"key":"4_CR47","doi-asserted-by":"crossref","unstructured":"Zeng, Z., Liu, B., et al.: WSOD2: learning bottom-up and top-down objectness distillation for weakly-supervised object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00838"},{"issue":"9","key":"4_CR48","first-page":"5866","volume":"44","author":"D Zhang","year":"2021","unstructured":"Zhang, D., Han, J., Cheng, G., Yang, M.: Weakly supervised object localization and detection: a survey. IEEE TPAMI 44(9), 5866\u20135885 (2021)","journal-title":"IEEE TPAMI"},{"key":"4_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wei, Y., et al.: Adversarial complementary learning for weakly supervised object localization. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00144"},{"key":"4_CR50","unstructured":"Zhao, J., et al.: The 2nd anti-UAV workshop & challenge: methods and results. In: ICCVW 2021 (2021)"},{"key":"4_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., et al.: Learning deep features for discriminative localization. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"4_CR52","unstructured":"Zhu, X., Su, W., et al.: Deformable DETR: deformable transformers for end-to-end object detection. In: ICLR (2021)"},{"key":"4_CR53","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\/978-3-031-20077-9_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T00:04:50Z","timestamp":1667865890000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20077-9_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200762","9783031200779"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20077-9_4","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)"}}]}}