{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T12:23:30Z","timestamp":1784031810049,"version":"3.55.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012632","type":"print"},{"value":"9783030012649","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01264-9_45","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T08:20:53Z","timestamp":1538986853000},"page":"765-781","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2611,"title":["CornerNet: Detecting Objects as Paired Keypoints"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1009-164X","authenticated-orcid":false,"given":"Hei","family":"Law","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9594-4554","authenticated-orcid":false,"given":"Jia","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"key":"45_CR1","doi-asserted-by":"crossref","unstructured":"Bell, S., Lawrence Zitnick, C., Bala, K., Girshick, R.: Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2874\u20132883 (2016)","DOI":"10.1109\/CVPR.2016.314"},{"key":"45_CR2","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS improving object detection with one line of code. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5562\u20135570. IEEE (2017)","DOI":"10.1109\/ICCV.2017.593"},{"key":"45_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1007\/978-3-319-46493-0_22","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Cai","year":"2016","unstructured":"Cai, Z., Fan, Q., Feris, R.S., Vasconcelos, N.: A unified multi-scale deep convolutional neural network for fast object detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 354\u2013370. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_22"},{"key":"45_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. arXiv preprint arXiv:1712.00726 (2017)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"45_CR5","unstructured":"Chen, Y., Li, J., Xiao, H., Jin, X., Yan, S., Feng, J.: Dual path networks. In: Advances in Neural Information Processing Systems, pp. 4470\u20134478 (2017)"},{"key":"45_CR6","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. arXiv preprint arXiv:1605.06409 (2016)"},{"key":"45_CR7","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. CoRR, abs\/1703.06211, vol. 1(2), p. 3 (2017)"},{"key":"45_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: IEEE Conference on Computer Vision and Pattern Recognition CVPR 2009, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"1","key":"45_CR9","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.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111(1), 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"45_CR10","unstructured":"Fu, C.Y., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: DSSD: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659 (2017)"},{"key":"45_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R.: FAST R-CNN. arXiv preprint arXiv:1504.08083 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"45_CR12","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. arxiv preprint arxiv: 170306870 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"45_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-319-10578-9_23","volume-title":"Computer Vision \u2013 ECCV 2014","author":"K He","year":"2014","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 346\u2013361. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_23"},{"key":"45_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"45_CR16","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: Speed\/accuracy trade-offs for modern convolutional object detectors. In: IEEE CVPR (2017)","DOI":"10.1109\/CVPR.2017.351"},{"key":"45_CR17","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"45_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"45_CR19","doi-asserted-by":"crossref","unstructured":"Kong, T., Sun, F., Yao, A., Liu, H., Lu, M., Chen, Y.: Ron: reverse connection with objectness prior networks for object detection. arXiv preprint arXiv:1707.01691 (2017)","DOI":"10.1109\/CVPR.2017.557"},{"key":"45_CR20","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"45_CR21","unstructured":"Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., Sun, J.: Light-head R-CNN: in defense of two-stage object detector. arXiv preprint arXiv:1711.07264 (2017)"},{"key":"45_CR22","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. arXiv preprint arXiv:1612.03144 (2016)","DOI":"10.1109\/CVPR.2017.106"},{"key":"45_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. arXiv preprint arXiv:1708.02002 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"45_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":"45_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":"45_CR26","unstructured":"Newell, A., Deng, J.: Pixels to graphs by associative embedding. In: Advances in Neural Information Processing Systems, pp. 2168\u20132177 (2017)"},{"key":"45_CR27","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: end-to-end learning for joint detection and grouping. In: Advances in Neural Information Processing Systems, pp. 2274\u20132284 (2017)"},{"key":"45_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"45_CR29","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch (2017)"},{"key":"45_CR30","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"45_CR31","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. arXiv preprint 1612 (2016)","DOI":"10.1109\/CVPR.2017.690"},{"key":"45_CR32","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"45_CR33","doi-asserted-by":"crossref","unstructured":"Shen, Z., Liu, Z., Li, J., Jiang, Y.G., Chen, Y., Xue, X.: DSOD: learning deeply supervised object detectors from scratch. In: The IEEE International Conference on Computer Vision (ICCV), vol. 3, p. 7 (2017)","DOI":"10.1109\/ICCV.2017.212"},{"key":"45_CR34","unstructured":"Shen, Z., et al.: Learning object detectors from scratch with gated recurrent feature pyramids. arXiv preprint arXiv:1712.00886 (2017)"},{"key":"45_CR35","unstructured":"Shrivastava, A., Sukthankar, R., Malik, J., Gupta, A.: Beyond skip connections: top-down modulation for object detection. arXiv preprint arXiv:1612.06851 (2016)"},{"key":"45_CR36","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"45_CR37","doi-asserted-by":"crossref","unstructured":"Singh, B., Davis, L.S.: An analysis of scale invariance in object detection-snip. arXiv preprint arXiv:1711.08189 (2017)","DOI":"10.1109\/CVPR.2018.00377"},{"key":"45_CR38","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI, vol. 4, p. 12 (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"45_CR39","doi-asserted-by":"crossref","unstructured":"Tychsen-Smith, L., Petersson, L.: Denet: scalable real-time object detection with directed sparse sampling. arXiv preprint arXiv:1703.10295 (2017)","DOI":"10.1109\/ICCV.2017.54"},{"key":"45_CR40","doi-asserted-by":"crossref","unstructured":"Tychsen-Smith, L., Petersson, L.: Improving object localization with fitness nms and bounded iou loss. arXiv preprint arXiv:1711.00164 (2017)","DOI":"10.1109\/CVPR.2018.00719"},{"issue":"2","key":"45_CR41","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. Int. J. Comput. Vis. 104(2), 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"45_CR42","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Choi, W., Lin, Y., Savarese, S.: Subcategory-aware convolutional neural networks for object proposals and detection. arXiv preprint arXiv:1604.04693 (2016)","DOI":"10.1109\/WACV.2017.108"},{"key":"45_CR43","doi-asserted-by":"crossref","unstructured":"Xu, H., Lv, X., Wang, X., Ren, Z., Chellappa, R.: Deep regionlets for object detection. arXiv preprint arXiv:1712.02408 (2017)","DOI":"10.1007\/978-3-030-01252-6_49"},{"key":"45_CR44","doi-asserted-by":"crossref","unstructured":"Zhai, Y., Fu, J., Lu, Y., Li, H.: Feature selective networks for object detection. arXiv preprint arXiv:1711.08879 (2017)","DOI":"10.1109\/CVPR.2018.00435"},{"key":"45_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.Z.: Single-shot refinement neural network for object detection. arXiv preprint arXiv:1711.06897 (2017)","DOI":"10.1109\/CVPR.2018.00442"},{"key":"45_CR46","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhao, C., Wang, J., Zhao, X., Wu, Y., Lu, H.: Couplenet: coupling global structure with local parts for object detection. In: Proceedings of International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.444"},{"key":"45_CR47","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 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01264-9_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:58:55Z","timestamp":1665190735000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01264-9_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012632","9783030012649"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01264-9_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"9 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}