{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:41:23Z","timestamp":1775745683982,"version":"3.50.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T00:00:00Z","timestamp":1565222400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T00:00:00Z","timestamp":1565222400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s11263-019-01204-1","type":"journal-article","created":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T11:02:25Z","timestamp":1565262145000},"page":"642-656","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":662,"title":["CornerNet: Detecting Objects as Paired Keypoints"],"prefix":"10.1007","volume":"128","author":[{"given":"Hei","family":"Law","sequence":"first","affiliation":[]},{"given":"Jia","family":"Deng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,8,8]]},"reference":[{"key":"1204_CR1","doi-asserted-by":"crossref","unstructured":"Bell, S., Lawrence Zitnick, C., Bala, K., & Girshick, R. (2016). 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).","DOI":"10.1109\/CVPR.2016.314"},{"key":"1204_CR2","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., & Davis, L.\u00a0S. (2017). Soft-NMS\u2014Improving object detection with one line of code. In 2017 IEEE international conference on computer vision (ICCV) (pp. 5562\u20135570). IEEE.","DOI":"10.1109\/ICCV.2017.593"},{"key":"1204_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Z., Fan, Q., Feris, R.\u00a0S., & Vasconcelos, N. (2016). A unified multi-scale deep convolutional neural network for fast object detection. In European conference on computer vision (pp. 354\u2013370). Springer.","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"1204_CR4","unstructured":"Cai, Z., & Vasconcelos, N. (2017). Cascade R-CNN: Delving into high quality object detection. arXiv preprint arXiv:1712.00726 ."},{"key":"1204_CR5","unstructured":"Chen, Y., Li, J., Xiao, H., Jin, X., Yan, S., & Feng, J. (2017). Dual path networks. In Advances in neural information processing systems (pp. 4470\u20134478)."},{"key":"1204_CR6","unstructured":"Dai, J., Li, Y., He, K., & Sun, J. (2016). R-FCN: Object detection via region-based fully convolutional networks. arXiv preprint arXiv:1605.06409 ."},{"key":"1204_CR7","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017). Deformable convolutional networks. CoRR, arXiv:1703.06211 ."},{"key":"1204_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In IEEE conference on computer vision and pattern recognition, CVPR 2009 (pp. 248\u2013255). IEEE.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1204_CR9","doi-asserted-by":"crossref","unstructured":"Erhan, D., Szegedy, C., Toshev, A., & Anguelov, D. (2014). Scalable object detection using deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2147\u20132154).","DOI":"10.1109\/CVPR.2014.276"},{"issue":"1","key":"1204_CR10","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. (2015). The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111(1), 98\u2013136.","journal-title":"International Journal of Computer Vision"},{"key":"1204_CR11","unstructured":"Fu, C.-Y., Liu, W., Ranga, A., Tyagi, A., & Berg, A.\u00a0C. (2017). Dssd: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659 ."},{"key":"1204_CR12","unstructured":"Girshick, R. (2015). Fast R-CNN. arXiv preprint arXiv:1504.08083 ."},{"key":"1204_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). 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).","DOI":"10.1109\/CVPR.2014.81"},{"key":"1204_CR14","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask R-CNN. arxiv preprint arxiv: 170306870 ."},{"key":"1204_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2014). Spatial pyramid pooling in deep convolutional networks for visual recognition. In European conference on computer vision (pp. 346\u2013361). Springer.","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"1204_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision (pp. 1026\u20131034).","DOI":"10.1109\/ICCV.2015.123"},{"key":"1204_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1204_CR18","doi-asserted-by":"crossref","unstructured":"Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., Fischer, I., Wojna, Z., Song, Y., Guadarrama, S., et al. (2017). Speed\/accuracy trade-offs for modern convolutional object detectors. In IEEE CVPR.","DOI":"10.1109\/CVPR.2017.351"},{"key":"1204_CR19","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning (pp. 448\u2013456)."},{"key":"1204_CR20","doi-asserted-by":"crossref","unstructured":"Jiang, B., Luo, R., Mao, J., Xiao, T., & Jiang, Y. (2018). Acquisition of localization confidence for accurate object detection. In Computer Vision\u2013ECCV 2018 (pp. 816\u2013832). Springer.","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"1204_CR21","unstructured":"Kingma, D.\u00a0P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 ."},{"key":"1204_CR22","unstructured":"Kong, T., Sun, F., Yao, A., Liu, H., Lu, M., & Chen, Y. (2017). Ron: Reverse connection with objectness prior networks for object detection. arXiv preprint arXiv:1707.01691 ."},{"key":"1204_CR23","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097\u20131105)."},{"key":"1204_CR24","unstructured":"Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., & Sun, J. (2017). Light-head R-CNN: In defense of two-stage object detector. arXiv preprint arXiv:1711.07264 ."},{"key":"1204_CR25","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2016). Feature pyramid networks for object detection. arXiv preprint arXiv:1612.03144 ."},{"key":"1204_CR26","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2017). Focal loss for dense object detection. arXiv preprint arXiv:1708.02002 ."},{"key":"1204_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C.\u00a0L. (2014). Microsoft coco: Common objects in context. In European conference on computer vision (pp. 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1204_CR28","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A.\u00a0C. (2016). Ssd: Single shot multibox detector. In European conference on computer vision (pp. 21\u201337). Springer.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1204_CR29","unstructured":"Newell, A., & Deng, J. (2017). Pixels to graphs by associative embedding. In Advances in neural information processing systems (pp. 2168\u20132177)."},{"key":"1204_CR30","unstructured":"Newell, A., Huang, Z., & Deng, J. (2017). Associative embedding: End-to-end learning for joint detection and grouping. In Advances in neural information processing systems (pp. 2274\u20132284)."},{"key":"1204_CR31","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., & Deng, J. (2016). Stacked hourglass networks for human pose estimation. In European conference on computer vision (pp. 483\u2013499). Springer.","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"1204_CR32","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., & Lerer, A. (2017). Automatic differentiation in pytorch."},{"key":"1204_CR33","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779\u2013788).","DOI":"10.1109\/CVPR.2016.91"},{"key":"1204_CR34","unstructured":"Redmon, J., & Farhadi, A. (2016). Yolo9000: Better, faster, stronger. arXiv preprint, 1612."},{"key":"1204_CR35","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems (pp. 91\u201399)."},{"key":"1204_CR36","doi-asserted-by":"crossref","unstructured":"Shen, Z., Liu, Z., Li, J., Jiang, Y.-G., Chen, Y., & Xue, X. (2017a). Dsod: Learning deeply supervised object detectors from scratch. In The IEEE international conference on computer vision (ICCV) (Vol. 3, p. 7).","DOI":"10.1109\/ICCV.2017.212"},{"key":"1204_CR37","unstructured":"Shen, Z., Shi, H., Feris, R., Cao, L., Yan, S., Liu, D., Wang, X., Xue, X., & Huang, T.\u00a0S. (2017b). Learning object detectors from scratch with gated recurrent feature pyramids. arXiv preprint arXiv:1712.00886 ."},{"key":"1204_CR38","unstructured":"Shrivastava, A., Sukthankar, R., Malik, J., & Gupta, A. (2016). Beyond skip connections: Top-down modulation for object detection. arXiv preprint arXiv:1612.06851 ."},{"key":"1204_CR39","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ."},{"key":"1204_CR40","unstructured":"Singh, B., & Davis, L.\u00a0S. (2017). An analysis of scale invariance in object detection-snip. arXiv preprint arXiv:1711.08189 ."},{"key":"1204_CR41","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A.\u00a0A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. In AAAI (Vol. 4, p. 12).","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1204_CR42","doi-asserted-by":"crossref","unstructured":"Tychsen-Smith, L., & Petersson, L. (2017a). Denet: Scalable real-time object detection with directed sparse sampling. arXiv preprint arXiv:1703.10295 .","DOI":"10.1109\/ICCV.2017.54"},{"key":"1204_CR43","doi-asserted-by":"crossref","unstructured":"Tychsen-Smith, L., & Petersson, L. (2017b). Improving object localization with fitness NMS and bounded IOU loss. arXiv preprint arXiv:1711.00164 .","DOI":"10.1109\/CVPR.2018.00719"},{"issue":"2","key":"1204_CR44","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. (2013). Selective search for object recognition. International Journal of Computer Vision, 104(2), 154\u2013171.","journal-title":"International Journal of Computer Vision"},{"key":"1204_CR45","unstructured":"Wang, X., Chen, K., Huang, Z., Yao, C., & Liu, W. (2017). Point linking network for object detection. arXiv preprint arXiv:1706.03646 ."},{"key":"1204_CR46","unstructured":"Xiang, Y., Choi, W., Lin, Y., & Savarese, S. (2016). Subcategory-aware convolutional neural networks for object proposals and detection. arXiv preprint arXiv:1604.04693 ."},{"key":"1204_CR47","unstructured":"Xu, H., Lv, X., Wang, X., Ren, Z., & Chellappa, R. (2017). Deep regionlets for object detection. arXiv preprint arXiv:1712.02408 ."},{"key":"1204_CR48","unstructured":"Zhai, Y., Fu, J., Lu, Y., & Li, H. (2017). Feature selective networks for object detection. arXiv preprint arXiv:1711.08879 ."},{"key":"1204_CR49","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, Z., & Li, S.\u00a0Z. (2017). Single-shot refinement neural network for object detection. arXiv preprint arXiv:1711.06897 ."},{"key":"1204_CR50","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhao, C., Wang, J., Zhao, X., Wu, Y., & Lu, H. (2017). Couplenet: Coupling global structure with local parts for object detection. In Proceedings of international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.444"},{"key":"1204_CR51","doi-asserted-by":"crossref","unstructured":"Zitnick, C.\u00a0L., Doll\u00e1r, P. (2014). Edge boxes: Locating object proposals from edges. In European conference on computer vision (pp. 391\u2013405). Springer.","DOI":"10.1007\/978-3-319-10602-1_26"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01204-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-019-01204-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01204-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T09:39:17Z","timestamp":1664098757000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-019-01204-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,8]]},"references-count":51,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["1204"],"URL":"https:\/\/doi.org\/10.1007\/s11263-019-01204-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,8]]},"assertion":[{"value":"1 February 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}