{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:52:02Z","timestamp":1766137922362,"version":"3.37.3"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T00:00:00Z","timestamp":1645488000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T00:00:00Z","timestamp":1645488000000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s11263-021-01573-6","type":"journal-article","created":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T10:02:59Z","timestamp":1645524179000},"page":"970-989","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Delving into the Effectiveness of Receptive Fields: Learning Scale-Transferrable Architectures for Practical Object Detection"],"prefix":"10.1007","volume":"130","author":[{"given":"Zhaoxiang","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5959-4294","authenticated-orcid":false,"given":"Cong","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Junran","family":"Peng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,22]]},"reference":[{"key":"1573_CR1","doi-asserted-by":"crossref","unstructured":"Cai, Z., & Vasconcelos, N. (2018). Cascade r-cnn: Delving into high quality object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162.","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1573_CR2","unstructured":"Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., Zhang, Z., Cheng, D., Zhu, C., Cheng, T., Zhao, Q., Li, B., Lu, X., Zhu, R., Wu, Y., Dai, J., Wang, J., Shi, J., Ouyang, W., Loy, C. C., & Lin, D. (2019). Mmdetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155."},{"issue":"4","key":"1573_CR3","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4), 834\u2013848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1573_CR4","unstructured":"Chen, L. C., Papandreou, G., Schroff, F., & Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587."},{"key":"1573_CR5","doi-asserted-by":"publisher","first-page":"107334","DOI":"10.1016\/j.patcog.2020.107334","volume":"105","author":"Q Chen","year":"2020","unstructured":"Chen, Q., Wang, P., Cheng, A., Wang, W., Zhang, Y., & Cheng, J. (2020). Robust one-stage object detection with location-aware classifiers. Pattern Recognition, 105, 107334.","journal-title":"Pattern Recognition"},{"key":"1573_CR6","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017). Deformable convolutional networks. In Proceedings of the IEEE International Conference on Computer Vision, pp. 764\u2013773.","DOI":"10.1109\/ICCV.2017.89"},{"key":"1573_CR7","unstructured":"Fu, C. Y., Liu, W., Ranga, A., Tyagi, A., & Berg, A. C. (2017). Dssd: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659."},{"key":"1573_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"1573_CR9","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":"1573_CR10","unstructured":"Goyal, P., Doll\u00e1r, P., Girshick, R., Noordhuis, P., Wesolowski, L., Kyrola, A., Tulloch, A., Jia, Y., & He, K. (2017). Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677."},{"key":"1573_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Girshick, R., & Doll\u00e1r, P. (2019). Rethinking imagenet pre-training. Proceedings of the IEEE International Conference on Computer Vision, pp. 4918\u20134927.","DOI":"10.1109\/ICCV.2019.00502"},{"key":"1573_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"1573_CR13","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"},{"issue":"9","key":"1573_CR14","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2015). Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(9), 1904\u20131916.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1573_CR15","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":"1573_CR16","unstructured":"Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861."},{"key":"1573_CR17","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1573_CR18","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"1573_CR19","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the International Conference on Machine Learning, pp. 448\u2013456."},{"key":"1573_CR20","first-page":"2017","volume":"28","author":"M Jaderberg","year":"2015","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., & Kavukcuoglu, K. (2015). Spatial transformer networks. Advances in Neural Information Processing Systems, 28, 2017\u20132025.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1573_CR21","doi-asserted-by":"crossref","unstructured":"Jeon, Y., & Kim, J. (2017). Active convolution: Learning the shape of convolution for image classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4201\u20134209.","DOI":"10.1109\/CVPR.2017.200"},{"key":"1573_CR22","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 Proceedings of the European Conference on Computer Vision, pp. 784\u2013799.","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"1573_CR23","doi-asserted-by":"crossref","unstructured":"Law, H., & Deng, J. (2018). Cornernet: Detecting objects as paired keypoints. In Proceedings of the European Conference on Computer Vision, pp. 734\u2013750.","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"1573_CR24","doi-asserted-by":"crossref","unstructured":"Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., & Sun, J. (2018). Detnet: Design backbone for object detection. In Proceedings of the European Conference on Computer Vision, pp. 334\u2013350.","DOI":"10.1007\/978-3-030-01240-3_21"},{"key":"1573_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"1573_CR26","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"1573_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In Proceedings of the European Conference on Computer Vision, pp. 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1573_CR28","doi-asserted-by":"crossref","unstructured":"Liu, S., Huang, D., & Wang, Y. (2018). Receptive field block net for accurate and fast object detection. In Proceedings of the European Conference on Computer Vision, pp. 385\u2013400.","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"1573_CR29","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016). Ssd: Single shot multibox detector. In Proceedings of the European Conference on Computer Vision, pp. 21\u201337.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1573_CR30","doi-asserted-by":"crossref","unstructured":"Peng, J., Sun, M., Zhang, Z., Tan, T., & Yan, J. (2019). Pod: Practical object detection with scale-sensitive network. In Proceedings of the IEEE International Conference on Computer Vision, pp. 9607\u20139616.","DOI":"10.1109\/ICCV.2019.00970"},{"key":"1573_CR31","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":"1573_CR32","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":"1573_CR33","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, pp. 91\u201399."},{"issue":"3","key":"1573_CR34","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., & Berg, A. C. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"1573_CR35","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1573_CR36","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":"1573_CR37","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations."},{"key":"1573_CR38","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1573_CR39","doi-asserted-by":"crossref","unstructured":"Tychsen-Smith, L., & Petersson, L. (2018). Improving object localization with fitness nms and bounded iou loss. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6877\u20136885.","DOI":"10.1109\/CVPR.2018.00719"},{"issue":"2","key":"1573_CR40","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":"1573_CR41","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500.","DOI":"10.1109\/CVPR.2017.634"},{"key":"1573_CR42","doi-asserted-by":"crossref","unstructured":"Xu, H., Lv, X., Wang, X., Ren, Z., Bodla, N., & Chellappa, R. (2018). Deep regionlets for object detection. In Proceedings of the European Conference on Computer Vision, pp. 798\u2013814.","DOI":"10.1007\/978-3-030-01252-6_49"},{"key":"1573_CR43","doi-asserted-by":"publisher","first-page":"107098","DOI":"10.1016\/j.patcog.2019.107098","volume":"99","author":"J Xu","year":"2020","unstructured":"Xu, J., Wang, W., Wang, H., & Guo, J. (2020). Multi-model ensemble with rich spatial information for object detection. Pattern Recognition, 99, 107098.","journal-title":"Pattern Recognition"},{"key":"1573_CR44","unstructured":"Yu, F., & Koltun, V. (2016). Multi-scale context aggregation by dilated convolutions. In International Conference on Learning Representations."},{"key":"1573_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, R., Tang, S., Zhang, Y., Li, J., & Yan, S. (2017). Scale-adaptive convolutions for scene parsing. In Proceedings of the IEEE International Conference on Computer Vision, pp. 2031\u20132039.","DOI":"10.1109\/ICCV.2017.224"},{"key":"1573_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., & Li, S. Z. (2020). Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9759\u20139768.","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"1573_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, Z., & Li, S. Z. (2018). Single-shot refinement neural network for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4203\u20134212.","DOI":"10.1109\/CVPR.2018.00442"},{"key":"1573_CR48","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid scene parsing network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881\u20132890.","DOI":"10.1109\/CVPR.2017.660"},{"key":"1573_CR49","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., & Dai, J. (2019). Deformable convnets v2: More deformable, better results. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9308\u20139316.","DOI":"10.1109\/CVPR.2019.00953"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01573-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01573-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01573-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,25]],"date-time":"2022-03-25T10:38:07Z","timestamp":1648204687000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01573-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,22]]},"references-count":49,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["1573"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01573-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2022,2,22]]},"assertion":[{"value":"8 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 November 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}