{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:10:37Z","timestamp":1778166637681,"version":"3.51.4"},"reference-count":80,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,8,19]],"date-time":"2020-08-19T00:00:00Z","timestamp":1597795200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,8,19]],"date-time":"2020-08-19T00:00:00Z","timestamp":1597795200000},"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":[[2021,1]]},"DOI":"10.1007\/s11263-020-01370-7","type":"journal-article","created":{"date-parts":[[2020,8,19]],"date-time":"2020-08-19T06:02:55Z","timestamp":1597816975000},"page":"142-160","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Recursive Context Routing for Object Detection"],"prefix":"10.1007","volume":"129","author":[{"given":"Zhe","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,8,19]]},"reference":[{"issue":"2","key":"1370_CR1","doi-asserted-by":"publisher","first-page":"332","DOI":"10.3758\/BF03194073","volume":"14","author":"ME Auckland","year":"2007","unstructured":"Auckland, M. E., Cave, K. R., & Donnelly, N. (2007). Nontarget objects can influence perceptual processes during object recognition. Psychonomic Bulletin Review, 14(2), 332\u2013337.","journal-title":"Psychonomic Bulletin Review"},{"key":"1370_CR2","doi-asserted-by":"crossref","unstructured":"Bell, S., Lawrence\u00a0Zitnick, C., Bala, K., & Girshick, R. (2016). Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks. In CVPR (pp. 2874\u20132883). IEEE.","DOI":"10.1109\/CVPR.2016.314"},{"issue":"3","key":"1370_CR3","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1037\/h0037158","volume":"103","author":"I Biederman","year":"1974","unstructured":"Biederman, I., Rabinowitz, J. C., Glass, A. L., & Stacy, E. W. (1974). On the information extracted from a glance at a scene. Journal of Experimental Psychology, 103(3), 597.","journal-title":"Journal of Experimental Psychology"},{"issue":"2","key":"1370_CR4","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/0010-0285(82)90007-X","volume":"14","author":"I Biederman","year":"1982","unstructured":"Biederman, I., Mezzanotte, R. J., & Rabinowitz, J. C. (1982). Scene perception: Detecting and judging objects undergoing relational violations. Cognitive Psychology, 14(2), 143\u2013177.","journal-title":"Cognitive Psychology"},{"issue":"3","key":"1370_CR5","first-page":"556","volume":"15","author":"SJ Boyce","year":"1989","unstructured":"Boyce, S. J., Pollatsek, A., & Rayner, K. (1989). Effect of background information on object identification. Journal of Experimental Psychology: Human Perception and Performance, 15(3), 556.","journal-title":"Journal of Experimental Psychology: Human Perception and Performance"},{"issue":"4","key":"1370_CR6","first-page":"699","volume":"32","author":"JR Brockmole","year":"2006","unstructured":"Brockmole, J. R., Castelhano, M. S., & Henderson, J. M. (2006). Contextual cueing in naturalistic scenes: Global and local contexts. Journal of Experimental Psychology: Learning, Memory, and Cognition, 32(4), 699.","journal-title":"Journal of Experimental Psychology: Learning, Memory, and Cognition"},{"issue":"12","key":"1370_CR7","doi-asserted-by":"publisher","first-page":"1886","DOI":"10.1080\/17470210701781155","volume":"61","author":"JR Brockmole","year":"2008","unstructured":"Brockmole, J. R., Hambrick, D. Z., Windisch, D. J., & Henderson, J. M. (2008). The role of meaning in contextual cueing: Evidence from chess expertise. The Quarterly Journal of Experimental Psychology, 61(12), 1886\u20131896.","journal-title":"The Quarterly Journal of Experimental Psychology"},{"key":"1370_CR8","doi-asserted-by":"crossref","unstructured":"Cai, Z., & Vasconcelos, N. (2018). Cascade r-cnn: Delving into high quality object detection. In CVPR. IEEE.","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1370_CR9","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., & Hu, H. (2019). Gcnet: Non-local networks meet squeeze-excitation networks and beyond. arXiv preprint arXiv:1904.11492.","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"1370_CR10","doi-asserted-by":"crossref","unstructured":"Chen, K., Pang, J., Wang, J., Xiong, Y., Li, X., Sun, S., et\u00a0al. (2019a). Hybrid task cascade for instance segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4974\u20134983).","DOI":"10.1109\/CVPR.2019.00511"},{"issue":"4","key":"1370_CR11","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2017a). 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":"1370_CR12","unstructured":"Chen, L. C., Papandreou, G., Schroff, F., & Adam, H. (2017b). Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587."},{"key":"1370_CR13","doi-asserted-by":"crossref","unstructured":"Chen, X., & Gupta, A. (2017). Spatial memory for context reasoning in object detection. In ICCV (pp. 4106\u20134116). IEEE.","DOI":"10.1109\/ICCV.2017.440"},{"key":"1370_CR14","doi-asserted-by":"crossref","unstructured":"Chen, X., Li, L. J., Fei-Fei, L., & Gupta, A. (2018a). Iterative visual reasoning beyond convolutions. In CVPR. IEEE.","DOI":"10.1109\/CVPR.2018.00756"},{"key":"1370_CR15","doi-asserted-by":"crossref","unstructured":"Chen, Y., Rohrbach, M., Yan, Z., Shuicheng, Y., Feng, J., & Kalantidis, Y. (2019b). Graph-based global reasoning networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 433\u2013442).","DOI":"10.1109\/CVPR.2019.00052"},{"key":"1370_CR16","doi-asserted-by":"crossref","unstructured":"Chen, Z., Huang, S., & Tao, D. (2018b). Context refinement for object detection. In Proceedings of the European conference on computer vision (ECCV) (pp. 71\u201386). Springer, Berlin.","DOI":"10.1007\/978-3-030-01237-3_5"},{"key":"1370_CR17","doi-asserted-by":"crossref","unstructured":"Choi, M. J., Lim, J. J., Torralba, A., & Willsky, A. S. (2010). Exploiting hierarchical context on a large database of object categories. In: CVPR (pp. 129\u2013136). IEEE.","DOI":"10.1109\/CVPR.2010.5540221"},{"issue":"1","key":"1370_CR18","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1006\/cogp.1998.0681","volume":"36","author":"MM Chun","year":"1998","unstructured":"Chun, M. M., & Jiang, Y. (1998). Contextual cueing: Implicit learning and memory of visual context guides spatial attention. Cognitive Psychology, 36(1), 28\u201371.","journal-title":"Cognitive Psychology"},{"issue":"4","key":"1370_CR19","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1111\/1467-9280.00168","volume":"10","author":"MM Chun","year":"1999","unstructured":"Chun, M. M., & Jiang, Y. (1999). Top-down attentional guidance based on implicit learning of visual covariation. Psychological Science, 10(4), 360\u2013365.","journal-title":"Psychological Science"},{"issue":"2","key":"1370_CR20","first-page":"224","volume":"29","author":"MM Chun","year":"2003","unstructured":"Chun, M. M., & Jiang, Y. (2003). Implicit, long-term spatial contextual memory. Journal of Experimental Psychology: Learning, Memory, and Cognition, 29(2), 224.","journal-title":"Journal of Experimental Psychology: Learning, Memory, and Cognition"},{"key":"1370_CR21","unstructured":"Dai, J., Li, Y., He, K., & Sun, J. (2016). R-fcn: Object detection via region-based fully convolutional networks. In NIPS (pp. 379\u2013387)."},{"key":"1370_CR22","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., et al. (2017). Deformable convolutional networks. In ICCV. IEEE.","DOI":"10.1109\/ICCV.2017.89"},{"issue":"8","key":"1370_CR23","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1111\/j.0956-7976.2004.00719.x","volume":"15","author":"JL Davenport","year":"2004","unstructured":"Davenport, J. L., & Potter, M. C. (2004). Scene consistency in object and background perception. Psychological Science, 15(8), 559\u2013564.","journal-title":"Psychological Science"},{"issue":"3","key":"1370_CR24","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1037\/h0084324","volume":"46","author":"P De Graef","year":"1992","unstructured":"De Graef, P., De Troy, A., & d\u2019Ydewalle, G. (1992). Local and global contextual constraints on the identification of objects in scenes. Canadian Journal of Psychology\/Revue canadienne de psychologie, 46(3), 489.","journal-title":"Canadian Journal of Psychology\/Revue canadienne de psychologie"},{"key":"1370_CR25","doi-asserted-by":"crossref","unstructured":"Divvala, S. K., Hoiem, D., Hays, J. H., Efros, A. A., & Hebert, M. (2009). An empirical study of context in object detection. In CVPR (pp. 1271\u20131278). IEEE.","DOI":"10.1109\/CVPR.2009.5206532"},{"key":"1370_CR26","unstructured":"Everingham, M., Van\u00a0Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2007). The pascal visual object classes challenge 2007 (voc2007) results."},{"key":"1370_CR27","first-page":"303","volume-title":"The pascal visual object classes (voc) challenge","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge (Vol. 88, pp. 303\u2013338). Berlin: Springer."},{"issue":"6","key":"1370_CR28","first-page":"712","volume":"114","author":"C Galleguillos","year":"2010","unstructured":"Galleguillos, C., & Belongie, S. (2010). Context based object categorization: A critical survey. CVIU, 114(6), 712\u2013722.","journal-title":"CVIU"},{"key":"1370_CR29","doi-asserted-by":"crossref","unstructured":"Galleguillos, C., Rabinovich, A., & Belongie, S. (2008). Object categorization using co-occurrence, location and appearance. In CVPR (pp. 1\u20138). IEEE.","DOI":"10.1109\/CVPR.2008.4587799"},{"key":"1370_CR30","first-page":"1231","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013). Vision meets robotics: The kitti dataset. IJRR, 32, 1231\u20131237.","journal-title":"IJRR"},{"key":"1370_CR31","unstructured":"Ghiasi, G., Lin, T. Y., & Le, Q. V. (2018). Dropblock: A regularization method for convolutional networks. In Advances in neural information processing systems (pp. 10727\u201310737)."},{"key":"1370_CR32","doi-asserted-by":"crossref","unstructured":"Gidaris, S., & Komodakis, N. (2015). Object detection via a multi-region and semantic segmentation-aware CNN model. In ICCV (pp. 1134\u20131142). IEEE.","DOI":"10.1109\/ICCV.2015.135"},{"key":"1370_CR33","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015). Fast R-CNN. In: ICCV (pp. 1440\u20131448). IEEE.","DOI":"10.1109\/ICCV.2015.169"},{"key":"1370_CR34","doi-asserted-by":"crossref","unstructured":"Harzallah, H., Jurie, F., & Schmid, C. (2009). Combining efficient object localization and image classification. In ICCV (pp. 237\u2013244). IEEE.","DOI":"10.1109\/ICCV.2009.5459257"},{"key":"1370_CR35","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R. (2017). Mask R-CNN. ICCV.","DOI":"10.1109\/ICCV.2017.322"},{"key":"1370_CR36","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR (pp. 770\u2013778). IEEE.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1370_CR37","doi-asserted-by":"crossref","unstructured":"Heitz, G., & Koller, D. (2008). Learning spatial context: Using stuff to find things. In ECCV (pp. 30\u201343). Springer, Berlin.","DOI":"10.1007\/978-3-540-88682-2_4"},{"issue":"1","key":"1370_CR38","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1146\/annurev.psych.50.1.243","volume":"50","author":"JM Henderson","year":"1999","unstructured":"Henderson, J. M., & Hollingworth, A. (1999). High-level scene perception. Annual Review of Psychology, 50(1), 243\u2013271.","journal-title":"Annual Review of Psychology"},{"key":"1370_CR39","unstructured":"Hinton, G. E., Sabour, S., & Frosst, N. (2018). Matrix capsules with EM routing. In ICLR."},{"issue":"4","key":"1370_CR40","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1037\/0096-3445.127.4.398","volume":"127","author":"A Hollingworth","year":"1998","unstructured":"Hollingworth, A. (1998). Does consistent scene context facilitate object perception? Journal of Experimental Psychology: General, 127(4), 398.","journal-title":"Journal of Experimental Psychology: General"},{"key":"1370_CR41","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., & Wei, Y. (2018a). Relation networks for object detection. In CVPR (Vol. 2). IEEE.","DOI":"10.1109\/CVPR.2018.00378"},{"key":"1370_CR42","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018b). 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":"1370_CR43","doi-asserted-by":"crossref","unstructured":"Kong, T., Yao, A., Chen, Y., & Sun, F. (2016). Hypernet: Towards accurate region proposal generation and joint object detection. In CVPR (pp. 845\u2013853). IEEE.","DOI":"10.1109\/CVPR.2016.98"},{"key":"1370_CR44","doi-asserted-by":"crossref","unstructured":"Li, H., Guo, X., Dai, B., Ouyang, W., & Wang, X. (2018). Neural network encapsulation. In Proceedings of the European conference on computer vision (ECCV) (pp. 252\u2013267).","DOI":"10.1007\/978-3-030-01252-6_16"},{"issue":"3","key":"1370_CR45","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1007\/s11263-018-1101-7","volume":"127","author":"H Li","year":"2019","unstructured":"Li, H., Liu, Y., Ouyang, W., & Wang, X. (2019). Zoom out-and-in network with map attention decision for region proposal and object detection. International Journal of Computer Vision, 127(3), 225\u2013238.","journal-title":"International Journal of Computer Vision"},{"key":"1370_CR46","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017a). Feature pyramid networks for object detection. In CVPR. IEEE.","DOI":"10.1109\/CVPR.2017.106"},{"key":"1370_CR47","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2017b). 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":"1370_CR48","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2018). Focal loss for dense object detection. In TPAMI.","DOI":"10.1109\/ICCV.2017.324"},{"key":"1370_CR49","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., et al. (2014). Microsoft coco: Common objects in context. In ECCV (pp. 740\u2013755). Springer, Berlin.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1370_CR50","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2019","unstructured":"Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., et al. (2019). Deep learning for generic object detection: A survey. International Journal of Computer Vision, 128, 261\u2013318.","journal-title":"International Journal of Computer Vision"},{"key":"1370_CR51","doi-asserted-by":"crossref","unstructured":"Liu, S., Huang, D., & Wang, A. (2018a). Receptive field block net for accurate and fast object detection. In ECCV. Springer, Berlin.","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"1370_CR52","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., et al. (2016). SSD: Single shot multibox detector. In ECCV (pp. 21\u201337). Springer, Berlin.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1370_CR53","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, R., Shan, S., & Chen, X. (2018b). Structure inference net: Object detection using scene-level context and instance-level relationships. In CVPR (pp. 6985\u20136994).","DOI":"10.1109\/CVPR.2018.00730"},{"key":"1370_CR54","doi-asserted-by":"crossref","unstructured":"Modolo, D., Vezhnevets, A., & Ferrari, V. (2015). Context forest for object class detection (Vol. 1, p. 6). In BMVC.","DOI":"10.5244\/C.29.188"},{"issue":"11\u201312","key":"1370_CR55","doi-asserted-by":"publisher","first-page":"1659","DOI":"10.1007\/s11263-018-1109-z","volume":"127","author":"T Mordan","year":"2019","unstructured":"Mordan, T., Thome, N., Henaff, G., & Cord, M. (2019). End-to-end learning of latent deformable part-based representations for object detection. International Journal of Computer Vision, 127(11\u201312), 1659\u20131679.","journal-title":"International Journal of Computer Vision"},{"key":"1370_CR56","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Chen, X., Liu, X., Cho, N. G., Lee, S. W., Fidler, S., et al. (2014). The role of context for object detection and semantic segmentation in the wild. In CVPR (pp. 891\u2013898). IEEE.","DOI":"10.1109\/CVPR.2014.119"},{"key":"1370_CR57","unstructured":"Ouyang, W., Wang, K., Zhu, X., & Wang, X. (2017). Learning chained deep features and classifiers for cascade in object detection. In ICCV."},{"issue":"1","key":"1370_CR58","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/s11263-016-0890-9","volume":"120","author":"W Ouyang","year":"2016","unstructured":"Ouyang, W., Zeng, X., & Wang, X. (2016). Learning mutual visibility relationship for pedestrian detection with a deep model. International Journal of Computer Vision, 120(1), 14\u201327.","journal-title":"International Journal of Computer Vision"},{"key":"1370_CR59","doi-asserted-by":"publisher","first-page":"519","DOI":"10.3758\/BF03197524","volume":"3","author":"TE Palmer","year":"1975","unstructured":"Palmer, T. E. (1975). The effects of contextual scenes on the identification of objects. Memory and Cognition, 3, 519\u2013526.","journal-title":"Memory and Cognition"},{"key":"1370_CR60","unstructured":"Qiao, S., Wang, H., Liu, C., Shen, W., & Yuille, A. (2019). Weight standardization. arXiv preprint arXiv:1903.10520."},{"key":"1370_CR61","doi-asserted-by":"crossref","unstructured":"Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., & Belongie, S. (2007). Objects in context. In ICCV (pp. 1\u20138). IEEE.","DOI":"10.1109\/ICCV.2007.4408986"},{"key":"1370_CR62","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In CVPR (pp. 779\u2013788). IEEE.","DOI":"10.1109\/CVPR.2016.91"},{"key":"1370_CR63","doi-asserted-by":"crossref","unstructured":"Ren, J., Chen, X., Liu, J., Sun, W., Pang, J., Yan, Q., et al. (2017). Accurate single stage detector using recurrent rolling convolution. In CVPR.","DOI":"10.1109\/CVPR.2017.87"},{"key":"1370_CR64","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. In NIPS (pp. 91\u201399)."},{"key":"1370_CR65","unstructured":"Sabour, S., Frosst, N., & Hinton, G. E. (2017). Dynamic routing between capsules. In NIPS (pp. 3856\u20133866)."},{"key":"1370_CR66","doi-asserted-by":"crossref","unstructured":"Shen, Z., Liu, Z., Li, J., Jiang, Y. G., Chen, Y., & Xue, X. (2017). Dsod: Learning deeply supervised object detectors from scratch. In CVPR (pp. 1919\u20131927). IEEE.","DOI":"10.1109\/ICCV.2017.212"},{"key":"1370_CR67","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In ICLR."},{"key":"1370_CR68","doi-asserted-by":"crossref","unstructured":"Torralba, A., Murphy, K. P., Freeman, W. T., & Rubin, M. A., et al. (2003). Context-based vision system for place and object recognition. In ICCV (Vol. 3, pp. 273\u2013280). IEEE.","DOI":"10.1109\/ICCV.2003.1238354"},{"issue":"10","key":"1370_CR69","doi-asserted-by":"publisher","first-page":"1744","DOI":"10.1109\/TPAMI.2009.186","volume":"32","author":"Z Tu","year":"2010","unstructured":"Tu, Z., & Bai, X. (2010). Auto-context and its application to high-level vision tasks and 3d brain image segmentation. TPAMI, 32(10), 1744\u20131757.","journal-title":"TPAMI"},{"issue":"2","key":"1370_CR70","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/s11263-016-0884-7","volume":"119","author":"C Vondrick","year":"2016","unstructured":"Vondrick, C., Khosla, A., Pirsiavash, H., Malisiewicz, T., & Torralba, A. (2016). Visualizing object detection features. International Journal of Computer Vision, 119(2), 145\u2013158.","journal-title":"International Journal of Computer Vision"},{"key":"1370_CR71","doi-asserted-by":"crossref","unstructured":"Wang, P., Chen, P., Yuan, Y., Liu, D., Huang, Z., Hou, X., et al. (2018a). Understanding convolution for semantic segmentation. In: 2018 IEEE winter conference on applications of computer vision (WACV) (pp. 1451\u20131460). IEEE.","DOI":"10.1109\/WACV.2018.00163"},{"key":"1370_CR72","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., & He, K. (2018b). Non-local neural networks. In CVPR. IEEE.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1370_CR73","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J. Y., & So\u00a0Kweon, I. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV) (pp. 3\u201319).","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1370_CR74","doi-asserted-by":"crossref","unstructured":"Wu, Y., & He, K. (2018). Group normalization. In ECCV. Springer, Berlin.","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"1370_CR75","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"},{"issue":"9","key":"1370_CR76","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"RR Yu","year":"2010","unstructured":"Yu, R. R., Chen, X. S., Morariu, V. I., Davis, L. S., & Redmond, W. (2010). The role of context selection in object detection. T-PAMI, 32(9), 1627\u20131645.","journal-title":"T-PAMI"},{"key":"1370_CR77","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Lerer, A., Lin, T. Y., Pinheiro, P. O., Gross, S., Chintala, S., et al. (2016). A multipath network for object detection. arXiv preprint arXiv:1604.02135.","DOI":"10.5244\/C.30.15"},{"key":"1370_CR78","doi-asserted-by":"publisher","first-page":"2109","DOI":"10.1109\/TPAMI.2017.2745563","volume":"40","author":"X Zeng","year":"2017","unstructured":"Zeng, X., Ouyang, W., Yan, J., Li, H., Xiao, T., Wang, K., et al. (2017). Crafting gbd-net for object detection. T-PAMI, 40, 2109\u20132123.","journal-title":"T-PAMI"},{"key":"1370_CR79","doi-asserted-by":"crossref","unstructured":"Zhang, H., Dana, K., Shi, J., Zhang, Z., Wang, X., Tyagi, A., et al. (2018). Context encoding for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7151\u20137160).","DOI":"10.1109\/CVPR.2018.00747"},{"key":"1370_CR80","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"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01370-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-020-01370-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01370-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T01:18:16Z","timestamp":1723425496000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-020-01370-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,19]]},"references-count":80,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["1370"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01370-7","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,19]]},"assertion":[{"value":"12 January 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 August 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}