{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T20:56:37Z","timestamp":1778187397784,"version":"3.51.4"},"reference-count":81,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T00:00:00Z","timestamp":1667174400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T00:00:00Z","timestamp":1667174400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076119"],"award-info":[{"award-number":["62076119"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61921006"],"award-info":[{"award-number":["61921006"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1007\/s11263-022-01707-4","type":"journal-article","created":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T17:04:07Z","timestamp":1667235847000},"page":"363-384","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["LIP: Local Importance-Based Pooling"],"prefix":"10.1007","volume":"131","author":[{"given":"Ziteng","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3674-7718","authenticated-orcid":false,"given":"Limin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gangshan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,31]]},"reference":[{"key":"1707_CR1","doi-asserted-by":"crossref","unstructured":"Bai, Y., Zhang, Y., Ding, M., & Ghanem, B. (2018). SOD-MTGAN: Small object detection via multi-task generative adversarial network. In ECCV.","DOI":"10.1007\/978-3-030-01261-8_13"},{"key":"1707_CR2","unstructured":"Boureau, Y., Ponce, J., & LeCun, Y. (2010). A theoretical analysis of feature pooling in visual recognition. In ICML."},{"key":"1707_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Z., & Vasconcelos, N. (2018). Cascade R-CNN: Delving into high quality object detection. In CVPR.","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1707_CR4","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. In arXiv"},{"key":"1707_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, J., Ding, R., & Marculescu, D. (2020). Vip: Virtual pooling for accelerating cnn-based image classification and object detection. In WACV, IEEE (pp. 1169\u20131178).","DOI":"10.1109\/WACV45572.2020.9093418"},{"key":"1707_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, B., Wei, Y., Shi, H., Feris, R.S., Xiong, J., & Huang, T.S. (2018). Revisiting RCNN: On awakening the classification power of faster RCNN. In ECCV.","DOI":"10.1007\/978-3-030-01267-0_28"},{"key":"1707_CR7","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In CVPR, IEEE Computer Society (pp. 1800\u20131807).","DOI":"10.1109\/CVPR.2017.195"},{"key":"1707_CR8","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016). The cityscapes dataset for semantic urban scene understanding. In CVPR.","DOI":"10.1109\/CVPR.2016.350"},{"key":"1707_CR9","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017). Deformable convolutional networks. ICCV.","DOI":"10.1109\/ICCV.2017.89"},{"key":"1707_CR10","doi-asserted-by":"crossref","unstructured":"Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. CVPR.","DOI":"10.1109\/CVPR.2005.177"},{"key":"1707_CR11","unstructured":"Deli\u00e8ge, A., Istasse, M., Kumar, A., Vleeschouwer, C. D., & Droogenbroeck, M. V. (2019). Ordinal pooling. In BMVC (p. 76) BMVA Press."},{"key":"1707_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., & Li, F. (2009). Imagenet: A large-scale hierarchical image database. CVPR.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1707_CR13","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In 9th international conference on learning representations."},{"key":"1707_CR14","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., & Feichtenhofer, C. (2021). Multiscale vision transformers. In ICCV, IEEE (pp. 6804\u20136815).","DOI":"10.1109\/ICCV48922.2021.00675"},{"issue":"2","key":"1707_CR15","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","volume":"43","author":"S Gao","year":"2021","unstructured":"Gao, S., Cheng, M., Zhao, K., Zhang, X., Yang, M., & Torr, P. H. S. (2021). Res2net: A new multi-scale backbone architecture. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(2), 652\u2013662.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1707_CR16","doi-asserted-by":"crossref","unstructured":"Gao, Z., Wang, L., & Wu, G. (2019). LIP: local importance-based pooling. In ICCV, IEEE (pp. 3354\u20133363).","DOI":"10.1109\/ICCV.2019.00345"},{"key":"1707_CR17","unstructured":"Goyal, P., Doll\u00e1r, P., Girshick, R.B., Noordhuis, P., Wesolowski, L., Kyrola, A., Tulloch, A., Jia, Y., & He, K. (2017). Accurate, large minibatch SGD: Training imagenet in 1 hour. In arXiv, arxiv:1706.02677."},{"key":"1707_CR18","unstructured":"Graham, B. (2014). Fractional max-pooling. In arXiv, arxiv:1412.6071."},{"key":"1707_CR19","doi-asserted-by":"crossref","unstructured":"G\u00fcl\u00e7ehre, \u00c7., Cho, K., Pascanu, R., & Bengio, Y. (2014). Learned-norm pooling for deep feedforward and recurrent neural networks. ECML PKDD.","DOI":"10.1007\/978-3-662-44848-9_34"},{"key":"1707_CR20","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 ICCV.","DOI":"10.1109\/ICCV.2015.123"},{"key":"1707_CR21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. CVPR. https:\/\/doi.org\/10.1109\/CVPR.2016.90.","journal-title":"CVPR"},{"key":"1707_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. B. (2017). Mask R-CNN. ICCV.","DOI":"10.1109\/ICCV.2017.322"},{"key":"1707_CR23","doi-asserted-by":"crossref","unstructured":"He, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., & Li, M. (2019). Bag of tricks for image classification with convolutional neural networks. In CVPR.","DOI":"10.1109\/CVPR.2019.00065"},{"key":"1707_CR24","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, Z., Xie, Z., & Lin, S. (2019). Local relation networks for image recognition. In ICCV.","DOI":"10.1109\/ICCV.2019.00356"},{"key":"1707_CR25","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In CVPR.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1707_CR26","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In CVPR.","DOI":"10.1109\/CVPR.2017.243"},{"key":"1707_CR27","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML."},{"key":"1707_CR28","unstructured":"Jia, X., Brabandere, B. D., Tuytelaars, T., & Gool, L. V. (2016). Dynamic filter networks. In NIPS."},{"key":"1707_CR29","doi-asserted-by":"crossref","unstructured":"Kobayashi, T. (2019). Global feature guided local pooling. In ICCV, IEEE (pp. 3364\u20133373).","DOI":"10.1109\/ICCV.2019.00346"},{"key":"1707_CR30","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. In Bartlett PL, Pereira FCN, Burges CJC, Bottou L, Weinberger KQ (eds) NIPS (pp. 1106\u20131114)."},{"key":"1707_CR31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68","author":"S Lazebnik","year":"2006","unstructured":"Lazebnik, S., Schmid, C., & Ponce, J. (2006). Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. CVPR. https:\/\/doi.org\/10.1109\/CVPR.2006.68.","journal-title":"CVPR"},{"issue":"11","key":"1707_CR32","doi-asserted-by":"publisher","first-page":"6668","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 6668.","journal-title":"Proceedings of the IEEE"},{"key":"1707_CR33","unstructured":"Lee, C., Gallagher, P.W., & Tu, Z. (2016). Generalizing pooling functions in convolutional neural networks: Mixed, gated, and tree. In AISTATS."},{"key":"1707_CR34","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Y., Wang, N., & Zhang, Z. (2019). Scale-aware trident networks for object detection. In ICCV","DOI":"10.1109\/ICCV.2019.00615"},{"key":"1707_CR35","doi-asserted-by":"crossref","unstructured":"Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., & Sun, J. (2018). Detnet: A backbone network for object detection. In ECCV.","DOI":"10.1007\/978-3-030-01240-3_21"},{"key":"1707_CR36","unstructured":"Lin, M., Chen, Q., & Yan, S. (2014a). Network in network. In ICLR"},{"key":"1707_CR37","doi-asserted-by":"crossref","unstructured":"Lin, T., Maire, M., Belongie, S. J., Hays, J., Perona, P., Ramanan, D., et al. (2014). Microsoft COCO: Common objects in context. ECCV.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1707_CR38","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R. B., He, K., Hariharan, B., & Belongie, S.J. (2017a). Feature pyramid networks for object detection. In CVPR.","DOI":"10.1109\/CVPR.2017.106"},{"key":"1707_CR39","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, R. B., He, K., & Doll\u00e1r, P. (2017b). Focal loss for dense object detection. In ICCV.","DOI":"10.1109\/ICCV.2017.324"},{"key":"1707_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV, IEEE (pp. 9992\u201310002).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1707_CR41","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. CVPR.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1707_CR42","doi-asserted-by":"crossref","unstructured":"Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision.","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"1707_CR43","doi-asserted-by":"crossref","unstructured":"Lu, X., Li, B., Yue, Y., Li, Q., & Yan, J. (2019). Grid R-CNN. In CVPR.","DOI":"10.1109\/CVPR.2019.00754"},{"key":"1707_CR44","unstructured":"Luo, W., Li, Y., Urtasun, R., & Zemel, R. S. (2016). Understanding the effective receptive field in deep convolutional neural networks. In NIPS."},{"key":"1707_CR45","doi-asserted-by":"crossref","unstructured":"Palacio, S., Folz, J., Hees, J., Raue, F., Borth, D., & Dengel, A. (2018). What do deep networks like to see? CVPR.","DOI":"10.1109\/CVPR.2018.00328"},{"key":"1707_CR46","unstructured":"Parmar, N., Ramachandran, P., Vaswani, A., Bello, I., Levskaya, A., & Shlens, J. (2019). Stand-alone self-attention in vision models. In NeurIPS."},{"key":"1707_CR47","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R.B., He, K., & Doll\u00e1r, P. (2020). Designing network design spaces. In CVPR, IEEE (pp. 10425\u201310433).","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"1707_CR48","doi-asserted-by":"crossref","unstructured":"Saeedan, F., Weber, N., Goesele, M., & Roth, S. (2018). Detail-preserving pooling in deep networks. CVPR.","DOI":"10.1109\/CVPR.2018.00949"},{"key":"1707_CR49","unstructured":"Simonyan, K., & Zisserman, A. (2014). Two-stream convolutional networks for action recognition in videos. In Ghahramani Z, Welling M, Cortes C, Lawrence ND, Weinberger KQ (eds) NIPS (pp. 568\u2013576)."},{"key":"1707_CR50","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In ICLR"},{"key":"1707_CR51","doi-asserted-by":"crossref","unstructured":"Singh, B., & Davis, L.S. (2018). An analysis of scale invariance in object detection SNIP. In CVPR.","DOI":"10.1109\/CVPR.2018.00377"},{"key":"1707_CR52","unstructured":"Singh, B., Najibi, M., & Davis, L.S. (2018). SNIPER: efficient multi-scale training. In NeurIPS."},{"key":"1707_CR53","doi-asserted-by":"crossref","unstructured":"Sivic, J., & Zisserman, A. (2003). Video google: A text retrieval approach to object matching in videos. ICCV.","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"1707_CR54","doi-asserted-by":"crossref","unstructured":"Stergiou, A., Poppe, R., & Kalliatakis, G. (2021). Refining activation downsampling with softpool. In ICCV, IEEE (pp. 10337\u201310346).","DOI":"10.1109\/ICCV48922.2021.01019"},{"key":"1707_CR55","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., & Wang, J. (2019). Deep high-resolution representation learning for human pose estimation. In CVPR.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"1707_CR56","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S. E., Anguelov, D., et al. (2015). Going deeper with convolutions. CVPR.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1707_CR57","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. CVPR.","DOI":"10.1109\/CVPR.2016.308"},{"key":"1707_CR58","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., & He, T. (2019). FCOS: Fully convolutional one-stage object detection. In ICCV, IEEE.","DOI":"10.1109\/ICCV.2019.00972"},{"key":"1707_CR59","unstructured":"Ulyanov, D., Vedaldi, A., & Lempitsky, V.S. (2016). Instance normalization: The missing ingredient for fast stylization. In arXiv"},{"key":"1707_CR60","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. In Guyon I, von Luxburg U, Bengio S, Wallach HM, Fergus R, Vishwanathan SVN, Garnett R (eds) NIPS, (pp. 5998\u20136008)."},{"key":"1707_CR61","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, K., Xu, R., Liu, Z., Loy, C.C., & Lin, D. (2019a). CARAFE: Content-aware reassembly of features. In ICCV.","DOI":"10.1109\/ICCV.2019.00310"},{"key":"1707_CR62","doi-asserted-by":"crossref","unstructured":"Wang, L., Gao, C., Liu, J., & Meng, D. (2017). A novel learning-based frame pooling method for event detection. Signal Processing.","DOI":"10.1016\/j.sigpro.2017.05.005"},{"issue":"4","key":"1707_CR63","doi-asserted-by":"publisher","first-page":"2055","DOI":"10.1109\/TIP.2017.2675339","volume":"26","author":"L Wang","year":"2017","unstructured":"Wang, L., Guo, S., Huang, W., Xiong, Y., & Qiao, Y. (2017). Knowledge guided disambiguation for large-scale scene classification with multi-resolution cnns. IEEE Transactions on Image Processing, 26(4), 2055\u20132068.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"11","key":"1707_CR64","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2019","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., & Gool, L. V. (2019). Temporal segment networks for action recognition in videos. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(11), 2740\u20132755.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1707_CR65","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D., Song, K., Liang, D., Lu, T., Luo, P., & Shao, L. (2021). Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In ICCV, IEEE (pp. 548\u2013558).","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"1707_CR66","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R. B., Gupta, A., & He, K. (2018). Non-local neural networks. CVPR.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1707_CR67","doi-asserted-by":"crossref","unstructured":"Wei, Z., Zhang, J., Liu, L., Zhu, F., Shen, F., Zhou, Y., Liu, S., Sun, Y., & Shao, L. (2019). Building detail-sensitive semantic segmentation networks with polynomial pooling. In CVPR, Computer Vision Foundation\/IEEE (pp. 7115\u20137123).","DOI":"10.1109\/CVPR.2019.00728"},{"key":"1707_CR68","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J., & Kweon, I. S. (2018). CBAM: Convolutional block attention module. In Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) ECCV (pp. 3\u201319), Springer.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1707_CR69","doi-asserted-by":"crossref","unstructured":"Xiao, B., Wu, H., & Wei, Y. (2018). Simple baselines for human pose estimation and tracking. In ECCV, vol. 11210.","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"1707_CR70","doi-asserted-by":"crossref","unstructured":"Xie, G., Zhang, X., Shu, X., Yan, S., & Liu, C. (2015). Task-driven feature pooling for image classification. ICCV.","DOI":"10.1109\/ICCV.2015.140"},{"key":"1707_CR71","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R.B., Doll\u00e1r, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks. In CVPR.","DOI":"10.1109\/CVPR.2017.634"},{"key":"1707_CR72","doi-asserted-by":"crossref","unstructured":"Yu, D., Wang, H., Chen, P., & Wei, Z. (2014). Mixed pooling for convolutional neural networks. RSKT.","DOI":"10.1007\/978-3-319-11740-9_34"},{"key":"1707_CR73","doi-asserted-by":"crossref","unstructured":"Zhai, S., Wu, H., Kumar, A., Cheng, Y., Lu, Y., Zhang, Z., & Feris, R. S. (2017). S3pool: Pooling with stochastic spatial sampling. CVPR.","DOI":"10.1109\/CVPR.2017.426"},{"key":"1707_CR74","unstructured":"Zhang, R. (2019). Making convolutional networks shift-invariant again. In ICML."},{"key":"1707_CR75","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid scene parsing network. In CVPR.","DOI":"10.1109\/CVPR.2017.660"},{"key":"1707_CR76","unstructured":"Zhao, J., & Snoek, C.G.M. (2021). Liftpool: Bidirectional convnet pooling. In ICLR, OpenReview.net."},{"key":"1707_CR77","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, \u00c0., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. CVPR.","DOI":"10.1109\/CVPR.2016.319"},{"issue":"6","key":"1707_CR78","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2018","unstructured":"Zhou, B., Lapedriza, \u00c0., Khosla, A., Oliva, A., & Torralba, A. (2018). Places: A 10 million image database for scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6), 1452\u20131464.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1707_CR79","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., & Dai, J. (2019a). Deformable convnets v2: More deformable, better results. In CVPR.","DOI":"10.1109\/CVPR.2019.00953"},{"key":"1707_CR80","doi-asserted-by":"crossref","unstructured":"Zhu, X., Cheng, D., Zhang, Z., Lin, S., & Dai, J. (2019b). An empirical study of spatial attention mechanisms in deep networks. In ICCV.","DOI":"10.1109\/ICCV.2019.00679"},{"key":"1707_CR81","unstructured":"Zou, X., Xiao, F., Yu, Z., & Lee, Y. J. (2020). Delving deeper into anti-aliasing in convnets. In BMVC, BMVA Press."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01707-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-022-01707-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01707-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T03:31:04Z","timestamp":1672975864000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-022-01707-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,31]]},"references-count":81,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["1707"],"URL":"https:\/\/doi.org\/10.1007\/s11263-022-01707-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,31]]},"assertion":[{"value":"10 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}