{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T15:43:39Z","timestamp":1743090219139,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031278174"},{"type":"electronic","value":"9783031278181"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-27818-1_56","type":"book-chapter","created":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T10:20:17Z","timestamp":1680171617000},"page":"683-694","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AutoRF: Auto Learning Receptive Fields with\u00a0Spatial Pooling"],"prefix":"10.1007","author":[{"given":"Peijie","family":"Dong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zimian","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hengyue","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,31]]},"reference":[{"key":"56_CR1","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. ArXiv abs\/1706.05587 (2017)"},{"key":"56_CR2","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"56_CR3","unstructured":"Deng, L., Yang, M., Li, T., He, Y., Wang, C.: RFBNet: deep multimodal networks with residual fusion blocks for RGB-D semantic segmentation. ArXiv abs\/1907.00135 (2019)"},{"key":"56_CR4","unstructured":"Devries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. ArXiv abs\/1708.04552 (2017)"},{"key":"56_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. ArXiv abs\/2010.11929 (2021)"},{"key":"56_CR6","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/s12065-007-0002-4","volume":"1","author":"D Floreano","year":"2008","unstructured":"Floreano, D., D\u00fcrr, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evol. Intel. 1, 47\u201362 (2008). https:\/\/doi.org\/10.1007\/s12065-007-0002-4","journal-title":"Evol. Intel."},{"key":"56_CR7","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.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37, 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"56_CR8","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhang, L., Cheng, M.M., Feng, J.: Strip pooling: rethinking spatial pooling for scene parsing. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4002\u20134011 (2020)","DOI":"10.1109\/CVPR42600.2020.00406"},{"key":"56_CR9","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","volume":"42","author":"J Hu","year":"2020","unstructured":"Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell. 42, 2011\u20132023 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"56_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108025","volume":"118","author":"Y Hu","year":"2021","unstructured":"Hu, Y., Wang, X., Li, L., Gu, Q.: Improving one-shot NAS with shrinking-and-expanding supernet. Pattern Recogn. 118, 108025 (2021)","journal-title":"Pattern Recogn."},{"key":"56_CR11","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images (2009)"},{"key":"56_CR12","unstructured":"Kwon, J., Kim, J., Park, H., Choi, I.: ASAM: adaptive sharpness-aware minimization for scale-invariant learning of deep neural networks. In: ICML (2021)"},{"key":"56_CR13","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 510\u2013519 (2019)","DOI":"10.1109\/CVPR.2019.00060"},{"key":"56_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Neural architecture search for lightweight non-local networks. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10294\u201310303 (2020)","DOI":"10.1109\/CVPR42600.2020.01031"},{"key":"56_CR15","unstructured":"Lin, M., Chen, Q., Yan, S.: Network in network. CoRR abs\/1312.4400 (2014)"},{"key":"56_CR16","unstructured":"Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: ICLR (Poster). OpenReview.net (2019). http:\/\/dblp.uni-trier.de\/db\/conf\/iclr\/iclr2019.html#LiuSY19"},{"key":"56_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"56_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"56_CR19","unstructured":"Luo, W., Li, Y., Urtasun, R., Zemel, R.S.: Understanding the effective receptive field in deep convolutional neural networks. In: NIPS (2016)"},{"key":"56_CR20","unstructured":"Ma, B., Zhang, J., Xia, Y., Tao, D.: Auto learning attention. In: NeurIPS (2020)"},{"key":"56_CR21","doi-asserted-by":"crossref","unstructured":"Nakai, K., Matsubara, T., Uehara, K.: Att-DARTS: differentiable neural architecture search for attention. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138 (2020)","DOI":"10.1109\/IJCNN48605.2020.9207447"},{"key":"56_CR22","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. ArXiv abs\/1804.02767 (2018)"},{"key":"56_CR23","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis."},{"key":"56_CR24","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Bengio, Y., LeCun, Y. (eds.) ICLR (2015). http:\/\/dblp.uni-trier.de\/db\/conf\/iclr\/iclr2015.html#SimonyanZ14a"},{"key":"56_CR25","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"56_CR26","unstructured":"Tolstikhin, I.O., et al.: MLP-Mixer: an all-MLP architecture for vision. ArXiv abs\/2105.01601 (2021)"},{"key":"56_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"56_CR28","unstructured":"You, Y., et al.: Large batch optimization for deep learning: training BERT in 76 minutes. arXiv:1904.00962 (2020)"},{"key":"56_CR29","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: BiSeNet: bilateral segmentation network for real-time semantic segmentation. ArXiv abs\/1808.00897 (2018)","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"56_CR30","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. CoRR abs\/1511.07122 (2016)"},{"key":"56_CR31","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: MetaFormer is actually what you need for vision. ArXiv abs\/2111.11418 (2021)","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"56_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6230\u20136239 (2017)","DOI":"10.1109\/CVPR.2017.660"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27818-1_56","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T10:34:39Z","timestamp":1680172479000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27818-1_56"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031278174","9783031278181"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27818-1_56","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"31 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bergen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 January 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conftool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"267","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"86","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}