{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T13:34:14Z","timestamp":1781962454185,"version":"3.54.5"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585549","type":"print"},{"value":"9783030585556","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58555-6_12","type":"book-chapter","created":{"date-parts":[[2020,11,15]],"date-time":"2020-11-15T21:04:21Z","timestamp":1605474261000},"page":"191-207","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":244,"title":["Disentangled Non-local Neural Networks"],"prefix":"10.1007","author":[{"given":"Minghao","family":"Yin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuliang","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,16]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Britz, D., Goldie, A., Luong, M.T., Le, Q.: Massive exploration of neural machine translation architectures. arXiv preprint arXiv:1703.03906 (2017)","DOI":"10.18653\/v1\/D17-1151"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: GCNET: non-local networks meet squeeze-excitation networks and beyond. arXiv preprint arXiv:1904.11492 (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"12_CR3","unstructured":"Chen, K., et al.: Mmdetection: open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"12_CR4","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cao, Y., Hu, H., Wang, L.: Memory enhanced global-local aggregation for video object detection. In: The Conference on Computer Vision and Pattern Recognition (CVPR), June 2020","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Pan, Y., Yao, T., Zhou, W., Li, H., Mei, T.: Relation distillation networks for video object detection. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00712"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"12_CR9","unstructured":"Fu, J., et al.: Adaptive context network for scene parsing. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6748\u20136757 (2019)"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Gu, J., Hu, H., Wang, L., Wei, Y., Dai, J.: Learning region features for object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 381\u2013395 (2018)","DOI":"10.1007\/978-3-030-01258-8_24"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Progressive sparse local attention for video object detection. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00401"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"He, J., Deng, Z., Qiao, Y.: Dynamic multi-scale filters for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3562\u20133572 (2019)","DOI":"10.1109\/ICCV.2019.00366"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"12_CR14","unstructured":"Hoshen, Y.: Vain: attentional multi-agent predictive modeling. In: Advances in Neural Information Processing Systems, pp. 2701\u20132711 (2017)"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection (2017)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, Z., Xie, Z., Lin, S.: Local relation networks for image recognition (2019)","DOI":"10.1109\/ICCV.2019.00356"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: Ccnet: Criss-cross attention for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"12_CR18","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Li, X., Zhong, Z., Wu, J., Yang, Y., Lin, Z., Liu, H.: Expectation-maximization attention networks for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9167\u20139176 (2019)","DOI":"10.1109\/ICCV.2019.00926"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"12_CR22","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: Advances in Neural Information Processing Systems, pp. 4967\u20134976 (2017)"},{"key":"12_CR23","unstructured":"Sun, K., et al.: High-resolution representations for labeling pixels and regions. arXiv preprint arXiv:1904.04514 (2019)"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Tang, G., Sennrich, R., Nivre, J.: An analysis of attention mechanisms: the case of word sense disambiguation in neural machine translation. arXiv preprint arXiv:1810.07595 (2018)","DOI":"10.18653\/v1\/W18-6304"},{"key":"12_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"12_CR27","unstructured":"Watters, N., Zoran, D., Weber, T., Battaglia, P., Pascanu, R., Tacchetti, A.: Visual interaction networks: learning a physics simulator from video. In: Advances in Neural Information Processing Systems, pp. 4539\u20134547 (2017)"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Wu, H., Chen, Y., Wang, N., Zhang, Z.: Sequence level semantics aggregation for video object detection. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00931"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Xu, J., Cao, Y., Zhang, Z., Hu, H.: Spatial-temporal relation networks for multi-object tracking. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00409"},{"key":"12_CR30","unstructured":"Yuan, Y., Wang, J.: Ocnet: object context network for scene parsing. arXiv preprint arXiv:1809.00916 (2018)"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, F., et al.: ACFNet: attentional class feature network for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6798\u20136807 (2019)","DOI":"10.1109\/ICCV.2019.00690"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Context encoding for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7151\u20137160 (2018)","DOI":"10.1109\/CVPR.2018.00747"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhang, H., Wang, C., Xie, J.: Co-occurrent features in semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 548\u2013557 (2019)","DOI":"10.1109\/CVPR.2019.00064"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, H., et al.: PSANet: point-wise spatial attention network for scene parsing. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 267\u2013283 (2018)","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, X., Cheng, D., Zhang, Z., Lin, S., Dai, J.: An empirical study of spatial attention mechanisms in deep networks. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00679"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Xu, M., Bai, S., Huang, T., Bai, X.: Asymmetric non-local neural networks for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 593\u2013602 (2019)","DOI":"10.1109\/ICCV.2019.00068"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58555-6_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T00:09:45Z","timestamp":1731629385000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58555-6_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585549","9783030585556"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58555-6_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"16 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}