{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T03:15:35Z","timestamp":1743045335243,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031023743"},{"type":"electronic","value":"9783031023750"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-02375-0_20","type":"book-chapter","created":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:03:10Z","timestamp":1652180590000},"page":"271-284","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["COMatchNet: Co-Attention Matching Network for\u00a0Video Object Segmentation"],"prefix":"10.1007","author":[{"given":"Lufei","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengming","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xia","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,11]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Bao, L., Wu, B., Liu, W.: CNN in MRF: video object segmentation via inference in a CNN-based higher-order spatio-temporal MRF. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5977\u20135986 (2018)","DOI":"10.1109\/CVPR.2018.00626"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2544\u20132550. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Caelles, S., Maninis, K.K., Pont-Tuset, J., Leal-Taix\u00e9, L., Cremers, D., Van Gool, L.: One-shot video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 221\u2013230 (2017)","DOI":"10.1109\/CVPR.2017.565"},{"key":"20_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Pont-Tuset, J., Montes, A., Van Gool, L.: Blazingly fast video object segmentation with pixel-wise metric learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1189\u20131198 (2018)","DOI":"10.1109\/CVPR.2018.00130"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Lasot: a high-quality benchmark for large-scale single object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5374\u20135383 (2019)","DOI":"10.1109\/CVPR.2019.00552"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Girgensohn, A., et al.: A semi-automatic approach to home video editing. In: Proceedings of the 13th Annual ACM Symposium on User Interface Software and Technology, pp. 81\u201389 (2000)","DOI":"10.1145\/354401.354415"},{"key":"20_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/978-3-030-01237-3_4","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y-T Hu","year":"2018","unstructured":"Hu, Y.-T., Huang, J.-B., Schwing, A.G.: VideoMatch: matching based video object segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 56\u201373. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_4"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"20_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"20_CR11","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. arXiv preprint arXiv:1606.00061 (2016)"},{"key":"20_CR12","unstructured":"Meinhardt, T., Leal-Taix\u00e9, L.: Make one-shot video object segmentation efficient again. arXiv preprint arXiv:2012.01866 (2020)"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Oh, S.W., Lee, J.Y., Sunkavalli, K., Kim, S.J.: Fast video object segmentation by reference-guided mask propagation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7376\u20137385 (2018)","DOI":"10.1109\/CVPR.2018.00770"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Oh, S.W., Lee, J.Y., Xu, N., Kim, S.J.: Video object segmentation using space-time memory networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9226\u20139235 (2019)","DOI":"10.1109\/ICCV.2019.00932"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 724\u2013732 (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"20_CR16","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Van Gool, L.: The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Annals Math. Stat. 400\u2013407 (1951)","DOI":"10.1214\/aoms\/1177729586"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Chai, Y., Schroff, F., Adam, H., Leibe, B., Chen, L.C.: Feelvos: fast end-to-end embedding learning for video object segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9481\u20139490 (2019)","DOI":"10.1109\/CVPR.2019.00971"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Leibe, B.: Online adaptation of convolutional neural networks for video object segmentation. arXiv preprint arXiv:1706.09364 (2017)","DOI":"10.5244\/C.31.116"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xu, J., Liu, L., Zhu, F., Shao, L.: Ranet: ranking attention network for fast video object segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3978\u20133987 (2019)","DOI":"10.1109\/ICCV.2019.00408"},{"key":"20_CR21","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":"20_CR22","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 284\u2013293 (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Xu, N., Yang, L., Fan, Y., Yue, D., Liang, Y., Yang, J., Huang, T.: Youtube-vos: a large-scale video object segmentation benchmark. arXiv preprint arXiv:1809.03327 (2018)","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"20_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1007\/978-3-030-58558-7_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Yang","year":"2020","unstructured":"Yang, Z., Wei, Y., Yang, Y.: Collaborative video object segmentation by foreground-background integration. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 332\u2013348. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_20"},{"key":"20_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1007\/978-3-030-01216-8_43","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Zolfaghari","year":"2018","unstructured":"Zolfaghari, M., Singh, K., Brox, T.: ECO: efficient convolutional network for online video understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 713\u2013730. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_43"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-02375-0_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:05:54Z","timestamp":1652180754000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-02375-0_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031023743","9783031023750"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-02375-0_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jeju Island","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.acpr2021.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"154","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":"85","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":"55% - 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)"}}]}}