{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:38:42Z","timestamp":1742913522411,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030880033"},{"type":"electronic","value":"9783030880040"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-88004-0_13","type":"book-chapter","created":{"date-parts":[[2021,10,21]],"date-time":"2021-10-21T23:06:25Z","timestamp":1634857585000},"page":"154-165","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Joint Attention Mechanism for Unsupervised Video Object Segmentation"],"prefix":"10.1007","author":[{"given":"Rui","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,22]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Jain, S.D., Xiong, B., Grauman, K.: Fusionseg: learning to combine motion and appearance for fully automatic segmentation of generic objects in videos. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 2117\u20132126 (2017)","DOI":"10.1109\/CVPR.2017.228"},{"key":"13_CR2","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":"13_CR3","doi-asserted-by":"crossref","unstructured":"Caelles, S., Montes, A., Maninis, K.-K., Chen, Y., Van Gool, L., Perazzi, F.: Pont-Tuset JJapa: The 2018 DAVIS challenge on video object segmentation (2018)","DOI":"10.1109\/CVPR.2017.565"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Alahari, K., Schmid, C.: Learning motion patterns in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3386\u20133394 (2017)","DOI":"10.1109\/CVPR.2017.64"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Li, S., Seybold, B., Vorobyov, A., Fathi, A., Huang, Q., Jay Kuo, C.-C.: Instance embedding transfer to unsupervised video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6526\u20136535 (2018)","DOI":"10.1109\/CVPR.2018.00683"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Learning unsupervised video object segmentation through visual attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3064\u20133074 (2019)","DOI":"10.1109\/CVPR.2019.00318"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Denil, M., Bazzani, L., Larochelle, H., de Freitas, N.J.Nc.: Learning where to attend with deep architectures for image tracking. 24, 2151-2184 (2012)","DOI":"10.1162\/NECO_a_00312"},{"key":"13_CR8","unstructured":"Jetley, S., Lord, N.A., Lee, N., Torr, P.H.J.: Learn to pay attention (2018)"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., Wang, X.: Multi-context attention for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1831\u20131840 (2017)","DOI":"10.1109\/CVPR.2017.601"},{"key":"13_CR10","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.J.: Hierarchical question-image co-attention for visual question answering (2016)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Zhou, T., Wang, S., Zhou, Y., Yao, Y, Li, J., Shao, L.: Motion-attentive transition for zero-shot video object segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 07, pp. 13066\u201313073 (2020)","DOI":"10.1609\/aaai.v34i07.7008"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Wang F et al.: Residual attention network for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2017)","DOI":"10.1109\/CVPR.2017.683"},{"key":"13_CR13","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.J.: Rethinking atrous convolution for semantic image segmentation (2017)"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Khoreva, A., Benenson, R., Schiele, B., Sorkine-Hornung, A.: Learning video object segmentation from static images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2663\u20132672 (2017)","DOI":"10.1109\/CVPR.2017.372"},{"key":"13_CR15","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Van Gool, L.J.: The 2017 davis challenge on video object segmentation (2017)"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Ochs, P., Malik, J., Brox, T.J.: Intelligence m: Segmentation of moving objects by long term video analysis. 36, 1187-1200 (2013)","DOI":"10.1109\/TPAMI.2013.242"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Fragkiadaki, K., Zhang, G., Shi, J.: Video segmentation by tracing discontinuities in a trajectory embedding. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp. 1846\u20131853 (2012)","DOI":"10.1109\/CVPR.2012.6247883"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Taylor, B., Karasev, V., Soatto, S.: Causal video object segmentation from persistence of occlusions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4268\u20134276 (2015)","DOI":"10.1109\/CVPR.2015.7299055"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Lee, Y.J., Kim, J., Grauman, K.: Key-segments for video object segmentation. In: 2011 International Conference on Computer Vision. IEEE, pp. 1995\u20132002 (2011)","DOI":"10.1109\/ICCV.2011.6126471"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Cheng, J., Tsai, Y.-H., Wang, S., Yang, M.-H.: Segflow: Joint learning for video object segmentation and optical flow. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 686\u2013695 (2017)","DOI":"10.1109\/ICCV.2017.81"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Keuper, M., Andres, B., Brox, T.: Motion trajectory segmentation via minimum cost multicuts. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3271\u20133279 (2015)","DOI":"10.1109\/ICCV.2015.374"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Alahari, K., Schmid, C.: Learning video object segmentation with visual memory. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4481\u20134490 (2017)","DOI":"10.1109\/ICCV.2017.480"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Koh, Y.J., Kim, C.-S.: Primary object segmentation in videos based on region augmentation and reduction. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 7417\u20137425 (2017)","DOI":"10.1109\/CVPR.2017.784"},{"key":"13_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-030-01252-6_44","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Song","year":"2018","unstructured":"Song, H., Wang, W., Zhao, S., Shen, J., Lam, K.-M.: Pyramid dilated deeper ConvLSTM for video salient object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 744\u2013760. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_44"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Fragkiadaki, K., Arbelaez, P., Felsen, P., Malik, J.: Learning to segment moving objects in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4083\u20134090 (2015)","DOI":"10.1109\/CVPR.2015.7299035"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Siam, M., et al.: Video object segmentation using teacher-student adaptation in a human robot interaction (hri) setting. In: 2019 International Conference on Robotics and Automation (ICRA). IEEE, pp. 50\u201356 (2019)","DOI":"10.1109\/ICRA.2019.8794254"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Ventura, C., Bellver, M., Girbau, A., Salvador, A., Marques, F., Giro-i-Nieto, X.: Rvos: End-to-end recurrent network for video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5277\u20135286 (2019)","DOI":"10.1109\/CVPR.2019.00542"},{"key":"13_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/978-3-030-01219-9_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Li","year":"2018","unstructured":"Li, S., Seybold, B., Vorobyov, A., Lei, X., Kuo, C.-C.: Unsupervised video object segmentation with motion-based bilateral networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 215\u2013231. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_13"},{"key":"13_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1007\/978-3-030-01246-5_48","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y-T Hu","year":"2018","unstructured":"Hu, Y.-T., Huang, J.-B., Schwing, A.G.: Unsupervised video object segmentation using motion saliency-guided spatio-temporal propagation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 813\u2013830. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_48"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-88004-0_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T15:05:23Z","timestamp":1709823923000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-88004-0_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030880033","9783030880040"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-88004-0_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"22 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"29 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.prcv.cn\/2021\/index_en.html","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"513","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":"201","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":"39% - 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":"5","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":"There were 30 oral and 171 poster presentations at the conference.","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)"}}]}}