{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T19:33:30Z","timestamp":1744313610332,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819985364"},{"type":"electronic","value":"9789819985371"}],"license":[{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8537-1_14","type":"book-chapter","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:02:17Z","timestamp":1703530937000},"page":"170-182","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Asymmetric Attention Fusion for\u00a0Unsupervised Video Object Segmentation"],"prefix":"10.1007","author":[{"given":"Hongfan","family":"Jiang","sequence":"first","affiliation":[]},{"given":"Xiaojun","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,26]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Berman, M., Triki, A.R., Blaschko, M.B.: The lov\u00e1sz-softmax loss: a tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4413\u20134421 (2018)","DOI":"10.1109\/CVPR.2018.00464"},{"key":"14_CR2","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y.W., Jin, X., Shen, X., Yang, M.H.: Video salient object detection via contrastive features and attention modules. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1320\u20131329 (2022)","DOI":"10.1109\/WACV51458.2022.00061"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Fan, D.P., Wang, W., Cheng, M.M., Shen, J.: Shifting more attention to video salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8554\u20138564 (2019)","DOI":"10.1109\/CVPR.2019.00875"},{"key":"14_CR5","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":"14_CR6","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2462\u20132470 (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Ji, G.P., Fu, K., Wu, Z., Fan, D.P., Shen, J., Shao, L.: Full-duplex strategy for video object segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4922\u20134933 (2021)","DOI":"10.1109\/ICCV48922.2021.00488"},{"key":"14_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1007\/978-3-030-88004-0_20","volume-title":"Pattern Recognition and Computer Vision","author":"Q Jiang","year":"2021","unstructured":"Jiang, Q., Wu, X., Kittler, J.: Insight on attention modules for skeleton-based action recognition. In: Ma, H., et al. (eds.) PRCV 2021. LNCS, vol. 13019, pp. 242\u2013255. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-88004-0_20"},{"issue":"8","key":"14_CR9","doi-asserted-by":"publisher","first-page":"2552","DOI":"10.1109\/TIP.2015.2425544","volume":"24","author":"H Kim","year":"2015","unstructured":"Kim, H., Kim, Y., Sim, J.Y., Kim, C.S.: Spatiotemporal saliency detection for video sequences based on random walk with restart. IEEE Trans. Image Process. 24(8), 2552\u20132564 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Koh, Y.J., Kim, C.S.: Primary object segmentation in videos based on region augmentation and reduction. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.784"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Li, F., Kim, T., Humayun, A., Tsai, D., Rehg, J.M.: Video segmentation by tracking many figure-ground segments. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2192\u20132199 (2013)","DOI":"10.1109\/ICCV.2013.273"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Li, H., Chen, G., Li, G., Yu, Y.: Motion guided attention for video salient object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7274\u20137283 (2019)","DOI":"10.1109\/ICCV.2019.00737"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Li, S., Seybold, B., Vorobyov, A., Fathi, A., Huang, Q., Kuo, C.C.J.: 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":"14_CR14","doi-asserted-by":"crossref","unstructured":"Lu, X., Wang, W., Ma, C., Shen, J., Shao, L., Porikli, F.: See more, know more: unsupervised video object segmentation with co-attention Siamese networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3623\u20133632 (2019)","DOI":"10.1109\/CVPR.2019.00374"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Miao, J., Wei, Y., Yang, Y.: Memory aggregation networks for efficient interactive video object segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10366\u201310375 (2020)","DOI":"10.1109\/CVPR42600.2020.01038"},{"issue":"6","key":"14_CR16","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1109\/TPAMI.2013.242","volume":"36","author":"P Ochs","year":"2013","unstructured":"Ochs, P., Malik, J., Brox, T.: Segmentation of moving objects by long term video analysis. IEEE Trans. Pattern Anal. Mach. Intell. 36(6), 1187\u20131200 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van\u00a0Gool, 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":"14_CR18","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1007\/978-3-031-18907-4_51","volume-title":"Pattern Recognition and Computer Vision (PRCV)","author":"J Rao","year":"2022","unstructured":"Rao, J., Xu, T., Song, X., Feng, Z.H., Wu, X.J.: Kitpose: Keypoint-interactive transformer for animal pose estimation. In: Yu, S., et al. (eds.) PRCV 2022. LNCS, vol. 13534, pp. 660\u2013673. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-18907-4_51"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Song, H., Wang, W., Zhao, S., Shen, J., Lam, K.M.: Pyramid dilated deeper ConvLSTM for video salient object detection. In: Proceedings of the European conference on computer vision (ECCV), pp. 715\u2013731 (2018)","DOI":"10.1007\/978-3-030-01252-6_44"},{"key":"14_CR20","unstructured":"Tan, M., Le, Q.: Efficientnetv2: smaller models and faster training. In: International Conference on Machine Learning, pp. 10096\u201310106. PMLR (2021)"},{"key":"14_CR21","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":"14_CR22","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H., Hung, W.C., Schulter, S., Sohn, K., Yang, M.H., Chandraker, M.: Learning to adapt structured output space for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7472\u20137481 (2018)","DOI":"10.1109\/CVPR.2018.00780"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Learning to detect salient objects with image-level supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 136\u2013145 (2017)","DOI":"10.1109\/CVPR.2017.404"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Wang, W., Lu, X., Shen, J., Crandall, D.J., Shao, L.: Zero-shot video object segmentation via attentive graph neural networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9236\u20139245 (2019)","DOI":"10.1109\/ICCV.2019.00933"},{"issue":"1","key":"14_CR25","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/TIP.2017.2754941","volume":"27","author":"W Wang","year":"2017","unstructured":"Wang, W., Shen, J., Shao, L.: Video salient object detection via fully convolutional networks. IEEE Trans. Image Process. 27(1), 38\u201349 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR26","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":"14_CR27","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Yang, C., Lamdouar, H., Lu, E., Zisserman, A., Xie, W.: Self-supervised video object segmentation by motion grouping. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7177\u20137188 (2021)","DOI":"10.1109\/ICCV48922.2021.00709"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhang, L., Qi, J., Lu, H., Wang, S., Zhang, X.: Learning motion-appearance co-attention for zero-shot video object segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1564\u20131573 (2021)","DOI":"10.1109\/ICCV48922.2021.00159"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Yang, Y., Loquercio, A., Scaramuzza, D., Soatto, S.: Unsupervised moving object detection via contextual information separation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 879\u2013888 (2019)","DOI":"10.1109\/CVPR.2019.00097"},{"key":"14_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1007\/978-3-030-88007-1_43","volume-title":"Pattern Recognition and Computer Vision","author":"D Zhang","year":"2021","unstructured":"Zhang, D., Wu, X.-J., Yu, J.: Discrete bidirectional matrix factorization hashing for zero-shot cross-media retrieval. In: Ma, H., et al. (eds.) PRCV 2021. LNCS, vol. 13020, pp. 524\u2013536. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-88007-1_43"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zhao, Z., Liu, D., Liu, Q., Liu, B.: Deep transport network for unsupervised video object segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8781\u20138790 (2021)","DOI":"10.1109\/ICCV48922.2021.00866"},{"key":"14_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1007\/978-3-030-58568-6_29","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Zhang","year":"2020","unstructured":"Zhang, L., Zhang, J., Lin, Z., M\u011bch, R., Lu, H., He, Y.: Unsupervised video object segmentation with joint hotspot tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 490\u2013506. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_29"},{"key":"14_CR34","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.\u00a034, pp. 13066\u201313073 (2020)","DOI":"10.1609\/aaai.v34i07.7008"}],"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\/978-981-99-8537-1_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:09:10Z","timestamp":1703531350000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8537-1_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,26]]},"ISBN":["9789819985364","9789819985371"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8537-1_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,26]]},"assertion":[{"value":"26 December 2023","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":"Xiamen","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","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":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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)"}}]}}