{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:06:45Z","timestamp":1742990805844,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031783111"},{"type":"electronic","value":"9783031783128"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78312-8_13","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T12:37:44Z","timestamp":1733229464000},"page":"188-203","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Memory Matching is Not Enough: Jointly Improving Memory Matching and Decoding for Video Object Segmentation"],"prefix":"10.1007","author":[{"given":"Jintu","family":"Zheng","sequence":"first","affiliation":[]},{"given":"Yun","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Yuqing","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Wanchao","family":"Su","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Schwing, A.G.: XMem: Long-term video object segmentation with an atkinson-shiffrin memory model. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"13_CR2","unstructured":"Cheng, H.K., Tai, Y.W., Tang, C.K.: Rethinking space-time networks with improved memory coverage for efficient video object segmentation. In: Advances in Neural Information Processing Systems. vol.\u00a034, pp. 11781\u201311794 (2021)"},{"key":"13_CR3","unstructured":"Chu, X., Tian, Z., Wang, Y., Zhang, B., Ren, H., Wei, X., Xia, H., Shen, C.: Twins: Revisiting the design of spatial attention in vision transformers. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems. vol.\u00a034, pp. 9355\u20139366. Curran Associates, Inc. (2021)"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Gelautz, M.: Short papers_. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 35(2) (2013)","DOI":"10.1109\/TPAMI.2013.76"},{"key":"13_CR5","doi-asserted-by":"publisher","first-page":"7063","DOI":"10.1109\/TIP.2022.3219230","volume":"31","author":"P Guo","year":"2022","unstructured":"Guo, P., Zhang, W., Li, X., Zhang, W.: Adaptive online mutual learning bi-decoders for video object segmentation. IEEE Trans. Image Process. 31, 7063\u20137077 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Hu, L., Zhang, P., Zhang, B., Pan, P., Xu, Y., Jin, R.: Learning position and target consistency for memory-based video object segmentation pp. 4144\u20134154 (2021)","DOI":"10.1109\/CVPR46437.2021.00413"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Huang, Z., Shi, X., Zhang, C., Wang, Q., Cheung, K.C., Qin, H., Dai, J., Li, H.: Flowformer: A transformer architecture for optical flow. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XVII. pp. 668\u2013685. Springer (2022)","DOI":"10.1007\/978-3-031-19790-1_40"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Lu, X., Wang, W., Danelljan, M., Zhou, T., Shen, J., Van\u00a0Gool, L.: Video object segmentation with episodic graph memory networks pp. 661\u2013679 (2020)","DOI":"10.1007\/978-3-030-58580-8_39"},{"key":"13_CR10","unstructured":"Mei, J., Wang, M., Lin, Y., Liu, Y.: Transvos: Video object segmentation with transformers. arXiv preprint arXiv:2106.00588 (2021)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Nowozin, S.: Optimal decisions from probabilistic models: the intersection-over-union case. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 548\u2013555 (2014)","DOI":"10.1109\/CVPR.2014.77"},{"key":"13_CR12","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: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 7376\u20137385 (2018)","DOI":"10.1109\/CVPR.2018.00770"},{"key":"13_CR13","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: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 9225\u20139234 (2019)","DOI":"10.1109\/ICCV.2019.00932"},{"key":"13_CR14","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Van\u00a0Gool, L.: The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Qiao, S., Chen, L.C., Yuille, A.: Detectors: Detecting objects with recursive feature pyramid and switchable atrous convolution. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 10213\u201310224 (2021)","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"13_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1007\/978-3-030-58542-6_38","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Seong","year":"2020","unstructured":"Seong, H., Hyun, J., Kim, E.: Kernelized Memory Network for Video Object Segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 629\u2013645. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_38"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Seong, H., Hyun, J., Kim, E.: Video object segmentation using kernelized memory network with multiple kernels. IEEE transactions on pattern analysis and machine intelligence (2022)","DOI":"10.1109\/TPAMI.2022.3163375"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Seong, H., Oh, S.W., Lee, J.Y., Lee, S., Lee, S., Kim, E.: Hierarchical memory matching network for video object segmentation. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 12869\u201312878 (2021)","DOI":"10.1109\/ICCV48922.2021.01265"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 8934\u20138943 (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"13_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Teed","year":"2020","unstructured":"Teed, Z., Deng, J.: RAFT: Recurrent All-Pairs Field Transforms for Optical Flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"key":"13_CR21","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: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 9473\u20139482 (2019)","DOI":"10.1109\/CVPR.2019.00971"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, D., Wu, Z., Luo, C., Tang, C., Dai, X., Zhao, Y., Xie, Y., Yuan, L., Jiang, Y.G.: Look before you match: Instance understanding matters in video object segmentation. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp.\u00a00\u20130 (2023)","DOI":"10.1109\/CVPR52729.2023.00225"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Xie, H., Yao, H., Zhou, S., Zhang, S., Sun, W.: Efficient regional memory network for video object segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00134"},{"key":"13_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1007\/978-3-030-01228-1_36","volume-title":"Computer Vision \u2013 ECCV 2018","author":"N Xu","year":"2018","unstructured":"Xu, N., Yang, L., Fan, Y., Yang, J., Yue, D., Liang, Y., Price, B., Cohen, S., Huang, T.: YouTube-VOS: Sequence-to-Sequence Video Object Segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 603\u2013619. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_36"},{"key":"13_CR25","unstructured":"Yang, Z., Miao, J., Wang, X., Wei, Y., Yang, Y.: Associating objects with scalable transformers for video object segmentation. arXiv preprint arXiv:2203.11442 (2022)"},{"key":"13_CR26","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":"13_CR27","unstructured":"Yang, Z., Wei, Y., Yang, Y.: Associating objects with transformers for video object segmentation. In: Advances in Neural Information Processing Systems. vol.\u00a034, pp. 2491\u20132502 (2021)"},{"issue":"9","key":"13_CR28","first-page":"4701","volume":"44","author":"Z Yang","year":"2022","unstructured":"Yang, Z., Wei, Y., Yang, Y.: Collaborative video object segmentation by multi-scale foreground-background integration. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 4701\u20134712 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR29","unstructured":"Yang, Z., Yang, Y.: Decoupling features in hierarchical propagation for video object segmentation. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems. vol.\u00a035, pp. 36324\u201336336. Curran Associates, Inc. (2022)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78312-8_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T13:06:14Z","timestamp":1733231174000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78312-8_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031783111","9783031783128"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78312-8_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}