{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T14:04:05Z","timestamp":1774879445850,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819584130","type":"print"},{"value":"9789819584147","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-8414-7_32","type":"book-chapter","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T13:16:37Z","timestamp":1774876597000},"page":"582-596","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Prototype-Based Query Mechanism for\u00a0Video Instance Segmentation"],"prefix":"10.1007","author":[{"given":"Xiaoqing","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"key":"32_CR1","unstructured":"Zhan, Z., McKee, D., Lazebnik, S.: Robust online video instance segmentation with track queries. arXiv preprint arXiv:2211.09108 (2022)"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Wu, J., Liu, Q., Jiang, Y., Bai, S., Yuille, A., Bai, X.: In defense of online models for video instance segmentation. In: European Conference on Computer Vision, pp. 588\u2013605. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Zheng, R., et al.: TMT-VIS: taxonomy-aware multi-dataset joint training for video instance segmentation. In: Advances in Neural Information Processing Systems, vol.\u00a036, pp. 38\u00a0844\u201338\u00a0862 (2023)","DOI":"10.52202\/075280-1687"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Wang, Y., Ahsan, U., Li, H., Hagen, M., et al.: A comprehensive review of modern object segmentation approaches. Found. Trends\u00ae Comput. Graph. Vis. 13(2\u20133), 111\u2013283 (2022)","DOI":"10.1561\/0600000097"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Zheng, R., et al.: Syncvis: synchronized video instance segmentation. In: Advances in Neural Information Processing Systems, vol.\u00a037, pp. 49\u00a0461\u201349\u00a0483 (2024)","DOI":"10.52202\/079017-1565"},{"key":"32_CR6","unstructured":"Cheng, B., Choudhuri, A., Misra, I., Kirillov, A., Girdhar, R., Schwing, A.G.: Mask2former for video instance segmentation (2021). https:\/\/arxiv.org\/abs\/2112.10764"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"32_CR8","unstructured":"Karim, R., Wildes, R.P.: Understanding video transformers for segmentation: a survey of application and interpretability. arXiv preprint arXiv:2310.12296 (2023)"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Yang, L., Fan, Y., Xu, N.: Video instance segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5188\u20135197 (2019)","DOI":"10.1109\/ICCV.2019.00529"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Transformer-based visual segmentation: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3434373"},{"key":"32_CR11","unstructured":"Dong, J., et al.: Hierarchical visual prompt learning for continual video instance segmentation. arXiv preprint arXiv:2508.08612 (2025)"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Chen, M., Li, L., Wang, W., Quan, R., Yang, Y.: General and task-oriented video segmentation. In: European Conference on Computer Vision, pp. 72\u201392. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-72667-5_5"},{"key":"32_CR13","unstructured":"Lee, S., Seo, J., Han, K., Choi, M., Im, S.: Context-aware video instance segmentation. arXiv preprint arXiv:2407.03010 (2024)"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Koner, R., Wang, Z., Parthasarathy, S., Chen, C.: Local2global query alignment for video instance segmentation. arXiv preprint arXiv:2507.20120 (2025)","DOI":"10.1109\/ICCVW69036.2025.00405"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Koner, R., et al.: Instanceformer: an online video instance segmentation framework. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 1, pp. 1188\u20131195 (2023)","DOI":"10.1609\/aaai.v37i1.25201"},{"key":"32_CR16","unstructured":"Wang, X., Zhang, R., Kong, T., Li, L., Shen, C.: Solov2: dynamic and fast instance segmentation. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 17\u00a0721\u201317\u00a0732 (2020)"},{"issue":"8","key":"32_CR17","doi-asserted-by":"publisher","first-page":"2022","DOI":"10.1007\/s11263-022-01629-1","volume":"130","author":"J Qi","year":"2022","unstructured":"Qi, J., et al.: Occluded video instance segmentation: a benchmark. Int. J. Comput. Vis. 130(8), 2022\u20132039 (2022)","journal-title":"Int. J. Comput. Vis."},{"key":"32_CR18","unstructured":"Wang, W., Feiszli, M., Wang, H., Tran, D.: Unidentified video objects: a benchmark for dense, open-world segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10\u00a0776\u201310\u00a0785 (2021)"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: Crossover learning for fast online video instance segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8043\u20138052 (2021)","DOI":"10.1109\/ICCV48922.2021.00794"},{"key":"32_CR20","unstructured":"Hwang, S., Heo, M., Oh, S.W., Kim, S.J.: Video instance segmentation using inter-frame communication transformers. In: Advances in Neural Information Processing Systems, vol.\u00a034, pp. 13\u00a0352\u201313\u00a0363 (2021)"},{"key":"32_CR21","unstructured":"Wu, J., Jiang, Y., Zhang, W., Bai, X., Bai, S.: Seqformer: a frustratingly simple model for video instance segmentation. arXiv preprint arXiv:2112.08275, vol.\u00a02, no.\u00a03, p.\u00a04 (2021)"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: Trackformer: multi-object tracking with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8844\u20138854 (2022)","DOI":"10.1109\/CVPR52688.2022.00864"},{"issue":"3","key":"32_CR23","doi-asserted-by":"publisher","first-page":"997","DOI":"10.3390\/s24030997","volume":"24","author":"A Fothi","year":"2024","unstructured":"Fothi, A., Szlatincsan, A., Somfai, E.: Cluster2former: semisupervised clustering transformers for video instance segmentation. Sensors 24(3), 997 (2024)","journal-title":"Sensors"},{"key":"32_CR24","unstructured":"Ke, L., Danelljan, M., Ding, H., Tai, Y.-W., Tang, C.-K., Yu, F.: Mask-free video instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22\u00a0857\u201322\u00a0866 (2023)"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Huang, D.-A., Yu, Z., Anandkumar, A.: Minvis: a minimal video instance segmentation framework without video-based training. In: Advances in Neural Information Processing Systems, vol.\u00a035, pp. 31\u00a0265\u201331\u00a0277 (2022)","DOI":"10.52202\/068431-2267"},{"key":"32_CR26","unstructured":"Yang, Z., Liu, D., Cheng, W., Wang, J., Wu, Y.: PM-vis: high-performance box-supervised video instance segmentation. arXiv preprint arXiv:2404.13863 (2024)"},{"key":"32_CR27","unstructured":"Chen, K., et al.: Mmdetection: open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"32_CR28","unstructured":"M.\u00a0Contributors: Mmtracking: Openmmlab video perception toolbox and benchmark (2020). com\/open-mmlab\/mmtracking"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755. Springer, Cham (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"32_CR30","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"32_CR31","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"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8414-7_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T13:16:44Z","timestamp":1774876604000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8414-7_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819584130","9789819584147"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8414-7_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"31 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}