{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T10:52:52Z","timestamp":1787482372986,"version":"build-2736575974"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"27","license":[{"start":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T00:00:00Z","timestamp":1734912000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T00:00:00Z","timestamp":1734912000000},"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":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-20533-z","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T05:21:08Z","timestamp":1734931268000},"page":"32821-32840","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["UPVIS: upsampled video query for offline video instance segmentation"],"prefix":"10.1007","volume":"84","author":[{"given":"Junho","family":"Jo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haesoo","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joon Seok","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongyoon","family":"Wee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5297-4649","authenticated-orcid":false,"given":"Nam Ik","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,23]]},"reference":[{"key":"20533_CR1","doi-asserted-by":"crossref","unstructured":"Bertasius G, Torresani L (2020) Classifying, segmenting, and tracking object instances in video with mask propagation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp 9739\u20139748","DOI":"10.1109\/CVPR42600.2020.00976"},{"key":"20533_CR2","doi-asserted-by":"crossref","unstructured":"Cao J, Anwer RM, Cholakkal H, Khan FS, Pang Y, Shao L (2020) Sipmask: spatial information preservation for fast image and video instance segmentation. In: Computer vision\u2013ECCV 2020: 16th european conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16, Springer pp 1\u201318","DOI":"10.1007\/978-3-030-58568-6_1"},{"key":"20533_CR3","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: ECCV","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"20533_CR4","unstructured":"Cheng B, Choudhuri A, Misra I, Kirillov A, Girdhar R, Schwing AG (2021) Mask2former for video instance segmentation. arXiv:2112.10764"},{"key":"20533_CR5","doi-asserted-by":"crossref","unstructured":"Cheng B, Misra I, Schwing AG, Kirillov A, Girdhar R (2022) Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1290\u20131299","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"20533_CR6","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"20533_CR7","doi-asserted-by":"crossref","unstructured":"Han SH, Hwang S, Oh SW, Park Y, Kim H, Kim MJ, Kim SJ (2022) Visolo: grid-based space-time aggregation for efficient online video instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp 2896\u20132905","DOI":"10.1109\/CVPR52688.2022.00291"},{"key":"20533_CR8","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"20533_CR9","doi-asserted-by":"crossref","unstructured":"Heo M, Hwang S, Hyun J, Kim H, Oh SW, Lee JY, Kim SJ (2023) A generalized framework for video instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp 14623\u201314632","DOI":"10.1109\/CVPR52729.2023.01405"},{"key":"20533_CR10","unstructured":"Heo M, Hwang S, Oh SW, Lee JY, Kim SJ (2022) Vita: video instance segmentation via object token association. In: Advances in neural information processing systems"},{"key":"20533_CR11","doi-asserted-by":"crossref","unstructured":"Hu H, Gu J, Zhang Z, Dai J, Wei Y (2018) Relation networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3588\u20133597","DOI":"10.1109\/CVPR.2018.00378"},{"key":"20533_CR12","first-page":"31265","volume":"35","author":"DA Huang","year":"2022","unstructured":"Huang DA, Yu Z, Anandkumar A (2022) Minvis: a minimal video instance segmentation framework without video-based training. Adv Neural Inf Process Syst 35:31265\u201331277","journal-title":"Adv Neural Inf Process Syst"},{"key":"20533_CR13","first-page":"13352","volume":"34","author":"S Hwang","year":"2021","unstructured":"Hwang S, Heo M, Oh SW, Kim SJ (2021) Video instance segmentation using inter-frame communication transformers. Adv Neural Inf Process Syst 34:13352\u201313363","journal-title":"Adv Neural Inf Process Syst"},{"key":"20533_CR14","doi-asserted-by":"crossref","unstructured":"Li X, Yuan H, Zhang W, Cheng G, Pang J, Loy CC (2023) Tube-link: a flexible cross tube baseline for universal video segmentation. In: ICCV","DOI":"10.1109\/ICCV51070.2023.01280"},{"key":"20533_CR15","doi-asserted-by":"crossref","unstructured":"Lim B, Son S, Kim H, Nah S, Mu Lee K (2017) Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops pp 136\u2013144","DOI":"10.1109\/CVPRW.2017.151"},{"key":"20533_CR16","doi-asserted-by":"crossref","unstructured":"Lin TY, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"20533_CR17","doi-asserted-by":"crossref","unstructured":"Liu Y, Cheng D, Zhang D, Xu S, Han J (2024) Capsule networks with residual pose routing. IEEE Trans Neural Netw Learn Syst","DOI":"10.1109\/TNNLS.2023.3347722"},{"issue":"7","key":"20533_CR18","first-page":"3688","volume":"44","author":"Y Liu","year":"2021","unstructured":"Liu Y, Zhang D, Zhang Q, Han J (2021) Part-object relational visual saliency. IEEE Trans Pattern Anal Mach Intell 44(7):3688\u20133704","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"20533_CR19","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision pp 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"20533_CR20","unstructured":"Meinhardt T, Feiszli M, Fan Y, Leal-Taixe L, Ranjan R (2023) Novis: a case for end-to-end near-online video instance segmentation. arXiv:2308.15266"},{"key":"20533_CR21","doi-asserted-by":"crossref","unstructured":"Milletari F, Navab N, Ahmadi SA (2016) V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 fourth international conference on 3D vision (3DV), IEEE pp 565\u2013571","DOI":"10.1109\/3DV.2016.79"},{"issue":"8","key":"20533_CR22","doi-asserted-by":"publisher","first-page":"2022","DOI":"10.1007\/s11263-022-01629-1","volume":"130","author":"J Qi","year":"2022","unstructured":"Qi J, Gao Y, Hu Y, Wang X, Liu X, Bai X, Belongie S, Yuille A, Torr PH, Bai S (2022) Occluded video instance segmentation: a benchmark. Int J Comput Vis 130(8):2022\u20132039","journal-title":"Int J Comput Vis"},{"key":"20533_CR23","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, Springer pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"20533_CR24","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"20533_CR25","doi-asserted-by":"crossref","unstructured":"Wang Y, Xu Z, Wang X, Shen C, Cheng B, Shen H, Xia H (2021) End-to-end video instance segmentation with transformers. In: Proc. IEEE conf. Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"20533_CR26","doi-asserted-by":"crossref","unstructured":"Wu J, Jiang Y, Bai S, Zhang W, Bai X (2022) Seqformer: sequential transformer for video instance segmentation. In: ECCV","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"20533_CR27","doi-asserted-by":"crossref","unstructured":"Wu J, Liu Q, Jiang Y, Bai S, Yuille A, Bai X (2022) In defense of online models for video instance segmentation. In: European conference on computer vision, Springer pp 588\u2013605","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"20533_CR28","doi-asserted-by":"crossref","unstructured":"Wu J, Liu Q, Jiang Y, Bai S, Yuille A, Bai X (2022) In defense of online models for video instance segmentation. In: ECCV","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"20533_CR29","doi-asserted-by":"crossref","unstructured":"Xia Z, Pan X, Song S, Li LE, Huang G (2022) Vision transformer with deformable attention. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4794\u20134803","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"20533_CR30","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":"20533_CR31","doi-asserted-by":"crossref","unstructured":"Yang S, Fang Y, Wang X, Li Y, Shan Y, Feng B, Liu W (2021) Tracking instances as queries. arXiv:2106.11963","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"20533_CR32","doi-asserted-by":"crossref","unstructured":"Yang S, Wang X, Li Y, Fang Y, Fang J, Liu W, Zhao X, Shan Y (2022) Temporally efficient vision transformer for video instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2885\u20132895","DOI":"10.1109\/CVPR52688.2022.00290"},{"key":"20533_CR33","doi-asserted-by":"crossref","unstructured":"Ying K, Zhong Q, Mao W, Wang Z, Chen H, Wu LY, Liu Y, Fan C, Zhuge Y, Shen C (2023) Ctvis: consistent training for online video instance segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 899\u2013908","DOI":"10.1109\/ICCV51070.2023.00089"},{"key":"20533_CR34","doi-asserted-by":"crossref","unstructured":"Zhang T, Tian X, Wu Y, Ji S, Wang X, Zhang Y, Wan P (2023) Dvis: decoupled video instance segmentation framework. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) pp 1282\u20131291","DOI":"10.1109\/ICCV51070.2023.00124"},{"key":"20533_CR35","unstructured":"Zhang T, Tian X, Zhou Y, Ji S, Wang X, Tao X, Zhang Y, Wan P, Wang Z, Wu Y (2023) Dvis++: improved decoupled framework for universal video segmentation. arXiv:2312.13305"},{"key":"20533_CR36","doi-asserted-by":"crossref","unstructured":"Zhou Y, Zhang T, Ji S, Yan S, Li X (2024) Dvis-daq: improving video segmentation via dynamic anchor queries. ECCV","DOI":"10.1007\/978-3-031-72973-7_26"},{"key":"20533_CR37","unstructured":"Zhu X, Su W, Lu L, Li B, Wang X, Dai J (2024) Deformable detr: deformable transformers for end-to-end object detection. arXiv:2010.04159x"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-20533-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-20533-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-20533-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T04:15:51Z","timestamp":1757132151000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-20533-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,23]]},"references-count":37,"journal-issue":{"issue":"27","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["20533"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-20533-z","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,23]]},"assertion":[{"value":"13 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 November 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}]}}