{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T22:54:14Z","timestamp":1774220054099,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Natural Science Foundation of China under Grant","award":["U1936213"],"award-info":[{"award-number":["U1936213"]}]},{"DOI":"10.13039\/501100012247","name":"Program of Shanghai Academic Research Leader","doi-asserted-by":"publisher","award":["21XD1421500"],"award-info":[{"award-number":["21XD1421500"]}],"id":[{"id":"10.13039\/501100012247","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Science and Technology Commission Project","award":["20020500600"],"award-info":[{"award-number":["20020500600"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s11760-026-05249-x","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:03:49Z","timestamp":1773169429000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TADeFormer: Harnessing temporal-spatial deformable attention for enhanced video instance segmentation"],"prefix":"10.1007","volume":"20","author":[{"given":"Jing","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoping","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mei","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"5249_CR1","doi-asserted-by":"crossref","unstructured":"Yang, L., Fan, Y., Xu, N.: Video instance segmentation. In: Int. Conf. Comput. Vis. (ICCV), pp. 5188\u20135197 (2019)","DOI":"10.1109\/ICCV.2019.00529"},{"key":"5249_CR2","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Int. Conf. Comput. Vis. (ICCV), pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"5249_CR3","doi-asserted-by":"crossref","unstructured":"Cao, J., Anwer, R.M., Cholakkal, H., Khan, F.S., Pang, Y., Shao, L.: Sipmask: Spatial information preservation for fast image and video instance segmentation. In: Eur. Conf. Comput. Vis. (ECCV), pp. 1\u201318 (2020)","DOI":"10.1007\/978-3-030-58568-6_1"},{"key":"5249_CR4","doi-asserted-by":"crossref","unstructured":"Liu, D., Cui, Y., Tan, W., Chen, Y.: Sg-net: Spatial granularity network for one-stage video instance segmentation. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR), pp. 9816\u20139825 (2021)","DOI":"10.1109\/CVPR46437.2021.00969"},{"key":"5249_CR5","unstructured":"Goel, V., Li, J., Garg, S., Maheshwari, H., Shi, H.: Msn: Efficient online mask selection network for video instance segmentation. arXiv preprint arXiv:2106.10452 (2021)"},{"issue":"1","key":"5249_CR6","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.vrih.2022.07.006","volume":"5","author":"M Zhang","year":"2023","unstructured":"Zhang, M., Tian, X.: Transformer architecture based on mutual attention for image-anomaly detection. Virtual Reality & Intelligent Hardware 5(1), 57\u201367 (2023)","journal-title":"Virtual Reality & Intelligent Hardware"},{"key":"5249_CR7","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2021","unstructured":"Lin, X., Sun, S., Huang, W., et al.: Eapt: Efficient attention pyramid transformer for image processing. IEEE Trans. Multimedia 25, 50\u201361 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"5249_CR8","doi-asserted-by":"crossref","unstructured":"Athar, A., Mahadevan, S., Osep, A., Leal-Taix\u00e9, L., Leibe, B.: Stem-seg: Spatio-temporal embeddings for instance segmentation in videos. In: Eur. Conf. Comput. Vis. (ECCV), pp. 158\u2013177 (2020). Springer","DOI":"10.1007\/978-3-030-58621-8_10"},{"key":"5249_CR9","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Torresani, L.: Classifying, segmenting, and tracking object instances in video with mask propagation. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR), pp. 9739\u20139748 (2020)","DOI":"10.1109\/CVPR42600.2020.00976"},{"key":"5249_CR10","first-page":"13352","volume":"34","author":"S Hwang","year":"2021","unstructured":"Hwang, S., Heo, M., Oh, S.W., Kim, S.J.: Video instance segmentation using inter-frame communication transformers. Adv. Neural Inform. Process. Syst. (NeurIPS) 34, 13352\u201313363 (2021)","journal-title":"Adv. Neural Inform. Process. Syst. (NeurIPS)"},{"key":"5249_CR11","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, Z., Wang, X., Shen, C., Cheng, B., Shen, H., Xia, H.: End-to-end video instance segmentation with transformers. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR), pp. 8741\u20138750 (2021)","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"5249_CR12","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need 30, (2017)"},{"key":"5249_CR13","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: Adv. Neural Inform. Process. Syst. (NeurIPS), 28 (2015)"},{"key":"5249_CR14","doi-asserted-by":"crossref","unstructured":"Wang, X., Kong, T., Shen, C., Jiang, Y., Li, L.: Solo: Segmenting objects by locations. In: Eur. Conf. Comput. Vis. (ECCV), pp. 649\u2013665 (2020). Springer","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"5249_CR15","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H.: Conditional convolutions for instance segmentation. In: Eur. Conf. Comput. Vis. (ECCV), pp. 282\u2013298 (2020). Springer","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"5249_CR16","unstructured":"Hu, J., Cao, L., Lu, Y., Zhang, S., Wang, Y., Li, K., Huang, F., Shao, L., Ji, R.: Istr: End-to-end instance segmentation with transformers. arXiv preprint arXiv:2105.00637 (2021)"},{"key":"5249_CR17","doi-asserted-by":"crossref","unstructured":"Fang, Y., Yang, S., Wang, X., Li, Y., Fang, C., Shan, Y., Feng, B., Liu, W.: Instances as queries. In: Int. Conf. Comput. Vis. (ICCV), pp. 6910\u20136919 (2021)","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"5249_CR18","doi-asserted-by":"crossref","unstructured":"Li, M., Li, S., Li, L., Zhang, L.: Spatial feature calibration and temporal fusion for effective one-stage video instance segmentation. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR), pp. 11215\u201311224 (2021)","DOI":"10.1109\/CVPR46437.2021.01106"},{"key":"5249_CR19","unstructured":"Cheng, B., Choudhuri, A., Misra, I., Kirillov, A., Girdhar, R., Schwing, A.G.: Mask2former for video instance segmentation. arXiv preprint arXiv:2112.10764 (2021)"},{"key":"5249_CR20","doi-asserted-by":"crossref","unstructured":"Wu, J., Jiang, Y., Bai, S., Zhang, W., Bai, X.: Seqformer: Sequential transformer for video instance segmentation. In: Eur. Conf. Comput. Vis. (ECCV), pp. 553\u2013569 (2022)","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"5249_CR21","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"5249_CR22","doi-asserted-by":"crossref","unstructured":"Gong, S., Zhuge, Y., Zhang, L., Yang, Z., Zhang, P., Lu, H.: The devil is in temporal token: High quality video reasoning segmentation. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR), pp. 29183\u201329192 (2025)","DOI":"10.1109\/CVPR52734.2025.02717"},{"issue":"5","key":"5249_CR23","doi-asserted-by":"publisher","first-page":"2293","DOI":"10.1002\/cav.2293","volume":"35","author":"Z Xiao","year":"2024","unstructured":"Xiao, Z., Chen, Y., Zhou, X., et al.: Human action recognition in immersive virtual reality based on multi-scale spatio-temporal attention network. Comput. Animat. Virtual Worlds 35(5), 2293 (2024)","journal-title":"Comput. Animat. Virtual Worlds"},{"key":"5249_CR24","doi-asserted-by":"crossref","unstructured":"Meeran, M.N., Mantha, B.P., et al.: Sam-pm: enhancing video camouflaged object detection using spatio-temporal attention. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR), pp. 1857\u20131866 (2024)","DOI":"10.1109\/CVPRW63382.2024.00192"},{"issue":"1","key":"5249_CR25","doi-asserted-by":"publisher","first-page":"2201","DOI":"10.1002\/cav.2201","volume":"35","author":"X Zhu","year":"2024","unstructured":"Zhu, X., Yao, X., Zhang, J., et al.: Tmsdnet: Transformer with multi-scale dense network for single and multi-view 3d reconstruction. Comput. Animat. Virtual Worlds 35(1), 2201 (2024)","journal-title":"Comput. Animat. Virtual Worlds"},{"key":"5249_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5249_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR), pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"issue":"1\u20132","key":"5249_CR28","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The hungarian method for the assignment problem. Naval Research Logistics Quarterly 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Research Logistics Quarterly"},{"key":"5249_CR29","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Int. Conf. Comput. Vis. (ICCV), pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"5249_CR30","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: A metric and a loss for bounding box regression. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR), pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"5249_CR31","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.-A.: V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565\u2013571 (2016). IEEE","DOI":"10.1109\/3DV.2016.79"},{"key":"5249_CR32","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR), pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"5249_CR33","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Eur. Conf. Comput. Vis. (ECCV), pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"5249_CR34","doi-asserted-by":"crossref","unstructured":"Wu, J., Jiang, Y., Sun, P., Yuan, Z., Luo, P.: Language as queries for referring video object segmentation. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR), pp. 4974\u20134984 (2022)","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"5249_CR35","doi-asserted-by":"crossref","unstructured":"Lin, H., Wu, R., Liu, S., Lu, J., Jia, J.: Video instance segmentation with a propose-reduce paradigm. In: Int. Conf. Comput. Vis. (ICCV), pp. 1739\u20131748 (2021)","DOI":"10.1109\/ICCV48922.2021.00176"},{"key":"5249_CR36","doi-asserted-by":"crossref","unstructured":"Thawakar, O., Narayan, S., Cao, J., Cholakkal, H., Anwer, R.M., Khan, M.H., Khan, S., Felsberg, M., Khan, F.S.: Video instance segmentation via multi-scale spatio-temporal split attention transformer. In: Eur. Conf. Comput. Vis. (ECCV), pp. 666\u2013681 (2022). Springer","DOI":"10.1007\/978-3-031-19818-2_38"},{"key":"5249_CR37","unstructured":"Xu, N., Yang, L., Yang, J., Yue, D., Fan, Y., Liang, Y., Huang, T.S.: YouTubeVIS Dataset 2021 Version. https:\/\/youtube-vos.org\/dataset\/vis\/ (2021)"},{"key":"5249_CR38","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: Int. Conf. Learn. Represent. (ICLR) (2017)"},{"key":"5249_CR39","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: Eur. Conf. Comput. Vis. (ECCV), pp. 740\u2013755 (2014). Springer","DOI":"10.1007\/978-3-319-10602-1_48"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05249-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-026-05249-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05249-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T22:15:33Z","timestamp":1774217733000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-026-05249-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":39,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["5249"],"URL":"https:\/\/doi.org\/10.1007\/s11760-026-05249-x","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"16 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2026","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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"169"}}