{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T20:50:24Z","timestamp":1758055824705,"version":"3.44.0"},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T00:00:00Z","timestamp":1749427200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T00:00:00Z","timestamp":1749427200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Macau University of Science and Technology Faculty Research Grants","award":["FRG-24-028-FIE"],"award-info":[{"award-number":["FRG-24-028-FIE"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972460, 62372470, 62272481, 62172440, 62072471"],"award-info":[{"award-number":["61972460, 62372470, 62272481, 62172440, 62072471"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Science and Technology Innovation Program of Hunan Province","award":["2023RC1029"],"award-info":[{"award-number":["2023RC1029"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s00371-025-04012-6","type":"journal-article","created":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T03:55:55Z","timestamp":1749441355000},"page":"9933-9950","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Privacy-aware Real-Time Target Person Matting in Multi-Person Scenes Using Dual Encoder-Decoder Networks"],"prefix":"10.1007","volume":"41","author":[{"given":"Jiang","family":"Xin","sequence":"first","affiliation":[]},{"given":"Xiaonan","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Xueling","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Ruyi","family":"Dai","sequence":"additional","affiliation":[]},{"given":"Ju","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Wenzhen","family":"Yue","sequence":"additional","affiliation":[]},{"given":"Yaoxue","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,9]]},"reference":[{"key":"4012_CR1","doi-asserted-by":"crossref","unstructured":"Sengupta, S., Jayaram, V., Curless, B., Seitz, S.M., Kemelmacher-Shlizerman, I.: Background matting: The world is your green screen. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2291\u20132300 (2020)","DOI":"10.1109\/CVPR42600.2020.00236"},{"key":"4012_CR2","doi-asserted-by":"crossref","unstructured":"Ke, Z., Sun, J., Li, K., Yan, Q., Lau, R.W.: Modnet: Real-time trimap-free portrait matting via objective decomposition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 1140\u20131147 (2022)","DOI":"10.1609\/aaai.v36i1.19999"},{"key":"4012_CR3","doi-asserted-by":"crossref","unstructured":"Lin, S., Yang, L., Saleemi, I., Sengupta, S.: Robust high-resolution video matting with temporal guidance. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 238\u2013247 (2022)","DOI":"10.1109\/WACV51458.2022.00319"},{"key":"4012_CR4","doi-asserted-by":"crossref","unstructured":"Li, J., Goel, V., Ohanyan, M., Navasardyan, S., Wei, Y., Shi, H.: Vmformer: End-to-end video matting with transformer. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6678\u20136687 (2024)","DOI":"10.1109\/WACV57701.2024.00654"},{"key":"4012_CR5","doi-asserted-by":"crossref","unstructured":"Xu, N., Price, B., Cohen, S., Huang, T.: Deep image matting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2970\u20132979 (2017)","DOI":"10.1109\/CVPR.2017.41"},{"key":"4012_CR6","doi-asserted-by":"crossref","unstructured":"Aksoy, Y., Ozan\u00a0Aydin, T., Pollefeys, M.: Designing effective inter-pixel information flow for natural image matting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 29\u201337 (2017)","DOI":"10.1109\/CVPR.2017.32"},{"key":"4012_CR7","doi-asserted-by":"crossref","unstructured":"Cai, S., Zhang, X., Fan, H., Huang, H., Liu, J., Liu, J., Liu, J., Wang, J., Sun, J.: Disentangled image matting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8819\u20138828 (2019)","DOI":"10.1109\/ICCV.2019.00891"},{"key":"4012_CR8","doi-asserted-by":"crossref","unstructured":"Li, Y., Lu, H.: Natural image matting via guided contextual attention. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11450\u201311457 (2020)","DOI":"10.1609\/aaai.v34i07.6809"},{"key":"4012_CR9","unstructured":"Forte, M., Piti\u00e9, F.: $$ f $$, $$ b $$, alpha matting. arXiv preprint arXiv:2003.07711 (2020)"},{"key":"4012_CR10","doi-asserted-by":"crossref","unstructured":"Lu, H., Dai, Y., Shen, C., Xu, S.: Indices matter: Learning to index for deep image matting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3266\u20133275 (2019)","DOI":"10.1109\/ICCV.2019.00336"},{"key":"4012_CR11","doi-asserted-by":"crossref","unstructured":"Sun, Y., Tang, C.-K., Tai, Y.-W.: Semantic image matting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11120\u201311129 (2021)","DOI":"10.1109\/CVPR46437.2021.01097"},{"key":"4012_CR12","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, G., Gu, Q., Tang, C.-K., Tai, Y.-W.: Deep video matting via spatio-temporal alignment and aggregation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6975\u20136984 (2021)","DOI":"10.1109\/CVPR46437.2021.00690"},{"key":"4012_CR13","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Wang, C., Cui, M., Ren, P., Xie, X., Hua, X.-S., Bao, H., Huang, Q., Xu, W.: Attention-guided temporally coherent video object matting. In: Proceedings of the 29th ACM International Conference on Multimedia. MM \u201921, pp. 5128\u20135137. Association for Computing Machinery, New York, NY, USA (2021). https:\/\/doi.org\/10.1145\/3474085.3475623","DOI":"10.1145\/3474085.3475623"},{"issue":"10","key":"4012_CR14","doi-asserted-by":"publisher","first-page":"5828","DOI":"10.1109\/TCSVT.2023.3260025","volume":"33","author":"Y Zhou","year":"2023","unstructured":"Zhou, Y., Zhou, L., Lam, T.L., Xu, Y.: Sampling propagation attention with trimap generation network for natural image matting. IEEE Transactions on Circuits and Systems for Video Technology 33(10), 5828\u20135843 (2023). https:\/\/doi.org\/10.1109\/TCSVT.2023.3260025","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"4012_CR15","doi-asserted-by":"crossref","unstructured":"Seong, H., Oh, S.W., Price, B., Kim, E., Lee, J.-Y.: One-trimap video matting. In: European Conference on Computer Vision, pp. 430\u2013448 (2022). Springer","DOI":"10.1007\/978-3-031-19818-2_25"},{"key":"4012_CR16","doi-asserted-by":"crossref","unstructured":"Huang, W.-L., Lee, M.-S.: End-to-end video matting with trimap propagation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14337\u201314347 (2023)","DOI":"10.1109\/CVPR52729.2023.01378"},{"key":"4012_CR17","doi-asserted-by":"crossref","unstructured":"Lin, S., Ryabtsev, A., Sengupta, S., Curless, B.L., Seitz, S.M., Kemelmacher-Shlizerman, I.: Real-time high-resolution background matting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8762\u20138771 (2021)","DOI":"10.1109\/CVPR46437.2021.00865"},{"key":"4012_CR18","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"4012_CR19","doi-asserted-by":"crossref","unstructured":"Shahrian, E., Rajan, D., Price, B., Cohen, S.: Improving image matting using comprehensive sampling sets. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 636\u2013643 (2013)","DOI":"10.1109\/CVPR.2013.88"},{"key":"4012_CR20","doi-asserted-by":"crossref","unstructured":"Shahrian, E., Rajan, D.: Weighted color and texture sample selection for image matting. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 718\u2013725 (2012). IEEE","DOI":"10.1109\/CVPR.2012.6247741"},{"issue":"7","key":"4012_CR21","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.1109\/TCSVT.2014.2302531","volume":"24","author":"M Jin","year":"2014","unstructured":"Jin, M., Kim, B.-K., Song, W.-J.: Adaptive propagation-based color-sampling for alpha matting. IEEE Transactions on Circuits and Systems for Video Technology 24(7), 1101\u20131110 (2014). https:\/\/doi.org\/10.1109\/TCSVT.2014.2302531","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"4012_CR22","doi-asserted-by":"crossref","unstructured":"Boda, J., Pandya, D.: A survey on image matting techniques. In: 2018 International Conference on Communication and Signal Processing (ICCSP), pp. 0765\u20130770 (2018). IEEE","DOI":"10.1109\/ICCSP.2018.8523834"},{"key":"4012_CR23","doi-asserted-by":"crossref","unstructured":"Sun, W., Luo, S., Wu, L.: An improved bayesian matting method based on image statistic characteristics. In: Sixth International Conference on Graphic and Image Processing (ICGIP 2014), vol. 9443, pp. 305\u2013309 (2015). SPIE","DOI":"10.1117\/12.2179335"},{"issue":"9","key":"4012_CR24","doi-asserted-by":"publisher","first-page":"2175","DOI":"10.1109\/TPAMI.2013.18","volume":"35","author":"Q Chen","year":"2013","unstructured":"Chen, Q., Li, D., Tang, C.-K.: Knn matting. IEEE transactions on pattern analysis and machine intelligence 35(9), 2175\u20132188 (2013)","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"4012_CR25","doi-asserted-by":"crossref","unstructured":"Qiao, Y., Liu, Y., Yang, X., Zhou, D., Xu, M., Zhang, Q., Wei, X.: Attention-guided hierarchical structure aggregation for image matting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13676\u201313685 (2020)","DOI":"10.1109\/CVPR42600.2020.01369"},{"issue":"7","key":"4012_CR26","doi-asserted-by":"publisher","first-page":"4324","DOI":"10.1109\/TCSVT.2021.3132461","volume":"32","author":"Y Xu","year":"2022","unstructured":"Xu, Y., Liu, B., Quan, Y., Ji, H.: Unsupervised deep background matting using deep matte prior. IEEE Transactions on Circuits and Systems for Video Technology 32(7), 4324\u20134337 (2022). https:\/\/doi.org\/10.1109\/TCSVT.2021.3132461","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"8","key":"4012_CR27","doi-asserted-by":"publisher","first-page":"3888","DOI":"10.1109\/TCSVT.2023.3234983","volume":"33","author":"L Hu","year":"2023","unstructured":"Hu, L., Kong, Y., Li, J., Li, X.: Effective local-global transformer for natural image matting. IEEE Transactions on Circuits and Systems for Video Technology 33(8), 3888\u20133898 (2023). https:\/\/doi.org\/10.1109\/TCSVT.2023.3234983","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"6","key":"4012_CR28","doi-asserted-by":"publisher","first-page":"2192","DOI":"10.1109\/TCSVT.2020.3024213","volume":"31","author":"F Zhou","year":"2021","unstructured":"Zhou, F., Tian, Y., Qi, Z.: Attention transfer network for nature image matting. IEEE Transactions on Circuits and Systems for Video Technology 31(6), 2192\u20132205 (2021). https:\/\/doi.org\/10.1109\/TCSVT.2020.3024213","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"4012_CR29","doi-asserted-by":"crossref","unstructured":"Yu, Q., Zhang, J., Zhang, H., Wang, Y., Lin, Z., Xu, N., Bai, Y., Yuille, A.: Mask guided matting via progressive refinement network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1154\u20131163 (2021)","DOI":"10.1109\/CVPR46437.2021.00121"},{"key":"4012_CR30","doi-asserted-by":"crossref","unstructured":"Park, K., Woo, S., Oh, S.W., Kweon, I.S., Lee, J.-Y.: Mask-guided matting in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1992\u20132001 (2023)","DOI":"10.1109\/CVPR52729.2023.00198"},{"issue":"8","key":"4012_CR31","doi-asserted-by":"publisher","first-page":"4041","DOI":"10.1109\/TCSVT.2023.3238580","volume":"33","author":"B Peng","year":"2023","unstructured":"Peng, B., Zhang, M., Lei, J., Fu, H., Shen, H., Huang, Q.: Rgb-d human matting: A real-world benchmark dataset and a baseline method. IEEE Transactions on Circuits and Systems for Video Technology 33(8), 4041\u20134053 (2023). https:\/\/doi.org\/10.1109\/TCSVT.2023.3238580","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"4012_CR32","doi-asserted-by":"crossref","unstructured":"Park, G., Son, S., Yoo, J., Kim, S., Kwak, N.: Matteformer: Transformer-based image matting via prior-tokens. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11696\u201311706 (2022)","DOI":"10.1109\/CVPR52688.2022.01140"},{"issue":"5","key":"4012_CR33","doi-asserted-by":"publisher","first-page":"3733","DOI":"10.1007\/s00371-023-03061-z","volume":"40","author":"S Song","year":"2024","unstructured":"Song, S., Chau, L.-P., Lin, Z.: Portrait matting using an attention-based memory network. The Visual Computer 40(5), 3733\u20133746 (2024)","journal-title":"The Visual Computer"},{"key":"4012_CR34","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":"4012_CR35","doi-asserted-by":"crossref","unstructured":"Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P.H., : Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"4012_CR36","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, Y., Guo, T., Xu, C., Deng, Y., Liu, Z., Ma, S., Xu, C., Xu, C., Gao, W.: Pre-trained image processing transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12299\u201312310 (2021)","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"4012_CR37","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"issue":"1","key":"4012_CR38","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2022","unstructured":"Han, K., Wang, Y., Chen, H., Chen, X., Guo, J., Liu, Z., Tang, Y., Xiao, A., Xu, C., Xu, Y.: A survey on vision transformer. IEEE transactions on pattern analysis and machine intelligence 45(1), 87\u2013110 (2022)","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"4012_CR39","doi-asserted-by":"crossref","unstructured":"Hu, L., Kong, Y., Li, J., Li, X.: Effective local-global transformer for natural image matting. IEEE Transactions on Circuits and Systems for Video Technology (2023)","DOI":"10.1109\/TCSVT.2023.3234983"},{"key":"4012_CR40","unstructured":"Ma, S., Li, J., Zhang, J., Zhang, H., Tao, D.: Rethinking portrait matting with privacy preserving. International journal of computer vision, 1\u201326 (2023)"},{"issue":"4","key":"4012_CR41","doi-asserted-by":"publisher","first-page":"2097","DOI":"10.1109\/TCSVT.2023.3300731","volume":"34","author":"Y Wang","year":"2024","unstructured":"Wang, Y., Tang, L., Zhong, Y., Li, B.: From composited to real-world: Transformer-based natural image matting. IEEE Transactions on Circuits and Systems for Video Technology 34(4), 2097\u20132111 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2023.3300731","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"4012_CR42","doi-asserted-by":"crossref","unstructured":"Yao, J., Wang, X., Ye, L., Liu, W.: Matte anything: Interactive natural image matting with segment anything models. arXiv preprint arXiv:2306.04121 (2023)","DOI":"10.1016\/j.imavis.2024.105067"},{"key":"4012_CR43","doi-asserted-by":"crossref","unstructured":"Li, J., Zhang, J., Tao, D.: Referring image matting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22448\u201322457 (2023)","DOI":"10.1109\/CVPR52729.2023.02150"},{"key":"4012_CR44","doi-asserted-by":"crossref","unstructured":"Sun, Y., Tang, C.-K., Tai, Y.-W.: Human instance matting via mutual guidance and multi-instance refinement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2647\u20132656 (2022)","DOI":"10.1109\/CVPR52688.2022.00267"},{"issue":"4","key":"4012_CR45","doi-asserted-by":"publisher","first-page":"2633","DOI":"10.1109\/TCSVT.2023.3306400","volume":"34","author":"Q Liu","year":"2024","unstructured":"Liu, Q., Zhang, S., Meng, Q., Zhong, B., Liu, P., Yao, H.: End-to-end human instance matting. IEEE Transactions on Circuits and Systems for Video Technology 34(4), 2633\u20132647 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2023.3306400","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"4012_CR46","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.-Y., et al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"4012_CR47","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: Transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7262\u20137272 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"4012_CR48","doi-asserted-by":"crossref","unstructured":"Koonce, B., Koonce, B.: Mobilenetv3. Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization, 125\u2013144 (2021)","DOI":"10.1007\/978-1-4842-6168-2_11"},{"issue":"4","key":"4012_CR49","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence 40(4), 834\u2013848 (2017)","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"4012_CR50","doi-asserted-by":"crossref","unstructured":"Wang, T., Liu, S., Tian, Y., Li, K., Yang, M.-H.: Video matting via consistency-regularized graph neural networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4902\u20134911 (2021)","DOI":"10.1109\/ICCV48922.2021.00486"},{"key":"4012_CR51","unstructured":"AISegment: AISegment.com - Matting Human Datasets. https:\/\/www.kaggle.com\/datasets\/laurentmih\/aisegmentcom-matting-human-datasets\/ Accessed 2021"},{"key":"4012_CR52","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: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755 (2014). Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"4012_CR53","doi-asserted-by":"crossref","unstructured":"Hou, Q., Liu, F.: Context-aware image matting for simultaneous foreground and alpha estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4130\u20134139 (2019)","DOI":"10.1109\/ICCV.2019.00423"},{"key":"4012_CR54","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: Transformer for semantic segmentation. arXiv preprint arXiv:2105.05633 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"4012_CR55","unstructured":"Kingma, D., Ba, J.: Adam: A method for stochastic optimization. Computer Science (2014)"},{"key":"4012_CR56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-020-3097-4","volume":"63","author":"S-M Hu","year":"2020","unstructured":"Hu, S.-M., Liang, D., Yang, G.-Y., Yang, G.-W., Zhou, W.-Y.: Jittor: a novel deep learning framework with meta-operators and unified graph execution. Science China Information Sciences 63, 1\u201321 (2020)","journal-title":"Science China Information Sciences"},{"key":"4012_CR57","doi-asserted-by":"crossref","unstructured":"Kim, T., Kim, K., Lee, J., Cha, D., Lee, J., Kim, D.: Revisiting image pyramid structure for high resolution salient object detection. In: Proceedings of the Asian Conference on Computer Vision, pp. 108\u2013124 (2022)","DOI":"10.1007\/978-3-031-26293-7_16"},{"key":"4012_CR58","unstructured":"CVPR: Human-centric Video Matting Challenge. https:\/\/maadaa.ai\/cvpr2021-human-centric-videomatting-challenge\/ Accessed 2021"},{"key":"4012_CR59","doi-asserted-by":"crossref","unstructured":"Rhemann, C., Rother, C., Wang, J., Gelautz, M., Kohli, P., Rott, P.: A perceptually motivated online benchmark for image matting. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1826\u20131833 (2009). IEEE","DOI":"10.1109\/CVPR.2009.5206503"},{"issue":"1","key":"4012_CR60","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":"4012_CR61","doi-asserted-by":"crossref","unstructured":"Yao, J., Chen, J., Niu, L., Sheng, B.: Scene-aware human pose generation using transformer. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 2847\u20132855 (2023)","DOI":"10.1145\/3581783.3612439"},{"key":"4012_CR62","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, B., Li, Z., Huang, H., Lu, C., Guo, Y.: Video object matting via hierarchical space-time semantic guidance. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5120\u20135129 (2023)","DOI":"10.1109\/WACV56688.2023.00509"},{"key":"4012_CR63","doi-asserted-by":"crossref","unstructured":"Sun, Y., Tang, C.-K., Tai, Y.-W.: Ultrahigh resolution image\/video matting with spatio-temporal sparsity. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14112\u201314121 (2023)","DOI":"10.1109\/CVPR52729.2023.01356"},{"issue":"4","key":"4012_CR64","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592423","volume":"42","author":"Z Gu","year":"2023","unstructured":"Gu, Z., Xian, W., Snavely, N., Davis, A.: Factormatte: Redefining video matting for re-composition tasks. ACM Transactions on Graphics (TOG) 42(4), 1\u201314 (2023)","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"4012_CR65","doi-asserted-by":"crossref","unstructured":"Li, J., Henschel, R., Goel, V., Ohanyan, M., Navasardyan, S., Shi, H.: Video instance matting. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6668\u20136677 (2024)","DOI":"10.1109\/WACV57701.2024.00653"},{"key":"4012_CR66","doi-asserted-by":"crossref","unstructured":"Li, J., Ohanyan, M., Goel, V., Navasardyan, S., Wei, Y., Shi, H.: Videomatt: A simple baseline for accessible real-time video matting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2176\u20132185 (2023)","DOI":"10.1109\/CVPRW59228.2023.00211"},{"key":"4012_CR67","doi-asserted-by":"crossref","unstructured":"Lin, C.-C., Wang, J., Luo, K., Lin, K., Li, L., Wang, L., Liu, Z.: Adaptive human matting for dynamic videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10229\u201310238 (2023)","DOI":"10.1109\/CVPR52729.2023.00986"},{"key":"4012_CR68","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Zharkov, I.: Lightweight portrait matting via regional attention and refinement. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 4158\u20134167 (2024)","DOI":"10.1109\/WACV57701.2024.00411"},{"key":"4012_CR69","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"4012_CR70","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Learning generalisable omni-scale representations for person re-identification. TPAMI (2021)","DOI":"10.1109\/TPAMI.2021.3069237"},{"issue":"4","key":"4012_CR71","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1016\/j.vrih.2022.08.010","volume":"5","author":"X Hu","year":"2023","unstructured":"Hu, X., Bao, X., Wei, G., Li, Z.: Human-pose estimation based on weak supervision. Virtual Reality & Intelligent Hardware 5(4), 366\u2013377 (2023)","journal-title":"Virtual Reality & Intelligent Hardware"},{"issue":"4\u20135","key":"4012_CR72","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1080\/10447318.2018.1543081","volume":"35","author":"A Kamel","year":"2019","unstructured":"Kamel, A., Liu, B., Li, P., Sheng, B.: An investigation of 3d human pose estimation for learning tai chi: A human factor perspective. International Journal of Human-Computer Interaction 35(4\u20135), 427\u2013439 (2019)","journal-title":"International Journal of Human-Computer Interaction"},{"issue":"5","key":"4012_CR73","doi-asserted-by":"publisher","first-page":"2774","DOI":"10.1109\/TSMC.2019.2916896","volume":"51","author":"K Aouaidjia","year":"2019","unstructured":"Aouaidjia, K., Sheng, B., Li, P., Kim, J., Feng, D.D.: Efficient body motion quantification and similarity evaluation using 3-d joints skeleton coordinates. IEEE Transactions on Systems, Man, and Cybernetics: Systems 51(5), 2774\u20132788 (2019)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"issue":"1","key":"4012_CR74","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.vrih.2023.07.002","volume":"6","author":"M Jiang","year":"2024","unstructured":"Jiang, M., Tian, Z., Yu, C., Shi, Y., Liu, L., Peng, T., Hu, X., Yu, F.: Intelligent 3d garment system of the human body based on deep spiking neural network. Virtual Reality & Intelligent Hardware 6(1), 43\u201355 (2024)","journal-title":"Virtual Reality & Intelligent Hardware"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04012-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04012-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04012-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T09:36:38Z","timestamp":1757928998000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04012-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,9]]},"references-count":74,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["4012"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04012-6","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2025,6,9]]},"assertion":[{"value":"14 May 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2025","order":2,"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 Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}