{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T19:24:21Z","timestamp":1768245861981,"version":"3.49.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1","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":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s11432-023-4648-7","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T14:45:52Z","timestamp":1768229152000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Task prior attention network for multi-task learning of dense prediction"],"prefix":"10.1007","volume":"69","author":[{"given":"Yangyang","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibo","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lefei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,4]]},"reference":[{"key":"4648_CR1","first-page":"3614","volume":"44","author":"S Vandenhende","year":"2022","unstructured":"Vandenhende S, Georgoulis S, van Gansbeke W, et al. Multi-task learning for dense prediction tasks: a survey. IEEE Trans Pattern Anal Mach Intell, 2022, 44: 3614\u20133633","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4648_CR2","first-page":"5693","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"K Sun","year":"2019","unstructured":"Sun K, Xiao B, Liu D, et al. Deep high-resolution representation learning for human pose estimation. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019. 5693\u20135703"},{"key":"4648_CR3","first-page":"3994","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"I Misra","year":"2016","unstructured":"Misra I, Shrivastava A, Gupta A, et al. Cross-stitch networks for multi-task learning. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2016. 3994\u20134003"},{"key":"4648_CR4","first-page":"675","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"D Xu","year":"2018","unstructured":"Xu D, Ouyang W, Wang X, et al. PAD-Net: multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018. 675\u2013684"},{"key":"4648_CR5","first-page":"3205","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Gao","year":"2019","unstructured":"Gao Y, Ma J, Zhao M, et al. Nddr-cnn: layerwise feature fusing in multi-task CNNs by neural discriminative dimensionality reduction. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019. 3205\u20133214"},{"key":"4648_CR6","first-page":"4513","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"L Zhou","year":"2020","unstructured":"Zhou L, Cui Z, Xu C, et al. Pattern-structure diffusion for multi-task learning. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020. 4513\u20134522"},{"key":"4648_CR7","first-page":"15849","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"D Bruggemann","year":"2021","unstructured":"Bruggemann D, Kanakis M, Obukhov A, et al. Exploring relational context for multi-task dense prediction. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, 2021. 15849\u201315858"},{"key":"4648_CR8","volume-title":"Proceedings of the 9th International Conference on Learning Representations","author":"A Dosovitskiy","year":"2021","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16\u00d716 words: transformers for image recognition at scale. In: Proceedings of the 9th International Conference on Learning Representations, 2021"},{"key":"4648_CR9","volume-title":"Proceedings of the 10th International Conference on Learning Representations","author":"W Wang","year":"2022","unstructured":"Wang W, Cao Y, Zhang J, et al. FP-DETR: detection transformer advanced by fully pre-training. In: Proceedings of the 10th International Conference on Learning Representations, 2022"},{"key":"4648_CR10","first-page":"9992","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"Z Liu","year":"2021","unstructured":"Liu Z, Lin Y, Cao Y, et al. Swin Transformer: hierarchical vision transformer using shifted windows. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, 2021. 9992\u201310002"},{"key":"4648_CR11","first-page":"12031","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"D Bhattacharjee","year":"2022","unstructured":"Bhattacharjee D, Zhang T, S\u00fcsstrunk S, et al. Mult: an end-to-end multitask learning transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022. 12031\u201312041"},{"key":"4648_CR12","first-page":"1871","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"S Liu","year":"2019","unstructured":"Liu S, Johns E, Davison A J. End-to-end multi-task learning with attention. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019. 1871\u20131880"},{"key":"4648_CR13","first-page":"1228","volume":"4","author":"Y Xu","year":"2023","unstructured":"Xu Y, Li X, Yuan H, et al. Multi-task learning with multi-query transformer for dense prediction. IEEE Trans Circ Syst Video Technol, 2023, 4: 1228\u20131240","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"4648_CR14","first-page":"10945","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"D S Raychaudhuri","year":"2022","unstructured":"Raychaudhuri D S, Suh Y, Schulter S, et al. Controllable dynamic multi-task architectures. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022. 10945\u201310954"},{"key":"4648_CR15","first-page":"304","volume-title":"Proceedings of European Conference on Computer Vision","author":"X Xu","year":"2022","unstructured":"Xu X, Zhao H, Vineet V, et al. MTFormer: multi-task learning via transformer and cross-task reasoning. In: Proceedings of European Conference on Computer Vision, 2022. 304\u2013321"},{"key":"4648_CR16","first-page":"12077","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"E Xie","year":"2021","unstructured":"Xie E, Wang W, Yu Z, et al. SegFormer: simple and efficient design for semantic segmentation with transformers. In: Proceedings of Advances in Neural Information Processing Systems, 2021. 12077\u201312090"},{"key":"4648_CR17","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Z Chen","year":"2023","unstructured":"Chen Z, Duan Y, Wang W, et al. Vision transformer adapter for dense predictions. In: Proceedings of the 11th International Conference on Learning Representations, 2023"},{"key":"4648_CR18","first-page":"746","volume-title":"Proceedings of European Conference on Computer Vision","author":"N Silberman","year":"2012","unstructured":"Silberman N, Hoiem D, Kohli P, et al. Indoor segmentation and support inference from RGBD images. In: Proceedings of European Conference on Computer Vision, 2012. 746\u2013760"},{"key":"4648_CR19","first-page":"1979","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"X Chen","year":"2014","unstructured":"Chen X, Mottaghi R, Liu X, et al. Detect what you can: detecting and representing objects using holistic models and body parts. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2014. 1979\u20131986"},{"key":"4648_CR20","first-page":"7482","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"A Kendall","year":"2018","unstructured":"Kendall A, Gal Y, Cipolla R. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018. 7482\u20137491"},{"key":"4648_CR21","first-page":"793","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Z Chen","year":"2018","unstructured":"Chen Z, Badrinarayanan V, Lee C, et al. GradNorm: gradient normalization for adaptive loss balancing in deep multitask networks. In: Proceedings of the 35th International Conference on Machine Learning, 2018. 793\u2013802"},{"key":"4648_CR22","first-page":"525","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"O Sener","year":"2018","unstructured":"Sener O, Koltun V. Multi-task learning as multi-objective optimization. In: Proceedings of Advances in Neural Information Processing Systems, 2018. 525\u2013536"},{"key":"4648_CR23","first-page":"1013","volume-title":"Proceedings of IEEE Intelligent Vehicles Symposium","author":"M Teichmann","year":"2018","unstructured":"Teichmann M, Weber M, Zoellner M, et al. Multinet: real-time joint semantic reasoning for autonomous driving. In: Proceedings of IEEE Intelligent Vehicles Symposium, 2018. 1013\u20131020"},{"key":"4648_CR24","first-page":"4106","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Zhang","year":"2019","unstructured":"Zhang Z, Cui Z, Xu C, et al. Pattern-affinitive propagation across depth, surface normal and semantic segmentation. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019. 4106\u20134115"},{"key":"4648_CR25","doi-asserted-by":"publisher","first-page":"180303","DOI":"10.1007\/s11432-020-2937-y","volume":"63","author":"J Jiang","year":"2020","unstructured":"Jiang J, Li Y, Chen L, et al. Multitask deep learning-based multiuser hybrid beamforming for mm-wave orthogonal frequency division multiple access systems. Sci China Inf Sci, 2020, 63: 180303","journal-title":"Sci China Inf Sci"},{"key":"4648_CR26","first-page":"11540","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Gao","year":"2020","unstructured":"Gao Y, Bai H, Jie Z, et al. MTL-NAS: task-agnostic neural architecture search towards general-purpose multi-task learning. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020. 11540\u201311549"},{"key":"4648_CR27","first-page":"527","volume-title":"Proceedings of European Conference on Computer Vision","author":"S Vandenhende","year":"2020","unstructured":"Vandenhende S, Georgoulis S, Gool LV. MTI-Net: multi-scale task interaction networks for multi-task learning. In: Proceedings of European Conference on Computer Vision, 2020. 527\u2013543"},{"key":"4648_CR28","first-page":"117","volume-title":"Proceedings of CAAI International Conference on Artificial Intelligence","author":"Y Xu","year":"2022","unstructured":"Xu Y, Zhang L. DGMLP: deformable gating MLP sharing for multi-task learning. In: Proceedings of CAAI International Conference on Artificial Intelligence, 2022. 117\u2013128"},{"key":"4648_CR29","doi-asserted-by":"publisher","first-page":"3072","DOI":"10.1609\/aaai.v37i3.25411","volume":"37","author":"Y Xu","year":"2023","unstructured":"Xu Y, Yang Y, Zhang L. DeMT: deformable mixer transformer for multi-task learning of dense prediction. AAAI, 2023, 37: 3072\u20133080","journal-title":"AAAI"},{"key":"4648_CR30","first-page":"514","volume-title":"Proceedings of European Conference on Computer Vision","author":"H Ye","year":"2022","unstructured":"Ye H, Xu D. Inverted pyramid multi-task transformer for dense scene understanding. In: Proceedings of European Conference on Computer Vision, 2022. 514\u2013530"},{"key":"4648_CR31","first-page":"213","volume-title":"Proceedings of European Conference on Computer Vision","author":"N Carion","year":"2020","unstructured":"Carion N, Massa F, Synnaeve G, et al. End-to-End object detection with transformers. In: Proceedings of European Conference on Computer Vision, 2020. 213\u2013229"},{"key":"4648_CR32","first-page":"2286","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"S d\u2019Ascoli","year":"2021","unstructured":"d\u2019Ascoli S, Touvron H, Leavitt M L, et al. ConViT: improving vision transformers with soft convolutional inductive biases. In: Proceedings of the 38th International Conference on Machine Learning, 2021. 2286\u20132296"},{"key":"4648_CR33","doi-asserted-by":"publisher","first-page":"122104","DOI":"10.1007\/s11432-021-3340-y","volume":"66","author":"S Hussain","year":"2023","unstructured":"Hussain S, Xi X M, Ullah I, et al. Difficulty-aware prior-guided hierarchical network for adaptive segmentation of breast tumors. Sci China Inf Sci, 2023, 66: 122104","journal-title":"Sci China Inf Sci"},{"key":"4648_CR34","first-page":"74","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"B Kim","year":"2021","unstructured":"Kim B, Lee J, Kang J, et al. HOTR: end-to-end human-object interaction detection with transformers. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021. 74\u201383"},{"key":"4648_CR35","first-page":"582","volume-title":"Proceedings of European Conference on Computer Vision","author":"H Yuan","year":"2022","unstructured":"Yuan H, Li X, Yang Y, et al. PolyphonicFormer: unified query learning for depth-aware video panoptic segmentation. In: Proceedings of European Conference on Computer Vision, 2022. 582\u2013599"},{"key":"4648_CR36","first-page":"1228","volume-title":"Proceedings of the 36th AAAI Conference on Artificial Intelligence","author":"M Lan","year":"2022","unstructured":"Lan M, Zhang J, He F, et al. Siamese network with interactive transformer for video object segmentation. In: Proceedings of the 36th AAAI Conference on Artificial Intelligence, 2022. 1228\u20131236"},{"key":"4648_CR37","first-page":"16825","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"L Ru","year":"2022","unstructured":"Ru L, Zhan Y, Yu B, et al. Learning affinity from attention: end-to-end weakly-supervised semantic segmentation with transformers. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022. 16825\u201316834"},{"key":"4648_CR38","first-page":"357","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"Z Peng","year":"2021","unstructured":"Peng Z, Huang W, Gu S, et al. Conformer: local features coupling global representations for visual recognition. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, 2021. 357\u2013366"},{"key":"4648_CR39","first-page":"5260","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Chen","year":"2022","unstructured":"Chen Y, Dai X, Chen D, et al. Mobile-former: bridging mobileNet and transformer. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022. 5260\u20135269"},{"key":"4648_CR40","doi-asserted-by":"publisher","first-page":"4674","DOI":"10.1145\/3503161.3548348","volume-title":"Proceedings of ACM International Conference on Multimedia","author":"M Huang","year":"2022","unstructured":"Huang M, Zhang L. Atrous pyramid transformer with spectral convolution for image inpainting. In: Proceedings of ACM International Conference on Multimedia, 2022. 4674\u20134683"},{"key":"4648_CR41","first-page":"22","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"H Wu","year":"2021","unstructured":"Wu H, Xiao B, Codella N, et al. CvT: introducing convolutions to vision transformers. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, 2021. 22\u201331"},{"key":"4648_CR42","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1109\/MGRS.2022.3145854","volume":"10","author":"L Zhang","year":"2022","unstructured":"Zhang L, Zhang L. Artificial intelligence for remote sensing data analysis: a review of challenges and opportunities. IEEE Geosci Remote Sens Mag, 2022, 10: 270\u2013294","journal-title":"IEEE Geosci Remote Sens Mag"},{"key":"4648_CR43","doi-asserted-by":"publisher","first-page":"222104","DOI":"10.1007\/s11432-021-3558-y","volume":"65","author":"Y N Song","year":"2022","unstructured":"Song Y N, Gao L, Li X Y, et al. A novel vision-based multi-task robotic grasp detection method for multi-object scenes. Sci China Inf Sci, 2022, 65: 222104","journal-title":"Sci China Inf Sci"},{"key":"4648_CR44","doi-asserted-by":"publisher","first-page":"160109","DOI":"10.1007\/s11432-021-3435-8","volume":"65","author":"K J Zhang","year":"2022","unstructured":"Zhang K J, Zhang R, Wu Y L, et al. Few-shot font style transfer with multiple style encoders. Sci China Inf Sci, 2022, 65: 160109","journal-title":"Sci China Inf Sci"},{"key":"4648_CR45","first-page":"12239","volume-title":"Proceedings of 2021 IEEE\/CVF International Conference on Computer Vision","author":"B Graham","year":"2021","unstructured":"Graham B, El-Nouby A, Touvron H, et al. LeViT: a vision transformer in convNet\u2019s clothing for faster inference. In: Proceedings of 2021 IEEE\/CVF International Conference on Computer Vision, 2021. 12239\u201312249"},{"key":"4648_CR46","first-page":"3965","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Z Dai","year":"2021","unstructured":"Dai Z, Liu H, Le QV, et al. Coatnet: marrying convolution and attention for all data sizes. In: Proceedings of Advances in Neural Information Processing Systems, 2021. 34: 3965\u20133977"},{"key":"4648_CR47","first-page":"5998","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of Advances in Neural Information Processing Systems, 2017. 5998\u20136008"},{"key":"4648_CR48","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1007\/s11263-022-01739-w","volume":"131","author":"Q Zhang","year":"2023","unstructured":"Zhang Q, Xu Y, Zhang J, et al. ViTAEv2: vision transformer advanced by exploring inductive bias for image recognition and beyond. Int J Comput Vis, 2023, 131: 1141\u20131162","journal-title":"Int J Comput Vis"},{"key":"4648_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3335484","volume":"61","author":"J Wang","year":"2023","unstructured":"Wang J, Li W, Zhang M, et al. Remote-sensing scene classification via multistage self-guided separation network. IEEE Trans Geosci Remote Sens, 2023, 61: 1\u201312","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"4648_CR50","doi-asserted-by":"publisher","first-page":"3153","DOI":"10.1109\/TCYB.2022.3169773","volume":"53","author":"M Zhang","year":"2022","unstructured":"Zhang M, Li W, Zhang Y, et al. Hyperspectral and LiDAR data classification based on structural optimization transmission. IEEE Trans Cybern, 2022, 53: 3153\u20133164","journal-title":"IEEE Trans Cybern"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-4648-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-023-4648-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-4648-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T16:05:34Z","timestamp":1768233934000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-023-4648-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["4648"],"URL":"https:\/\/doi.org\/10.1007\/s11432-023-4648-7","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"17 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"112108"}}