{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T12:59:15Z","timestamp":1781182755355,"version":"3.54.1"},"reference-count":28,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T00:00:00Z","timestamp":1770595200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In complex image multi-task learning, the precision and effectiveness of feature extraction are often constrained by traditional convolutional methods, including issues with scale invariance and difficulties in feature sharing across tasks. To tackle these challenges, we introduce a straightforward but efficient model called AKSeg. AKSeg effectively combines Adaptive Kernel Convolution (AKConv) with a Nash-based multi-task learning strategy within the SegNet framework, improving the model\u2019s ability to capture multi-task features from images. First, AKSeg incorporates AKConv into the encoder layer of the SegNet. By dynamically adjusting the size and shape of convolutional kernels, AKSeg can accurately capture features of various scales from images. Then, a Nash game strategy is employed in the AKSeg to update parameters and weights as tasks change. To tackle challenges like feature extraction across varying tasks and improve multi-task learning capability, AKSeg utilizes multiple channels to efficiently extract distinct features for each task. Additionally, AKSeg addresses the issue of dead Rectified Linear Unit (ReLU) by eliminating inactive neurons through the use of Leaky Rectified Linear Unit (LeakyReLU). Extensive experimental results demonstrate that the AKSeg outperforms baseline methods remarkably. Specifically, AKSeg reduces the loss value by 4.48%, improves mIoU by 4.52%, and increases pixel accuracy by 1.73%. These results validate the usefulness of AKSeg in enhancing image multi-task learning performance.<\/jats:p>","DOI":"10.1093\/comjnl\/bxaf135","type":"journal-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T12:31:19Z","timestamp":1762777879000},"page":"644-654","source":"Crossref","is-referenced-by-count":0,"title":["AKSeg: combining variable kernel convolution with Nash multi task learning"],"prefix":"10.1093","volume":"69","author":[{"given":"Wei","family":"Xie","sequence":"first","affiliation":[{"name":"China Electronics Technology Group Corporation No. 10 Institute , No. 48 Yingkang Road, Jinniu District, Chengdu 610036 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keyu","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University , No. 999 Xi'an Road, Pidu District, Chengdu 611756 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenxing","family":"Yang","sequence":"additional","affiliation":[{"name":"China North Chemical Research and Design Institute, China North Industries Group Corporation Limited , No. 55 Zizhuyuan Road, Haidian District, Beijing 100089 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University , No. 999 Xi'an Road, Pidu District, Chengdu 611756 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobo","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University , No. 999 Xi'an Road, Pidu District, Chengdu 611756 ,","place":["China"]},{"name":"State Key Laboratory of Bridge Intelligent and Green Construction, Southwest Jiaotong University , No. 999 Xi'an Road, Pidu District, Chengdu 611756 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,2,9]]},"reference":[{"key":"2026061108211366300_ref1","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/978-3-031-04086-3_31","article-title":"Data-driven nonlinear modal analysis: a deep learning approach","volume-title":"Nonlinear Structures & Systems","author":"Li","year":"2023"},{"key":"2026061108211366300_ref2","volume-title":"Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2019), Prague, Czech Republic."},{"key":"2026061108211366300_ref3","volume-title":"Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023), Rhodes Island, Greece."},{"key":"2026061108211366300_ref4","volume":"141","journal-title":"Pattern Recognition"},{"key":"2026061108211366300_ref5","volume-title":"Proceedings of the 3rd International Conference on ICT for Digital, Smart, and Sustainable Development (ICIDSSD 2022), New Delhi, India."},{"key":"2026061108211366300_ref6","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.patrec.2018.07.012","article-title":"Multi-stage cascaded deconvolution for depth map and surface normal prediction from single image - sciencedirect","volume":"127","author":"A","year":"2019","journal-title":"Pattern Recogn Lett"},{"key":"2026061108211366300_ref7"},{"key":"2026061108211366300_ref8","volume-title":"Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, HI, USA."},{"key":"2026061108211366300_ref9","doi-asserted-by":"crossref","first-page":"2470","DOI":"10.3390\/electronics10202470","article-title":"CNN variants for computer vision: history, architecture, application, challenges and future scope","volume":"10","author":"Bhatt","year":"2021","journal-title":"Electronics"},{"key":"2026061108211366300_ref10","doi-asserted-by":"crossref","first-page":"105190","DOI":"10.1016\/j.imavis.2024.105190","article-title":"LDConv: linear deformable convolution for improving convolutional neural networks","volume":"149","author":"Zhang","year":"2024","journal-title":"Image and Vision Comput"},{"key":"2026061108211366300_ref11","volume-title":"Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, CA, USA"},{"key":"2026061108211366300_ref12","volume-title":"Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV 2017), Venice, Italy"},{"key":"2026061108211366300_ref13","journal-title":"Proceedings of the 39th International Conference on Machine Learning (ICML 2022), Baltimore, MD, USA."},{"key":"2026061108211366300_ref14","volume-title":"Proceedings of the 2017 International Conference on Radar, Antenna, Microwave, Electronics, and Telecommunications (ICRAMET 2017), Jakarta, Indonesia."},{"key":"2026061108211366300_ref15","volume-title":"Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV 2019), Seoul, South Korea."},{"key":"2026061108211366300_ref16","volume-title":"Proceedings of the 10th International Conference on Learning Representations (ICLR 2022), Virtual Event"},{"key":"2026061108211366300_ref17","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017), Copenhagen, Denmark."},{"key":"2026061108211366300_ref18","volume-title":"Proceedings of the 9th International Conference on Learning Representations (ICLR 2021), Virtual Event"},{"key":"2026061108211366300_ref19","volume-title":"Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), Las Vegas, NV, USA"},{"key":"2026061108211366300_ref20","volume-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"2026061108211366300_ref21","volume-title":"Proceedings of the 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC 2019), Beijing, China"},{"key":"2026061108211366300_ref22","volume-title":"Computer Vision \u2013 ECCV 2012, Florence, Italy"},{"key":"2026061108211366300_ref23","volume-title":"Proceedings of the Future Technologies Conference (FTC) 2020, Vancouver, Canada (Virtual)"},{"key":"2026061108211366300_ref24","volume-title":"Proceedings of the 33rd British Machine Vision Conference (BMVC 2022), London, UK"},{"key":"2026061108211366300_ref25","volume-title":"Proceedings of the 2019 IEEE International Conference on Robotics and Automation (ICRA 2019), Montreal, Canada"},{"key":"2026061108211366300_ref26","volume-title":"Proceedings of the 29th British Machine Vision Conference (BMVC 2018), Newcastle, UK."},{"key":"2026061108211366300_ref27","volume-title":"Proceedings of the 29th British Machine Vision Conference (BMVC 2018), Newcastle, UK."},{"key":"2026061108211366300_ref28","volume-title":"Proceedings of the 2023 International Joint Conference on Neural Networks (IJCNN 2023), Gold Coast, Australia"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/69\/4\/644\/66822033\/bxaf135.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/69\/4\/644\/66822033\/bxaf135.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T12:21:20Z","timestamp":1781180480000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/69\/4\/644\/8469546"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,9]]},"references-count":28,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,2,9]]},"published-print":{"date-parts":[[2026,4,18]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxaf135","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,4]]},"published":{"date-parts":[[2026,2,9]]}}}