{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T17:21:16Z","timestamp":1770830476754,"version":"3.50.1"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62071171"],"award-info":[{"award-number":["62071171"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100006407","name":"Natural Science Foundation of Henan","doi-asserted-by":"crossref","award":["232300421023"],"award-info":[{"award-number":["232300421023"]}],"id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s13042-025-02774-y","type":"journal-article","created":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T15:25:21Z","timestamp":1754321121000},"page":"9649-9664","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Attention-nested dual-branch network in real-time semantic segmentation"],"prefix":"10.1007","volume":"16","author":[{"given":"Jiali","family":"Xing","sequence":"first","affiliation":[]},{"given":"Siming","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Lintao","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Yongsheng","family":"Dong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,4]]},"reference":[{"issue":"8","key":"2774_CR1","doi-asserted-by":"publisher","first-page":"3128","DOI":"10.1109\/TCSVT.2020.3037234","volume":"31","author":"J Zhuang","year":"2021","unstructured":"Zhuang J, Wang Z, Wang B (2021) Video semantic segmentation with distortion-aware feature correction. IEEE Trans Circuits Syst Video Technol 31(8):3128\u20133139","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"10","key":"2774_CR2","doi-asserted-by":"publisher","first-page":"3483","DOI":"10.1007\/s13042-023-01845-2","volume":"14","author":"M Zhang","year":"2023","unstructured":"Zhang M, Chen K, Zhu J (2023) An efficient planning method based on deep reinforcement learning with hybrid actions for autonomous driving on highway. Int J Mach Learn Cybern 14(10):3483\u20133499","journal-title":"Int J Mach Learn Cybern"},{"issue":"1","key":"2774_CR3","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma J, He Y, Li F, Han L, You C, Wang B (2024) Segment anything in medical images. Nat Commun 15(1):654","journal-title":"Nat Commun"},{"key":"2774_CR4","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1007\/s13042-021-01459-6","volume":"13","author":"F Cao","year":"2022","unstructured":"Cao F, Gao C, Ye H (2022) A novel method for image segmentation: two-stage decoding network with boundary attention. Int J Mach Learn Cybern 13:1461\u20131473","journal-title":"Int J Mach Learn Cybern"},{"key":"2774_CR5","doi-asserted-by":"publisher","first-page":"112827","DOI":"10.1016\/j.knosys.2024.112827","volume":"309","author":"S Chowdhury","year":"2025","unstructured":"Chowdhury S, Soni B (2025) R-vqa: a robust visual question answering model. Knowl-Based Syst 309:112827","journal-title":"Knowl-Based Syst"},{"issue":"8","key":"2774_CR6","doi-asserted-by":"publisher","first-page":"10479","DOI":"10.1007\/s13369-023-07661-8","volume":"48","author":"S Chowdhury","year":"2023","unstructured":"Chowdhury S, Soni B (2023) Qsfvqa: a time efficient, scalable and optimized vqa framework. Arab J Sci Eng 48(8):10479\u201310491","journal-title":"Arab J Sci Eng"},{"issue":"6","key":"2774_CR7","doi-asserted-by":"publisher","first-page":"70010","DOI":"10.1111\/coin.70010","volume":"40","author":"S Chowdhury","year":"2024","unstructured":"Chowdhury S, Soni B (2024) Beyond words: Esc-net revolutionizes vqa by elevating visual features and defying language priors. Comput Intell 40(6):70010","journal-title":"Comput Intell"},{"key":"2774_CR8","doi-asserted-by":"publisher","first-page":"109948","DOI":"10.1016\/j.engappai.2024.109948","volume":"142","author":"S Chowdhury","year":"2025","unstructured":"Chowdhury S, Soni B (2025) Envqa: improving visual question answering model by enriching the visual feature. Eng Appl Artif Intell 142:109948","journal-title":"Eng Appl Artif Intell"},{"key":"2774_CR9","doi-asserted-by":"publisher","first-page":"129906","DOI":"10.1016\/j.neucom.2025.129906","volume":"635","author":"S Chowdhury","year":"2025","unstructured":"Chowdhury S, Soni B (2025) Handling language prior and compositional reasoning issues in visual question answering system. Neurocomputing 635:129906","journal-title":"Neurocomputing"},{"key":"2774_CR10","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2774_CR11","doi-asserted-by":"crossref","unstructured":"Chen L-C, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder\u2013decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European conference on computer vision, pp 801\u2013818","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"2774_CR12","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2881\u20132890","DOI":"10.1109\/CVPR.2017.660"},{"key":"2774_CR13","doi-asserted-by":"crossref","unstructured":"Nirkin Y, Wolf L, Hassner T (2021) HyperSeg: patch-wise hypernetwork for real-time semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4061\u20134070","DOI":"10.1109\/CVPR46437.2021.00405"},{"issue":"4","key":"2774_CR14","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2018","unstructured":"Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"7","key":"2774_CR15","doi-asserted-by":"publisher","first-page":"5486","DOI":"10.1007\/s10489-024-05461-7","volume":"54","author":"O Sharma","year":"2024","unstructured":"Sharma O, Sahoo NC, Puhan NB (2024) Transformer based composite network for autonomous driving trajectory prediction on multi-lane highways. Appl Intell 54(7):5486\u20135520","journal-title":"Appl Intell"},{"key":"2774_CR16","doi-asserted-by":"publisher","first-page":"3145","DOI":"10.1007\/s13042-019-01005-5","volume":"10","author":"S Ghosh","year":"2019","unstructured":"Ghosh S, Pal A, Jaiswal S, Santosh K, Das N, Nasipuri M (2019) SegFast-V2: semantic image segmentation with less parameters in deep learning for autonomous driving. Int J Mach Learn Cybern 10:3145\u20133154","journal-title":"Int J Mach Learn Cybern"},{"issue":"10","key":"2774_CR17","doi-asserted-by":"publisher","first-page":"6211","DOI":"10.1109\/TCYB.2022.3163440","volume":"53","author":"J Guo","year":"2022","unstructured":"Guo J, Li D, He B, Ge SS (2022) An intelligent collaborative system for robot dynamics. IEEE Trans Cybern 53(10):6211\u20136221","journal-title":"IEEE Trans Cybern"},{"key":"2774_CR18","doi-asserted-by":"crossref","unstructured":"Zhao H, Qi X, Shen X, Shi J, Jia J (2018) Icnet for real-time semantic segmentation on high-resolution images. In: Proceedings of the European conference on computer vision, pp 405\u2013420","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"2774_CR19","doi-asserted-by":"crossref","unstructured":"Orsic M, Kreso I, Bevandic P, Segvic S (2019) In defense of pre-trained imagenet architectures for real-time semantic segmentation of road-driving images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 12607\u201312616","DOI":"10.1109\/CVPR.2019.01289"},{"key":"2774_CR20","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"2774_CR21","doi-asserted-by":"crossref","unstructured":"Howard A, Sandler M, Chu G, Chen L-C, Chen B, Tan M, Wang W, Zhu Y, Pang R, Vasudevan V, Le QV, Adam H (2019) Searching for mobilenetv3. In: Proceedings of the IEEE international conference on computer vision, pp 1314\u20131324","DOI":"10.1109\/ICCV.2019.00140"},{"key":"2774_CR22","doi-asserted-by":"crossref","unstructured":"Yu C, Wang J, Peng C, Gao C, Yu G, Sang N (2018) BiSeNet: bilateral segmentation network for real-time semantic segmentation. In: Proceedings of the European conference on computer vision, pp 325\u2013341","DOI":"10.1007\/978-3-030-01261-8_20"},{"issue":"11","key":"2774_CR23","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1007\/s11263-021-01515-2","volume":"129","author":"C Yu","year":"2021","unstructured":"Yu C, Gao C, Wang J, Yu G, Shen C, Sang N (2021) BiSeNet V2: bilateral network with guided aggregation for real-time semantic segmentation. Int J Comput Vis 129(11):3051\u20133068","journal-title":"Int J Comput Vis"},{"key":"2774_CR24","doi-asserted-by":"crossref","unstructured":"Fan M, Lai S, Huang J, Wei X, Chai Z, Luo J, Wei X (2021) Rethinking BiSeNet for real-time semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9716\u20139725","DOI":"10.1109\/CVPR46437.2021.00959"},{"issue":"8","key":"2774_CR25","doi-asserted-by":"publisher","first-page":"2847","DOI":"10.1007\/s13042-023-01802-z","volume":"14","author":"P Song","year":"2023","unstructured":"Song P, Li J, Fan H, Fan L (2023) DBCGN: dual branch cascade graph network for skin lesion segmentation. Int J Mach Learn Cybern 14(8):2847\u20132865","journal-title":"Int J Mach Learn Cybern"},{"issue":"12","key":"2774_CR26","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"19","key":"2774_CR27","doi-asserted-by":"publisher","first-page":"11065","DOI":"10.1007\/s00500-024-09869-8","volume":"28","author":"J Pan","year":"2024","unstructured":"Pan J, Guo Z, Wu C, Zhai W (2024) Parameter optimization of the field-road trajectory segmentation model based on the chaos sensing slime mould algorithm. Soft Comput 28(19):11065\u201311132","journal-title":"Soft Comput"},{"key":"2774_CR28","doi-asserted-by":"crossref","unstructured":"Lei M, Wu H, Lv X, Wang X (2025) CondSeg: a general medical image segmentation framework via contrast-driven feature enhancement. In: Proceedings of the AAAI conference on artificial intelligence, vol 39, pp 4571\u20134579","DOI":"10.1609\/aaai.v39i5.32482"},{"key":"2774_CR29","doi-asserted-by":"publisher","first-page":"110258","DOI":"10.1016\/j.compbiomed.2025.110258","volume":"194","author":"W Chen","year":"2025","unstructured":"Chen W, McMillan AB (2025) SASWISE-UE: segmentation and synthesis with interpretable scalable ensembles for uncertainty estimation. Comput Biol Med 194:110258","journal-title":"Comput Biol Med"},{"key":"2774_CR30","doi-asserted-by":"crossref","unstructured":"Li C, Liu X, Li W, Wang C, Liu H, Liu Y, Chen Z, Yuan Y (2025) U-KAN makes strong backbone for medical image segmentation and generation. In: Proceedings of the AAAI conference on artificial intelligence, vol 39, pp 4652\u20134660","DOI":"10.1609\/aaai.v39i5.32491"},{"issue":"1","key":"2774_CR31","doi-asserted-by":"publisher","first-page":"2032","DOI":"10.1038\/s41598-024-52063-x","volume":"14","author":"S Ali","year":"2024","unstructured":"Ali S, Ghatwary N, Jha D, Isik-Polat E, Polat G, Yang C, Li W, Galdran A, Ballester M\u00c1G, Thambawita V et al (2024) Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision challenge. Sci Rep 14(1):2032","journal-title":"Sci Rep"},{"key":"2774_CR32","unstructured":"Ma J, Li F, Wang B (2024) U-Mamba: enhancing long-range dependency for biomedical image segmentation. arXiv preprint arXiv:2401.04722"},{"key":"2774_CR33","doi-asserted-by":"crossref","unstructured":"Li H, Xiong P, Fan H, Sun J (2019) DFANet: deep feature aggregation for real-time semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9522\u20139531","DOI":"10.1109\/CVPR.2019.00975"},{"key":"2774_CR34","doi-asserted-by":"crossref","unstructured":"Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1251\u20131258","DOI":"10.1109\/CVPR.2017.195"},{"issue":"3","key":"2774_CR35","doi-asserted-by":"publisher","first-page":"3448","DOI":"10.1109\/TITS.2022.3228042","volume":"24","author":"H Pan","year":"2023","unstructured":"Pan H, Hong Y, Sun W, Jia Y (2023) Deep dual-resolution networks for real-time and accurate semantic segmentation of traffic scenes. IEEE Trans Intell Transp Syst 24(3):3448\u20133460","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"2774_CR36","doi-asserted-by":"crossref","unstructured":"Xu J, Xiong Z, Bhattacharyya SP (2023) PIDNet: a real-time semantic segmentation network inspired by pid controllers. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 19529\u201319539","DOI":"10.1109\/CVPR52729.2023.01871"},{"key":"2774_CR37","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie E, Wang W, Yu Z, Anandkumar A, Alvarez JM, Luo P (2021) SegFormer: simple and efficient design for semantic segmentation with transformers. Adv Neural Inf Process Syst 34:12077\u201312090","journal-title":"Adv Neural Inf Process Syst"},{"key":"2774_CR38","doi-asserted-by":"crossref","unstructured":"Zhang W, Huang Z, Luo G, Chen T, Wang X, Liu W, Yu G, Shen C (2022) TopFormer: token pyramid transformer for mobile semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12083\u201312093","DOI":"10.1109\/CVPR52688.2022.01177"},{"key":"2774_CR39","doi-asserted-by":"publisher","first-page":"130099","DOI":"10.1016\/j.neucom.2025.130099","volume":"637","author":"S Jia","year":"2025","unstructured":"Jia S, Dong Y, Mao C, Zheng L, Li Y, Liu K (2025) Multi-path feature enhancement network for real-time semantic segmentation. Neurocomputing 637:130099","journal-title":"Neurocomputing"},{"key":"2774_CR40","doi-asserted-by":"crossref","unstructured":"Song Q, Mei K, Huang R (2021) AttaNet: attention-augmented network for fast and accurate scene parsing. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, no. 3, pp 2567\u20132575","DOI":"10.1609\/aaai.v35i3.16359"},{"key":"2774_CR41","doi-asserted-by":"crossref","unstructured":"Dai Y, Gieseke F, Oehmcke S, Wu Y, Barnard K (2021) Attentional feature fusion. In: Proceedings of the IEEE Winter conference on applications of computer vision, pp 3560\u20133569","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"2774_CR42","first-page":"3422007","volume":"62","author":"Z Li","year":"2024","unstructured":"Li Z, Hu J, Wu K, Miao J, Wu J (2024) Adjacent-atrous mechanism for expanding global receptive fields: an end-to-end network for multi-attribute scene analysis in remote sensing imagery. IEEE Trans Geosci Remote Sens 62:3422007","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2774_CR43","first-page":"3516501","volume":"63","author":"Z Li","year":"2024","unstructured":"Li Z, Hu J, Wu K, Miao J, Wu J (2024) Comprehensive attribute difference attention network for remote sensing image semantic understanding. IEEE Trans Geosci Remote Sens 63:3516501","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2774_CR44","doi-asserted-by":"crossref","unstructured":"Li X, You A, Zhu Z, Zhao H, Yang M, Yang K, Tan S, Tong Y (2020) Semantic flow for fast and accurate scene parsing. In: Proceedings of the European conference on computer vision, pp 775\u2013793","DOI":"10.1007\/978-3-030-58452-8_45"},{"key":"2774_CR45","doi-asserted-by":"crossref","unstructured":"Hao Y, Liu Y, Wu Z, Han L, Chen Y, Chen G, Chu L, Tang S, Yu Z, Chen Z, Lai B (2021) Edgeflow: achieving practical interactive segmentation with edge-guided flow. In: Proceedings of the IEEE international conference on computer vision, pp 1551\u20131560","DOI":"10.1109\/ICCVW54120.2021.00180"},{"issue":"1","key":"2774_CR46","first-page":"550","volume":"44","author":"Z Huang","year":"2022","unstructured":"Huang Z, Wei Y, Wang X, Liu W, Huang TS, Shi H (2022) AlignSeg: feature-aligned segmentation networks. IEEE Trans Pattern Anal Mach Intell 44(1):550\u2013557","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2774_CR47","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1007\/s11263-023-01875-x","volume":"132","author":"X Li","year":"2023","unstructured":"Li X, Zhang J, Yang Y, Cheng G, Yang K, Tong Y, Tao D (2023) SFNet: faster and accurate semantic segmentation via semantic flow. Int J Comput Vis 132:466\u2013489","journal-title":"Int J Comput Vis"},{"key":"2774_CR48","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"issue":"2","key":"2774_CR49","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.patrec.2008.04.005","volume":"30","author":"GJ Brostow","year":"2009","unstructured":"Brostow GJ, Fauqueur J, Cipolla R (2009) Semantic object classes in video: a high-definition ground truth database. Pattern Recognit Lett 30(2):88\u201397","journal-title":"Pattern Recognit Lett"},{"key":"2774_CR50","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou B, Zhao H, Puig X, Xiao T, Fidler S, Barriuso A, Torralba A (2019) Semantic understanding of scenes through the ADE20K dataset. Int J Comput Vis 127:302\u2013321","journal-title":"Int J Comput Vis"},{"issue":"1","key":"2774_CR51","first-page":"105","volume":"1","author":"Y Ma","year":"2019","unstructured":"Ma Y, Yu D, Wu T, Wang H (2019) Paddlepaddle: an open-source deep learning platform from industrial practice. Front Data Domputing 1(1):105\u2013115","journal-title":"Front Data Domputing"},{"key":"2774_CR52","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2774_CR53","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS (2018) CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2774_CR54","doi-asserted-by":"crossref","unstructured":"Wang Q, Wu B, Zhu P, Li P, Zuo W, Hu Q (2020) ECA-Net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11534\u201311542","DOI":"10.1109\/CVPR42600.2020.01155"},{"issue":"4","key":"2774_CR55","doi-asserted-by":"publisher","first-page":"5558","DOI":"10.1109\/LRA.2020.3007457","volume":"5","author":"L Sun","year":"2020","unstructured":"Sun L, Yang K, Hu X, Hu W, Wang K (2020) Real-time fusion network for rgb-d semantic segmentation incorporating unexpected obstacle detection for road-driving images. IEEE Robot Autom Lett 5(4):5558\u20135565","journal-title":"IEEE Robot Autom Lett"},{"key":"2774_CR56","unstructured":"Elhassan MA, Yang C, Huang C, Munea TL, Hong X, Adam A, Benabid A (2022) S$$^2$$-FPN: scale-ware strip attention guided feature pyramid network for real-time semantic segmentation. arXiv preprint arXiv:2206.07298"},{"key":"2774_CR57","doi-asserted-by":"crossref","unstructured":"Kumaar S, Lyu Y, Nex F, Yang MY (2021) CABiNet: efficient context aggregation network for low-latency semantic segmentation. In: IEEE international conference on robotics and automation, pp 13517\u201313524","DOI":"10.1109\/ICRA48506.2021.9560977"},{"key":"2774_CR58","doi-asserted-by":"publisher","first-page":"7887","DOI":"10.1109\/TMM.2024.3372835","volume":"26","author":"Q Zhou","year":"2024","unstructured":"Zhou Q, Wang L, Gao G, Bin K, Ou W, Lu H (2024) Boundary-guided lightweight semantic segmentation with multi-scale semantic context. IEEE Trans Multimed 26:7887\u20137900","journal-title":"IEEE Trans Multimed"},{"key":"2774_CR59","doi-asserted-by":"publisher","first-page":"127625","DOI":"10.1016\/j.neucom.2024.127625","volume":"587","author":"KI Rashid","year":"2024","unstructured":"Rashid KI, Yang C, Huang C (2024) Fast-DSAGCN: enhancing semantic segmentation with multifaceted attention mechanisms. Neurocomputing 587:127625","journal-title":"Neurocomputing"},{"key":"2774_CR60","doi-asserted-by":"publisher","first-page":"107988","DOI":"10.1016\/j.engappai.2024.107988","volume":"133","author":"X Song","year":"2024","unstructured":"Song X, Fang X, Meng X, Fang X, Lv M, Zhuo Y (2024) Real-time semantic segmentation network with an enhanced backbone based on atrous spatial pyramid pooling module. Eng Appl Artif Intell 133:107988","journal-title":"Eng Appl Artif Intell"},{"key":"2774_CR61","doi-asserted-by":"crossref","unstructured":"Xu Z, Wu D, Yu C, Chu X, Sang N, Gao C (2024) SCTNet: single-branch CNN with transformer semantic information for real-time segmentation. In: Proceedings of the AAAI conference on artificial intelligence, vol 38, pp 6378\u20136386","DOI":"10.1609\/aaai.v38i6.28457"},{"key":"2774_CR62","doi-asserted-by":"publisher","first-page":"128991","DOI":"10.1016\/j.neucom.2024.128991","volume":"617","author":"Y Dong","year":"2025","unstructured":"Dong Y, Mao C, Zheng L, Wu Q (2025) DMANet: dual-branch multiscale attention network for real-time semantic segmentation. Neurocomputing 617:128991","journal-title":"Neurocomputing"},{"issue":"1","key":"2774_CR63","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1038\/s41598-024-84685-6","volume":"15","author":"B Ye","year":"2025","unstructured":"Ye B, Xue R, Wu Q (2025) A hybrid attention multi-scale fusion network for real-time semantic segmentation. Sci Rep 15(1):872","journal-title":"Sci Rep"},{"key":"2774_CR64","doi-asserted-by":"publisher","first-page":"127680","DOI":"10.1016\/j.eswa.2025.127680","volume":"2025","author":"H Luo","year":"2025","unstructured":"Luo H, Liu C, Shark L-K (2025) Saba: scale-adaptive attention and boundary aware network for real-time semantic segmentation. Expert Syst Appl 2025:127680","journal-title":"Expert Syst Appl"},{"key":"2774_CR65","first-page":"1","volume":"2025","author":"Z Ye","year":"2025","unstructured":"Ye Z, Yan H, Sun Y, Li B, Liu L, Wu W (2025) MSPNet: real-time semantic segmentation with large kernel and atrous convolutions. Vis Comput 2025:1\u201316","journal-title":"Vis Comput"},{"issue":"3","key":"2774_CR66","first-page":"3448","volume":"24","author":"Y Hong","year":"2022","unstructured":"Hong Y, Pan H, Sun W, Jia Y (2022) Deep dual-resolution networks for real-time and accurate semantic segmentation of road scenes. IEEE Trans Intell Transp Syst 24(3):3448\u20133460","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"2774_CR67","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.neucom.2023.02.025","volume":"532","author":"T-H Tsai","year":"2023","unstructured":"Tsai T-H, Tseng Y-W (2023) BiSeNet V3: bilateral segmentation network with coordinate attention for real-time semantic segmentation. Neurocomputing 532:33\u201342","journal-title":"Neurocomputing"},{"key":"2774_CR68","doi-asserted-by":"crossref","unstructured":"Cavagnero N, Rosi G, Cuttano C, Pistilli F, Ciccone M, Averta G, Cermelli F (2024) Pem: prototype-based efficient maskformer for image segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 15804\u201315813","DOI":"10.1109\/CVPR52733.2024.01496"},{"key":"2774_CR69","unstructured":"Yan H, Wu M, Zhang C (2024) Multi-scale representations by varying window attention for semantic segmentation. arXiv preprint arXiv:2404.16573"},{"key":"2774_CR70","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02774-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02774-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02774-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T11:24:50Z","timestamp":1762514690000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02774-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,4]]},"references-count":70,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["2774"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02774-y","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,4]]},"assertion":[{"value":"4 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 August 2025","order":3,"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":"Conflict of interest"}}]}}