{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T02:40:49Z","timestamp":1787971249934,"version":"build-2784847793"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T00:00:00Z","timestamp":1718236800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T00:00:00Z","timestamp":1718236800000},"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":["62341603, 62006107"],"award-info":[{"award-number":["62341603, 62006107"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62341603, 62006107"],"award-info":[{"award-number":["62341603, 62006107"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Introduction and Cultivation Program for Young Innovative Talents of Universities in Shandong Province","award":["2021QCYY003"],"award-info":[{"award-number":["2021QCYY003"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1007\/s00371-024-03508-x","type":"journal-article","created":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T02:01:22Z","timestamp":1718244082000},"page":"5057-5066","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["ParaLkResNet: an efficient multi-scale image classification network"],"prefix":"10.1007","volume":"40","author":[{"given":"Tongshuai","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,6,13]]},"reference":[{"issue":"1","key":"3508_CR1","doi-asserted-by":"publisher","first-page":"3242","DOI":"10.1038\/s41467-021-23458-5","volume":"12","author":"L Dai","year":"2021","unstructured":"Dai, L., et al.: A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nat. Commun. 12(1), 3242 (2021)","journal-title":"Nat. Commun."},{"key":"3508_CR2","unstructured":"Dai, L., et al.: A deep learning system for predicting time to progression of diabetic retinopathy. Nat. Med. 1\u201311 (2024)"},{"key":"3508_CR3","doi-asserted-by":"publisher","first-page":"7192","DOI":"10.1109\/TIP.2020.2999854","volume":"29","author":"A Nazir","year":"2020","unstructured":"Nazir, A., et al.: OFF-eNET: an optimally fused fully end-to-end network for automatic dense volumetric 3D intracranial blood vessels segmentation. IEEE Trans. Image Process. 29, 7192\u20137202 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"3508_CR4","doi-asserted-by":"crossref","unstructured":"Qin, Y., et al.: UrbanEvolver: function-aware urban layout regeneration. Int. J. Comput. Vis. 1\u201320 (2024)","DOI":"10.1007\/s11263-024-02030-w"},{"key":"3508_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, Z., et al.: Deep colorization. In: Proceedings of the IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.55"},{"issue":"8","key":"3508_CR6","doi-asserted-by":"publisher","first-page":"2546","DOI":"10.1109\/TVCG.2019.2894627","volume":"26","author":"B Zhang","year":"2019","unstructured":"Zhang, B., et al.: Depth of field rendering using multilayer-neighborhood optimization. IEEE Trans. Vis. Comput. Gr. 26(8), 2546\u20132559 (2019)","journal-title":"IEEE Trans. Vis. Comput. Gr."},{"key":"3508_CR7","doi-asserted-by":"crossref","unstructured":"Jiang, N., et al.: Photohelper: portrait photographing guidance via deep feature retrieval and fusion. IEEE Trans. Multimed. (2022)","DOI":"10.1109\/TMM.2022.3144890"},{"issue":"7","key":"3508_CR8","doi-asserted-by":"publisher","first-page":"6662","DOI":"10.1109\/TCYB.2021.3079311","volume":"52","author":"B Sheng","year":"2021","unstructured":"Sheng, B., et al.: Improving video temporal consistency via broad learning system. IEEE Trans. Cybern. 52(7), 6662\u20136675 (2021)","journal-title":"IEEE Trans. Cybern."},{"key":"3508_CR9","doi-asserted-by":"crossref","unstructured":"Qian, B., et al.: DRAC 2022: a public benchmark for diabetic retinopathy analysis on ultra-wide optical coherence tomography angiography images. Patterns (2024)","DOI":"10.1016\/j.patter.2024.100929"},{"issue":"2","key":"3508_CR10","doi-asserted-by":"publisher","first-page":"1332","DOI":"10.1109\/TVCG.2018.2869326","volume":"26","author":"B Sheng","year":"2018","unstructured":"Sheng, B., et al.: Intrinsic image decomposition with step and drift shading separation. IEEE Trans. Vis. Comput. Gr. 26(2), 1332\u20131346 (2018)","journal-title":"IEEE Trans. Vis. Comput. Gr."},{"issue":"5","key":"3508_CR11","doi-asserted-by":"publisher","first-page":"2152","DOI":"10.1109\/TCYB.2018.2875983","volume":"50","author":"Z Chen","year":"2018","unstructured":"Chen, Z., et al.: Outdoor shadow estimating using multiclass geometric decomposition based on BLS. IEEE Trans. Cybern. 50(5), 2152\u20132165 (2018)","journal-title":"IEEE Trans. Cybern."},{"key":"3508_CR12","doi-asserted-by":"crossref","unstructured":"Wei, Y., et al.: SurroundOcc: multi-camera 3D occupancy prediction for autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01986"},{"issue":"1","key":"3508_CR13","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1109\/TII.2021.3085669","volume":"18","author":"J Li","year":"2021","unstructured":"Li, J., et al.: Automatic detection and classification system of domestic waste via multimodel cascaded convolutional neural network. IEEE Trans. Ind. Inform. 18(1), 163\u2013173 (2021)","journal-title":"IEEE Trans. Ind. Inform."},{"key":"3508_CR14","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning. PMLR (2019)"},{"key":"3508_CR15","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3508_CR16","unstructured":"Howard, A. G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. Preprint at arXiv:1704.04861 (2017)"},{"key":"3508_CR17","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Preprint at arXiv:1409.1556 (2014)"},{"key":"3508_CR18","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"3508_CR19","unstructured":"Krizhevsky, A., et al.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25 (2012)"},{"key":"3508_CR20","doi-asserted-by":"crossref","unstructured":"Xie, S., et al.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"3508_CR21","doi-asserted-by":"crossref","unstructured":"Zhao, H., et al.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"3508_CR22","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. Preprint at arXiv:2010.11929 (2020)"},{"key":"3508_CR23","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning. PMLR (2015)"},{"key":"3508_CR24","doi-asserted-by":"crossref","unstructured":"Hu, J., et al. Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"3508_CR25","doi-asserted-by":"crossref","unstructured":"Jia, X., et al.: U-net vs transformer: Is u-net outdated in medical image registration? In: International Workshop on Machine Learning in Medical Imaging. Springer (2022)","DOI":"10.1007\/978-3-031-21014-3_16"},{"key":"3508_CR26","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: MNGNAS: distilling adaptive combination of multiple searched networks for one-shot neural architecture search. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3293885"},{"key":"3508_CR27","doi-asserted-by":"crossref","unstructured":"Howard, A., et al.: Searching for mobilenetv3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"issue":"5","key":"3508_CR28","doi-asserted-by":"publisher","first-page":"2735","DOI":"10.1109\/TCYB.2019.2934823","volume":"51","author":"H Guo","year":"2019","unstructured":"Guo, H., et al.: Multiview high dynamic range image synthesis using fuzzy broad learning system. IEEE Trans. Cybern. 51(5), 2735\u20132747 (2019)","journal-title":"IEEE Trans. Cybern."},{"key":"3508_CR29","doi-asserted-by":"crossref","unstructured":"Chen, T., et al.: \" BNN-BN=?\": training binary neural networks without batch normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPRW53098.2021.00520"},{"key":"3508_CR30","first-page":"156","volume":"35","author":"Y Guo","year":"2022","unstructured":"Guo, Y., et al.: IM-loss: information maximization loss for spiking neural networks. Adv. Neural Inf. Process. Syst. 35, 156\u2013166 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3508_CR31","unstructured":"Arora, S., et al.: On the optimization of deep networks: Implicit acceleration by overparameterization. In: International Conference on Machine Learning. PMLR (2018)"},{"key":"3508_CR32","unstructured":"Guo, S., et al.: ExpandNet: training compact networks by linear expansion. Preprint: v3 (1811)"},{"key":"3508_CR33","unstructured":"Trockman, A., Kolter, J.Z.: Patches are all you need?\" Preprint at arXiv:2201.09792 (2022)"},{"key":"3508_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: EPSANet: an efficient pyramid squeeze attention block on convolutional neural network. In: Proceedings of the Asian Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-26313-2_33"},{"key":"3508_CR35","first-page":"15908","volume":"34","author":"K Han","year":"2021","unstructured":"Han, K., et al.: Transformer in transformer. Adv. Neural Inf. Process. Syst. 34, 15908\u201315919 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"8","key":"3508_CR36","doi-asserted-by":"publisher","first-page":"4499","DOI":"10.1109\/TNNLS.2021.3116209","volume":"34","author":"Z Xie","year":"2021","unstructured":"Xie, Z., et al.: BaGFN: broad attentive graph fusion network for high-order feature interactions. IEEE Trans. Neural Netw. Learn. Syst. 34(8), 4499\u20134513 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3508_CR37","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2021","unstructured":"Lin, X., et al.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimed. 25, 50\u201361 (2021)","journal-title":"IEEE Trans. Multimed."},{"key":"3508_CR38","unstructured":"Huo, X., et al.: HiFuse: hierarchical multi-scale feature fusion network for medical image classification (preprint) (2022)"},{"issue":"11","key":"3508_CR39","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00021","volume":"4","author":"A Araujo","year":"2019","unstructured":"Araujo, A., et al.: Computing receptive fields of convolutional neural networks. Distill 4(11), e21 (2019)","journal-title":"Distill"},{"key":"3508_CR40","doi-asserted-by":"crossref","unstructured":"Ding, X., et al.: RepVGG: making VGG-style convnets great again. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"3508_CR41","doi-asserted-by":"crossref","unstructured":"Ding, X., et al.: Scaling up your kernels to $$31\\times 31$$: revisiting large kernel design in CNNs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"3508_CR42","doi-asserted-by":"publisher","first-page":"3726","DOI":"10.1109\/TIP.2022.3175432","volume":"31","author":"J Cao","year":"2022","unstructured":"Cao, J., et al.: Do-conv: Depthwise over-parameterized convolutional layer. IEEE Trans. Image Process. 31, 3726\u20133736 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"3508_CR43","doi-asserted-by":"crossref","unstructured":"Zheng, Y., et al.: Regularizing neural networks via adversarial model perturbation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00806"},{"key":"3508_CR44","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)"},{"key":"3508_CR45","doi-asserted-by":"publisher","unstructured":"Darlow, L.N., et al.: CINIC-10 is not ImageNet or CIFAR-10. https:\/\/doi.org\/10.48550\/arXiv.1810.03505(2018)","DOI":"10.48550\/arXiv.1810.03505"},{"key":"3508_CR46","doi-asserted-by":"crossref","unstructured":"Pishchik, E.: Trainable activations for image classification (2023)","DOI":"10.20944\/preprints202301.0463.v1"},{"key":"3508_CR47","unstructured":"Romero, D. W., et al.: Flexconv: continuous kernel convolutions with differentiable kernel sizes. In: Preprint at arXiv:2110.08059 (2021)"},{"issue":"1","key":"3508_CR48","first-page":"8673","volume":"23","author":"L Bungert","year":"2022","unstructured":"Bungert, L., et al.: A Bregman learning framework for sparse neural networks. J. Mach. Learn. Res. 23(1), 8673\u20138715 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"3508_CR49","unstructured":"Schuler, J.P.S., et al.: Grouped pointwise convolutions reduce parameters in convolutional neural networks. Mendel (2022)"},{"key":"3508_CR50","doi-asserted-by":"crossref","unstructured":"Dwibedi, D., et al.: With a little help from my friends: nearest-neighbor contrastive learning of visual representations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"3508_CR51","first-page":"20717","volume":"35","author":"M Xiao","year":"2022","unstructured":"Xiao, M., et al.: Online training through time for spiking neural networks. Adv. Neural Inf. Process. Syst. 35, 20717\u201320730 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3508_CR52","unstructured":"Jeevan, P.: Convolutional xformers for vision. Preprint at arXiv:2201.10271 (2022)"},{"key":"3508_CR53","first-page":"16410","volume":"34","author":"C Zhu","year":"2021","unstructured":"Zhu, C., et al.: Gradinit: learning to initialize neural networks for stable and efficient training. Adva. Neural Inf. Process. Syst. 34, 16410\u201316422 (2021)","journal-title":"Adva. Neural Inf. Process. Syst."},{"key":"3508_CR54","doi-asserted-by":"crossref","unstructured":"Gavrikov, P., Keuper, J.: CNN filter DB: an empirical investigation of trained convolutional filters. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01848"},{"key":"3508_CR55","doi-asserted-by":"crossref","unstructured":"Schwarz Schuler, J.P., et al.: An enhanced scheme for reducing the complexity of pointwise convolutions in CNNs for image classification based on interleaved grouped filters without divisibility constraints. Entropy 24(9), 1264 (2022)","DOI":"10.3390\/e24091264"},{"key":"3508_CR56","doi-asserted-by":"crossref","unstructured":"Yao, D., et al.: Context-aware compilation of DNN training pipelines across edge and cloud. In: Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 5, no. 4, pp. 1\u201327 (2021)","DOI":"10.1145\/3494981"},{"key":"3508_CR57","unstructured":"Sander, M.E., et al.: Momentum residual neural networks. In: International Conference on Machine Learning. PMLR (2021)"},{"key":"3508_CR58","unstructured":"Hassani, A., et al.: Escaping the big data paradigm with compact transformers. Preprint at arXiv:2104.05704 (2021)"},{"key":"3508_CR59","first-page":"25404","volume":"35","author":"T Moreau","year":"2022","unstructured":"Moreau, T., et al.: Benchopt: reproducible, efficient and collaborative optimization benchmarks. Adv. Neural Inf. Process. Syst. 35, 25404\u201325421 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3508_CR60","doi-asserted-by":"crossref","unstructured":"Chrysos, G.G., et al.: Augmenting deep classifiers with polynomial neural networks. In: European Conference on Computer Vision. Springer (2022)","DOI":"10.1007\/978-3-031-19806-9_40"},{"key":"3508_CR61","doi-asserted-by":"crossref","unstructured":"Kabir, H.D., et al.: SpinalNet: deep neural network with gradual input. IEEE Trans. Artif. Intell. (2022)","DOI":"10.1109\/TAI.2022.3185179"},{"key":"3508_CR62","doi-asserted-by":"crossref","unstructured":"Samad, S.A., Gitanjali, J.: SCMA: exploring dual-module attention with multi-scale kernels for effective feature extraction. IEEE Access (2023)","DOI":"10.1109\/ACCESS.2023.3329581"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03508-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03508-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03508-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T18:46:15Z","timestamp":1732214775000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03508-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,13]]},"references-count":62,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["3508"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03508-x","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,13]]},"assertion":[{"value":"18 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2024","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}