{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T17:40:48Z","timestamp":1792172448435,"version":"4.4.0"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Province Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1016\/j.neunet.2024.106568","type":"journal-article","created":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T16:20:48Z","timestamp":1721751648000},"page":"106568","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":17,"special_numbering":"C","title":["HDConv: Heterogeneous kernel-based dilated convolutions"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5863-8283","authenticated-orcid":false,"given":"Haigen","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenghan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianwei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiu","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hailin","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2024.106568_b1","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., & Ferrari, V. (2018). COCO-Stuff: Thing and Stuff Classes in Context. In 2018 IEEE\/CVF conference on computer vision and pattern recognition (pp. 1209\u20131218).","DOI":"10.1109\/CVPR.2018.00132"},{"key":"10.1016\/j.neunet.2024.106568_b2","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., & Hu, H. (2020). GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond. In 2019 IEEE\/CVF international conference on computer vision workshop (pp. 1971\u20131980).","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"10.1016\/j.neunet.2024.106568_b3","series-title":"Scaling up kernels in 3D CNNs","author":"Chen","year":"2022"},{"issue":"4","key":"10.1016\/j.neunet.2024.106568_b4","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2024.106568_b5","doi-asserted-by":"crossref","unstructured":"Chen, Q., Wang, Y., Yang, T., Zhang, X., Cheng, J., & Sun, J. (2021). You Only Look One-level Feature. In IEEE conference on computer vision and pattern recognition (pp. 13039\u201313048).","DOI":"10.1109\/CVPR46437.2021.01284"},{"key":"10.1016\/j.neunet.2024.106568_b6","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-Decoder 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":"10.1016\/j.neunet.2024.106568_b7","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 Proc. of the IEEE conference on computer vision and pattern recognition (pp. 3213\u20133223).","DOI":"10.1109\/CVPR.2016.350"},{"key":"10.1016\/j.neunet.2024.106568_b8","doi-asserted-by":"crossref","unstructured":"Ding, X., Guo, Y., Ding, G., & Han, J. (2019). ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 1911\u20131920).","DOI":"10.1109\/ICCV.2019.00200"},{"key":"10.1016\/j.neunet.2024.106568_b9","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Han, J., & Ding, G. (2022). Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 11963\u201311975).","DOI":"10.1109\/CVPR52688.2022.01166"},{"issue":"1","key":"10.1016\/j.neunet.2024.106568_b10","doi-asserted-by":"crossref","first-page":"138","DOI":"10.3758\/s13414-021-02388-w","article-title":"Increasing pupil size is associated with improved detection performance in the periphery","volume":"84","author":"Eberhardt","year":"2022","journal-title":"Atten Percept Psychophys"},{"issue":"10","key":"10.1016\/j.neunet.2024.106568_b11","doi-asserted-by":"crossref","first-page":"2281","DOI":"10.1109\/TMI.2019.2903562","article-title":"CE-Net: Context encoder network for 2D medical image segmentation","volume":"38","author":"Gu","year":"2019","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.neunet.2024.106568_b12","first-page":"1140","article-title":"SegNeXt: Rethinking convolutional attention design for semantic segmentation","author":"Guo","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.1016\/j.neunet.2024.106568_b13","doi-asserted-by":"crossref","unstructured":"Hamaguchi, R., Fujita, A., Nemoto, K., Imaizumi, T., & Hikosaka, S. (2018). Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery. In 2018 IEEE winter conference on applications of computer vision (pp. 1442\u20131450).","DOI":"10.1109\/WACV.2018.00162"},{"key":"10.1016\/j.neunet.2024.106568_b14","doi-asserted-by":"crossref","unstructured":"He, J., Deng, Z., Zhou, L., Wang, Y., & Qiao, Y. (2019). Adaptive Pyramid Context Network for Semantic Segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7519\u20137528).","DOI":"10.1109\/CVPR.2019.00770"},{"key":"10.1016\/j.neunet.2024.106568_b15","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"},{"issue":"9","key":"10.1016\/j.neunet.2024.106568_b16","doi-asserted-by":"crossref","first-page":"6096","DOI":"10.1109\/TNNLS.2021.3133263","article-title":"Adaptively customizing activation functions for various layers","volume":"34","author":"Hu","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2024.106568_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108452","article-title":"Deep co-supervision and attention fusion strategy for automatic COVID-19 lung infection segmentation on CT images","volume":"124","author":"Hu","year":"2022","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2024.106568_b18","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., & Liu, W. (2019). CCNet: Criss-Cross Attention for Semantic Segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 603\u2013612).","DOI":"10.1109\/ICCV.2019.00069"},{"issue":"8","key":"10.1016\/j.neunet.2024.106568_b19","doi-asserted-by":"crossref","first-page":"5485","DOI":"10.1109\/TII.2020.3033170","article-title":"HDCB-net: A neural network with the hybrid dilated convolution for pixel-level crack detection on concrete bridges","volume":"17","author":"Jiang","year":"2021","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.neunet.2024.106568_b20","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.106568_b21","doi-asserted-by":"crossref","unstructured":"Li, X., Zhong, Z., Wu, J., Yang, Y., Lin, Z., & Liu, H. (2019). Expectation-Maximization Attention Networks for Semantic Segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9167\u20139176).","DOI":"10.1109\/ICCV.2019.00926"},{"key":"10.1016\/j.neunet.2024.106568_b22","series-title":"ECCV","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neunet.2024.106568_b23","series-title":"More ConvNets in the 2020s: Scaling up kernels beyond 51x51 using sparsity","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2024.106568_b24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022). A ConvNet for the 2020s. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 11976\u201311986).","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"10.1016\/j.neunet.2024.106568_b25","doi-asserted-by":"crossref","unstructured":"Mehta, S., Rastegari, M., Caspi, A., Shapiro, L., & Hajishirzi, H. (2018). ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation. In Proceedings of the European conference on computer vision (pp. 552\u2013568).","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"10.1016\/j.neunet.2024.106568_b26","first-page":"10353","article-title":"HorNet: Efficient high-order spatial interactions with recursive gated convolutions","author":"Rao","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.1016\/j.neunet.2024.106568_b27","series-title":"Advances in neural information processing systems","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"Vol. 28","author":"Ren","year":"2015"},{"key":"10.1016\/j.neunet.2024.106568_b28","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. In 3rd international conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, conference track proceedings."},{"key":"10.1016\/j.neunet.2024.106568_b29","doi-asserted-by":"crossref","unstructured":"Singh, P., Verma, V. K., Rai, P., & Namboodiri, V. P. (2019). HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4835\u20134844).","DOI":"10.1109\/CVPR.2019.00497"},{"key":"10.1016\/j.neunet.2024.106568_b30","doi-asserted-by":"crossref","unstructured":"Son, H., Lee, J., Cho, S., & Lee, S. (2021). Single Image Defocus Deblurring Using Kernel-Sharing Parallel Atrous Convolutions. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 2642\u20132650).","DOI":"10.1109\/ICCV48922.2021.00264"},{"issue":"8","key":"10.1016\/j.neunet.2024.106568_b31","doi-asserted-by":"crossref","first-page":"3159","DOI":"10.1111\/cogs.12684","article-title":"Gaze and the eye pupil adjust to imagined size and distance","volume":"42","author":"Sulutvedt","year":"2018","journal-title":"Cognitive Science"},{"key":"10.1016\/j.neunet.2024.106568_b32","series-title":"High-resolution representations for labeling pixels and regions","author":"Sun","year":"2019"},{"key":"10.1016\/j.neunet.2024.106568_b33","doi-asserted-by":"crossref","unstructured":"Takahashi, N., & Mitsufuji, Y. (2021). Densely Connected Multi-Dilated Convolutional Networks for Dense Prediction Tasks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 993\u20131002).","DOI":"10.1109\/CVPR46437.2021.00105"},{"key":"10.1016\/j.neunet.2024.106568_b34","doi-asserted-by":"crossref","unstructured":"Wang, P., Chen, P., Yuan, Y., Liu, D., Huang, Z., Hou, X., & Cottrell, G. (2018). Understanding Convolution for Semantic Segmentation. In 2018 IEEE winter conference on applications of computer vision (pp. 1451\u20131460).","DOI":"10.1109\/WACV.2018.00163"},{"key":"10.1016\/j.neunet.2024.106568_b35","doi-asserted-by":"crossref","unstructured":"Wang, Z., & Ji, S. (2018). Smoothed Dilated Convolutions for Improved Dense Prediction. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 2486\u20132495).","DOI":"10.1145\/3219819.3219944"},{"issue":"8","key":"10.1016\/j.neunet.2024.106568_b36","doi-asserted-by":"crossref","first-page":"2653","DOI":"10.1109\/TMI.2020.3000314","article-title":"A noise-robust framework for automatic segmentation of COVID-19 pneumonia lesions from CT images","volume":"39","author":"Wang","year":"2020","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.neunet.2024.106568_b37","doi-asserted-by":"crossref","unstructured":"Wei, J., Wang, S., & Huang, Q. (2020). F3Net: Fusion, Feedback and Focus for Salient Object Detection. In AAAI conference on artificial intelligence (pp. 12321\u201312328).","DOI":"10.1609\/aaai.v34i07.6916"},{"key":"10.1016\/j.neunet.2024.106568_b38","doi-asserted-by":"crossref","unstructured":"Wu, Z., Su, L., & Huang, Q. (2019). Stacked Cross Refinement Network for Edge-Aware Salient Object Detection. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 7264\u20137273).","DOI":"10.1109\/ICCV.2019.00736"},{"key":"10.1016\/j.neunet.2024.106568_b39","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., & Sun, J. (2018). Unified Perceptual Parsing for Scene Understanding. In Proceedings of the European conference on computer vision (pp. 770\u2013778).","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"10.1016\/j.neunet.2024.106568_b40","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1492\u20131500).","DOI":"10.1109\/CVPR.2017.634"},{"key":"10.1016\/j.neunet.2024.106568_b41","unstructured":"Yu, F., & Koltun, V. (2016). Multi-Scale Context Aggregation by Dilated Convolutions. In 4th international conference on learning representations, ICLR 2016,san juan, puerto rico, May 2-4, 2016, conference track proceedings."},{"key":"10.1016\/j.neunet.2024.106568_b42","doi-asserted-by":"crossref","unstructured":"Yu, F., Koltun, V., & Funkhouser, T. (2017). Dilated Residual Networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 472\u2013480).","DOI":"10.1109\/CVPR.2017.75"},{"key":"10.1016\/j.neunet.2024.106568_b43","doi-asserted-by":"crossref","unstructured":"Zhang, F., Chen, Y., Li, Z., Hong, Z., Liu, J., Ma, F., Han, J., & Ding, E. (2019). ACFNet: Attentional Class Feature Network for Semantic Segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 6798\u20136807).","DOI":"10.1109\/ICCV.2019.00690"},{"key":"10.1016\/j.neunet.2024.106568_b44","doi-asserted-by":"crossref","unstructured":"Zhang, H., Dana, K., Shi, J., Zhang, Z., Wang, X., Tyagi, A., & Agrawal, A. (2018). Context Encoding for Semantic Segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7151\u20137160).","DOI":"10.1109\/CVPR.2018.00747"},{"key":"10.1016\/j.neunet.2024.106568_b45","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid Scene Parsing Network. In 2017 IEEE conference on computer vision and pattern recognition (pp. 6230\u20136239).","DOI":"10.1109\/CVPR.2017.660"},{"key":"10.1016\/j.neunet.2024.106568_b46","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017). Scene Parsing Through ADE20K Dataset. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 633\u2013641).","DOI":"10.1109\/CVPR.2017.544"},{"key":"10.1016\/j.neunet.2024.106568_b47","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Xu, M., Bai, S., Huang, T., & Bai, X. (2019). Asymmetric Non-Local Neural Networks for Semantic Segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 593\u2013602).","DOI":"10.1109\/ICCV.2019.00068"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608024004921?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608024004921?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,9,14]],"date-time":"2024-09-14T16:28:53Z","timestamp":1726331333000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608024004921"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":47,"alternative-id":["S0893608024004921"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2024.106568","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2024,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"HDConv: Heterogeneous kernel-based dilated convolutions","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2024.106568","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106568"}}