{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T14:30:20Z","timestamp":1724077820109},"reference-count":76,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100006469","name":"Fund for the Development of Science and Technology","doi-asserted-by":"publisher","award":["0004\/2023\/ITP1"],"id":[{"id":"10.13039\/501100006469","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1016\/j.neucom.2024.127988","type":"journal-article","created":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T00:55:17Z","timestamp":1717462517000},"page":"127988","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Attention-Based Multi-Kernelized and Boundary-Aware Network for image semantic segmentation"],"prefix":"10.1016","volume":"597","author":[{"given":"Xuanchen","family":"Zhou","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-3201-002X","authenticated-orcid":false,"given":"Gengshen","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1870-9037","authenticated-orcid":false,"given":"Xin","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Pengpeng","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2024.127988_b1","doi-asserted-by":"crossref","unstructured":"Qibin Hou, Daquan Zhou, Jiashi Feng, Coordinate attention for efficient mobile network design, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 13713\u201313722.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"10.1016\/j.neucom.2024.127988_b2","doi-asserted-by":"crossref","unstructured":"Jie Hu, Li Shen, Gang Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10.1016\/j.neucom.2024.127988_b3","doi-asserted-by":"crossref","DOI":"10.1007\/s11042-024-18275-z","article-title":"Dual enhanced semantic hashing for fast image retrieval","author":"Fang","year":"2024","journal-title":"Multimedia Tools Appl."},{"key":"10.1016\/j.neucom.2024.127988_b4","doi-asserted-by":"crossref","unstructured":"Zilong Huang, Xinggang Wang, Lichao Huang, Chang Huang, Yunchao Wei, Wenyu Liu, Ccnet: Criss-cross attention for semantic segmentation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 603\u2013612.","DOI":"10.1109\/ICCV.2019.00069"},{"key":"10.1016\/j.neucom.2024.127988_b5","first-page":"10353","article-title":"Hornet: Efficient high-order spatial interactions with recursive gated convolutions","volume":"35","author":"Rao","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2024.127988_b6","unstructured":"Xiang Li, Wenhai Wang, Xiaolin Hu, Jian Yang, Selective kernel networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 510\u2013519."},{"key":"10.1016\/j.neucom.2024.127988_b7","doi-asserted-by":"crossref","unstructured":"Xia Li, Zhisheng Zhong, Jianlong Wu, Yibo Yang, Zhouchen Lin, Hong Liu, Expectation-maximization attention networks for semantic segmentation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 9167\u20139176.","DOI":"10.1109\/ICCV.2019.00926"},{"key":"10.1016\/j.neucom.2024.127988_b8","doi-asserted-by":"crossref","first-page":"95","DOI":"10.3389\/fnins.2019.00095","article-title":"Going deeper in spiking neural networks: VGG and residual architectures","volume":"13","author":"Sengupta","year":"2019","journal-title":"Front. Neurosci."},{"key":"10.1016\/j.neucom.2024.127988_b9","unstructured":"Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1r, Ross Girshick, Mask r-cnn, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2961\u20132969."},{"key":"10.1016\/j.neucom.2024.127988_b10","unstructured":"Saining Xie, Ross Girshick, Piotr Doll\u00e1r, Zhuowen Tu, Kaiming He, Aggregated residual transformations for deep neural networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1492\u20131500."},{"key":"10.1016\/j.neucom.2024.127988_b11","unstructured":"Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie, A convnet for the 2020s, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11976\u201311986."},{"key":"10.1016\/j.neucom.2024.127988_b12","unstructured":"Sanghyun Woo, Shoubhik Debnath, Ronghang Hu, Xinlei Chen, Zhuang Liu, In So Kweon, Saining Xie, Convnext v2: Co-designing and scaling convnets with masked autoencoders, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 16133\u201316142."},{"issue":"4","key":"10.1016\/j.neucom.2024.127988_b13","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1007\/s41095-023-0364-2","article-title":"Visual attention network","volume":"9","author":"Guo","year":"2023","journal-title":"Comput. Vis. Media"},{"key":"10.1016\/j.neucom.2024.127988_b14","first-page":"15908","article-title":"Transformer in transformer","volume":"34","author":"Han","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2024.127988_b15","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neucom.2024.127988_b16","doi-asserted-by":"crossref","unstructured":"Xiaolong Wang, Ross Girshick, Abhinav Gupta, Kaiming He, Non-local neural networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7794\u20137803.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"10.1016\/j.neucom.2024.127988_b17","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.neucom.2024.127988_b18","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2024.127988_b19","doi-asserted-by":"crossref","unstructured":"Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, Baining Guo, Swin transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.neucom.2024.127988_b20","first-page":"7281","article-title":"Hrformer: High-resolution vision transformer for dense predict","volume":"34","author":"Yuan","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2024.127988_b21","series-title":"International Conference on Machine Learning","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"key":"10.1016\/j.neucom.2024.127988_b22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.isprsjprs.2023.02.007","article-title":"Nationwide urban tree canopy mapping and coverage assessment in Brazil from high-resolution remote sensing images using deep learning","volume":"198","author":"Guo","year":"2023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.neucom.2024.127988_b23","series-title":"Conv2former: A simple transformer-style convnet for visual recognition","author":"Hou","year":"2022"},{"key":"10.1016\/j.neucom.2024.127988_b24","article-title":"Metaformer baselines for vision","author":"Yu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2024.127988_b25","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2023.1280831","article-title":"Deep facial attribute analysis","volume":"17","author":"Kong","year":"2023","journal-title":"Front. Neurosci."},{"key":"10.1016\/j.neucom.2024.127988_b26","article-title":"TCGNet: Type-correlation guidance for salient object detection","author":"Liu","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2024.127988_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126916","article-title":"Deep unsupervised part-whole relational visual saliency","volume":"563","author":"Liu","year":"2024","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.neucom.2024.127988_b28","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1109\/TGRS.2020.2991398","article-title":"CDnetV2: CNN-based cloud detection for remote sensing imagery with cloud-snow coexistence","volume":"59","author":"Guo","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2024.127988_b29","first-page":"1140","article-title":"Segnext: Rethinking convolutional attention design for semantic segmentation","volume":"35","author":"Guo","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2024.127988_b30","unstructured":"Jiacong Xu, Zixiang Xiong, Shankar P. Bhattacharyya, PIDNet: A Real-Time Semantic Segmentation Network Inspired by PID Controllers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19529\u201319539."},{"issue":"5","key":"10.1016\/j.neucom.2024.127988_b31","doi-asserted-by":"crossref","first-page":"3248","DOI":"10.1109\/TII.2021.3107785","article-title":"Synthetic to realistic imbalanced domain adaption for urban scene perception","volume":"18","author":"Hua","year":"2021","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.neucom.2024.127988_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127488","article-title":"Coordinate-aware mask R-CNN with group normalization: A underwater marine animal instance segmentation framework","volume":"583","author":"Yi","year":"2024","journal-title":"Neurocomputing"},{"issue":"7","key":"10.1016\/j.neucom.2024.127988_b33","first-page":"3688","article-title":"Part-object relational visual saliency","volume":"44","author":"Liu","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2024.127988_b34","article-title":"Virtual category learning: A semi-supervised learning method for dense prediction with extremely limited labels","author":"Chen","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2024.127988_b35","article-title":"Region-object relation-aware dense captioning via transformer","author":"Shao","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2024.127988_b36","doi-asserted-by":"crossref","unstructured":"Hang Zhang, Chongruo Wu, Zhongyue Zhang, Yi Zhu, Haibin Lin, Zhi Zhang, Yue Sun, Tong He, Jonas Mueller, R Manmatha, et al., Resnest: Split-attention networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 2736\u20132746.","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"10.1016\/j.neucom.2024.127988_b37","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov, Yuxin Wu, Kaiming He, Ross Girshick, Pointrend: Image segmentation as rendering, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9799\u20139808.","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"10.1016\/j.neucom.2024.127988_b38","doi-asserted-by":"crossref","first-page":"7200","DOI":"10.1109\/TIP.2021.3102509","article-title":"Mgseg: Multiple granularity-based real-time semantic segmentation network","volume":"30","author":"He","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neucom.2024.127988_b39","doi-asserted-by":"crossref","first-page":"6649","DOI":"10.1109\/TIP.2022.3214332","article-title":"Salient object detection via dynamic scale routing","volume":"31","author":"Wu","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neucom.2024.127988_b40","series-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"10.1016\/j.neucom.2024.127988_b41","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16","first-page":"660","article-title":"Boundary-preserving mask r-cnn","author":"Cheng","year":"2020"},{"key":"10.1016\/j.neucom.2024.127988_b42","unstructured":"Chenming Zhu, Xuanye Zhang, Yanran Li, Liangdong Qiu, Kai Han, Xiaoguang Han, SharpContour: A contour-based boundary refinement approach for efficient and accurate instance segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4392\u20134401."},{"key":"10.1016\/j.neucom.2024.127988_b43","doi-asserted-by":"crossref","unstructured":"Tao Zhang, Shiqing Wei, Shunping Ji, E2ec: An end-to-end contour-based method for high-quality high-speed instance segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4443\u20134452.","DOI":"10.1109\/CVPR52688.2022.00440"},{"key":"10.1016\/j.neucom.2024.127988_b44","series-title":"Focal self-attention for local-global interactions in vision transformers","author":"Yang","year":"2021"},{"key":"10.1016\/j.neucom.2024.127988_b45","series-title":"Inceptionnext: When inception meets convnext","author":"Yu","year":"2023"},{"key":"10.1016\/j.neucom.2024.127988_b46","doi-asserted-by":"crossref","unstructured":"Xiaohan Ding, Xiangyu Zhang, Jungong Han, Guiguang Ding, 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, 2022, pp. 11963\u201311975.","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"10.1016\/j.neucom.2024.127988_b47","doi-asserted-by":"crossref","unstructured":"Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, Hartwig Adam, Encoder-decoder with atrous separable convolution for semantic image segmentation, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 801\u2013818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"10.1016\/j.neucom.2024.127988_b48","article-title":"Capsule networks with residual pose routing","author":"Liu","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2024.127988_b49","article-title":"DCMSTRD: End-to-end dense captioning via multi-scale transformer decoding","author":"Shao","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2024.127988_b50","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778."},{"key":"10.1016\/j.neucom.2024.127988_b51","unstructured":"Dongchen Han, Xuran Pan, Yizeng Han, Shiji Song, Gao Huang, Flatten transformer: Vision transformer using focused linear attention, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 5961\u20135971."},{"key":"10.1016\/j.neucom.2024.127988_b52","series-title":"Attention u-net: Learning where to look for the pancreas","author":"Oktay","year":"2018"},{"key":"10.1016\/j.neucom.2024.127988_b53","doi-asserted-by":"crossref","unstructured":"Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang, Hanqing Lu, Dual attention network for scene segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 3146\u20133154.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"10.1016\/j.neucom.2024.127988_b54","first-page":"2280","article-title":"Fully attentional network for semantic segmentation","volume":"vol. 36","author":"Song","year":"2022"},{"key":"10.1016\/j.neucom.2024.127988_b55","doi-asserted-by":"crossref","unstructured":"Towaki Takikawa, David Acuna, Varun Jampani, Sanja Fidler, Gated-scnn: Gated shape cnns for semantic segmentation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 5229\u20135238.","DOI":"10.1109\/ICCV.2019.00533"},{"key":"10.1016\/j.neucom.2024.127988_b56","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.neucom.2023.03.003","article-title":"Where to look: Multi-granularity occlusion aware for video person re-identification","volume":"536","author":"Leng","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2024.127988_b57","unstructured":"Tsung-Yi Lin, Piotr Doll\u00e1r, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie, Feature pyramid networks for object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2117\u20132125."},{"key":"10.1016\/j.neucom.2024.127988_b58","series-title":"Deep dual-resolution networks for real-time and accurate semantic segmentation of road scenes","author":"Hong","year":"2021"},{"key":"10.1016\/j.neucom.2024.127988_b59","unstructured":"Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia, Pyramid scene parsing network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2881\u20132890."},{"issue":"3","key":"10.1016\/j.neucom.2024.127988_b60","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1016\/S0031-3203(00)00023-6","article-title":"On the canny edge detector","volume":"34","author":"Ding","year":"2001","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2024.127988_b61","first-page":"67","article-title":"An improved sobel edge detection","volume":"vol. 5","author":"Gao","year":"2010"},{"key":"10.1016\/j.neucom.2024.127988_b62","doi-asserted-by":"crossref","unstructured":"Bolei Zhou, Hang Zhao, Xavier Puig, Sanja Fidler, Adela Barriuso, Antonio Torralba, Scene parsing through ade20k dataset, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 633\u2013641.","DOI":"10.1109\/CVPR.2017.544"},{"key":"10.1016\/j.neucom.2024.127988_b63","doi-asserted-by":"crossref","unstructured":"Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, Bernt Schiele, The cityscapes dataset for semantic urban scene understanding, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 3213\u20133223.","DOI":"10.1109\/CVPR.2016.350"},{"key":"10.1016\/j.neucom.2024.127988_b64","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neucom.2024.127988_b65","doi-asserted-by":"crossref","unstructured":"Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, Jian Sun, Unified perceptual parsing for scene understanding, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 418\u2013434.","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"10.1016\/j.neucom.2024.127988_b66","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2024.127988_b67","doi-asserted-by":"crossref","unstructured":"Bowen Cheng, Ishan Misra, Alexander G Schwing, Alexander Kirillov, Rohit Girdhar, Masked-attention mask transformer for universal image segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 1290\u20131299.","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"10.1016\/j.neucom.2024.127988_b68","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VI 16","first-page":"173","article-title":"Object-contextual representations for semantic segmentation","author":"Yuan","year":"2020"},{"key":"10.1016\/j.neucom.2024.127988_b69","series-title":"Ddp: Diffusion model for dense visual prediction","author":"Ji","year":"2023"},{"key":"10.1016\/j.neucom.2024.127988_b70","series-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"10.1016\/j.neucom.2024.127988_b71","doi-asserted-by":"crossref","unstructured":"Robin Strudel, Ricardo Garcia, Ivan Laptev, Cordelia Schmid, Segmenter: Transformer for semantic segmentation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 7262\u20137272.","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"10.1016\/j.neucom.2024.127988_b72","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"issue":"10","key":"10.1016\/j.neucom.2024.127988_b73","doi-asserted-by":"crossref","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","article-title":"Deep high-resolution representation learning for visual recognition","volume":"43","author":"Wang","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2024.127988_b74","series-title":"Vision transformers with patch diversification","author":"Gong","year":"2021"},{"key":"10.1016\/j.neucom.2024.127988_b75","series-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"2235","article-title":"Sa-net: Shuffle attention for deep convolutional neural networks","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neucom.2024.127988_b76","doi-asserted-by":"crossref","unstructured":"Sanghyun Woo, Jongchan Park, Joon-Young Lee, In So Kweon, Cbam: Convolutional block attention module, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 3\u201319.","DOI":"10.1007\/978-3-030-01234-2_1"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231224007598?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231224007598?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,7,27]],"date-time":"2024-07-27T01:41:43Z","timestamp":1722044503000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231224007598"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":76,"alternative-id":["S0925231224007598"],"URL":"http:\/\/dx.doi.org\/10.1016\/j.neucom.2024.127988","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2024,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Attention-Based Multi-Kernelized and Boundary-Aware Network for image semantic segmentation","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2024.127988","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"127988"}}
