{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T11:20:32Z","timestamp":1720437632787},"reference-count":61,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Signal Processing: Image Communication"],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1016\/j.image.2021.116458","type":"journal-article","created":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T23:52:23Z","timestamp":1630367543000},"page":"116458","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":6,"special_numbering":"C","title":["S2-aware network for visual recognition"],"prefix":"10.1016","volume":"99","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-8339-5081","authenticated-orcid":false,"given":"Wenyi","family":"Zhao","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-6334-4044","authenticated-orcid":false,"given":"Huihua","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Xipeng","family":"Pan","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-9402-0421","authenticated-orcid":false,"given":"Lingqiao","family":"Li","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.image.2021.116458_b1","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"6054","article-title":"Scale-aware trident networks for object detection","author":"Li","year":"2019"},{"key":"10.1016\/j.image.2021.116458_b2","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1092","article-title":"SmallBigNet: Integrating core and contextual views for video classification","author":"Li","year":"2020"},{"key":"10.1016\/j.image.2021.116458_b3","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5012","article-title":"Looking for the devil in the details: Learning trilinear attention sampling network for fine-grained image recognition","author":"Zheng","year":"2019"},{"key":"10.1016\/j.image.2021.116458_b4","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4438","article-title":"Look closer to see better: Recurrent attention convolutional neural network for fine-grained image recognition","author":"Fu","year":"2017"},{"key":"10.1016\/j.image.2021.116458_b5","first-page":"9310","article-title":"Sniper: Efficient multi-scale training","volume":"31","author":"Singh","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"4","key":"10.1016\/j.image.2021.116458_b6","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":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2021.116458_b7","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"10.1016\/j.image.2021.116458_b8","doi-asserted-by":"crossref","unstructured":"C. Peng, X. Zhang, G. Yu, G. Luo, J. Sun, Large kernel matters\u2013improve semantic segmentation by global convolutional network, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 4353-4361.","DOI":"10.1109\/CVPR.2017.189"},{"key":"10.1016\/j.image.2021.116458_b9","series-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.image.2021.116458_b10","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10781","article-title":"Efficientdet: Scalable and efficient object detection","author":"Tan","year":"2020"},{"key":"10.1016\/j.image.2021.116458_b11","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3156","article-title":"Residual attention network for image classification","author":"Wang","year":"2017"},{"key":"10.1016\/j.image.2021.116458_b12","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.image.2021.116458_b13","series-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.image.2021.116458_b14","series-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"issue":"1","key":"10.1016\/j.image.2021.116458_b15","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/JBHI.2019.2912659","article-title":"Deep residual inception encoder\u2013decoder network for medical imaging synthesis","volume":"24","author":"Gao","year":"2019","journal-title":"IEEE J. Biomed. Health Inf."},{"issue":"1","key":"10.1016\/j.image.2021.116458_b16","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/s00521-018-3627-6","article-title":"Improved inception-residual convolutional neural network for object recognition","volume":"32","author":"Alom","year":"2020","journal-title":"Neural Comput. Appl."},{"issue":"12","key":"10.1016\/j.image.2021.116458_b17","doi-asserted-by":"crossref","first-page":"3499","DOI":"10.1109\/TBME.2019.2906667","article-title":"Dilated-inception net: multi-scale feature aggregation for cardiac right ventricle segmentation","volume":"66","author":"Li","year":"2019","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"10.1016\/j.image.2021.116458_b18","article-title":"A dilated inception network for visual saliency prediction","author":"Yang","year":"2019","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.image.2021.116458_b19","series-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"key":"10.1016\/j.image.2021.116458_b20","series-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"Szegedy","year":"2016"},{"key":"10.1016\/j.image.2021.116458_b21","series-title":"Stable ResNet","author":"Hayou","year":"2020"},{"key":"10.1016\/j.image.2021.116458_b22","series-title":"Improved residual networks for image and video recognition","author":"Duta","year":"2020"},{"key":"10.1016\/j.image.2021.116458_b23","series-title":"On the impact of the activation function on deep neural networks training","author":"Hayou","year":"2019"},{"key":"10.1016\/j.image.2021.116458_b24","series-title":"Dropout as data augmentation","author":"Bouthillier","year":"2015"},{"key":"10.1016\/j.image.2021.116458_b25","series-title":"Dual path networks","author":"Chen","year":"2017"},{"key":"10.1016\/j.image.2021.116458_b26","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"718","article-title":"Polynet: A pursuit of structural diversity in very deep networks","author":"Zhang","year":"2017"},{"key":"10.1016\/j.image.2021.116458_b27","article-title":"Deep subdomain adaptation network for image classification","author":"Zhu","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.image.2021.116458_b28","series-title":"A survey of convolutional neural networks: Analysis, applications, and prospects","author":"Li","year":"2020"},{"key":"10.1016\/j.image.2021.116458_b29","article-title":"Automatic evaluation of facial nerve paralysis by dual-path LSTM with deep differentiated network","author":"Xu","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.image.2021.116458_b30","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"286","article-title":"Image super-resolution using very deep residual channel attention networks","author":"Zhang","year":"2018"},{"key":"10.1016\/j.image.2021.116458_b31","series-title":"Proceedings of the IEEE International Conference on Computer Vision Workshops","first-page":"3814","article-title":"Lightweight and accurate recursive fractal network for image super-resolution","author":"Li","year":"2019"},{"key":"10.1016\/j.image.2021.116458_b32","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"key":"10.1016\/j.image.2021.116458_b33","first-page":"4898","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume":"29","author":"Luo","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.image.2021.116458_b34","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1251","article-title":"Xception: Deep learning with depthwise separable convolutions","author":"Chollet","year":"2017"},{"key":"10.1016\/j.image.2021.116458_b35","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2021.3069237","article-title":"Learning generalisable omni-scale representations for person re-identification","author":"Zhou","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2021.116458_b36","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"10.1016\/j.image.2021.116458_b37","series-title":"Dynamic group convolution for accelerating convolutional neural networks","author":"Su","year":"2020"},{"key":"10.1016\/j.image.2021.116458_b38","series-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","year":"2015"},{"key":"10.1016\/j.image.2021.116458_b39","article-title":"Dense dilated convolutions\u2019 merging network for land cover classification","author":"Liu","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.image.2021.116458_b40","series-title":"Fastfcn: Rethinking dilated convolution in the backbone for semantic segmentation","author":"Wu","year":"2019"},{"key":"10.1016\/j.image.2021.116458_b41","article-title":"A survey of restoration and enhancement for underwater images","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.image.2021.116458_b42","series-title":"European Conference on Computer Vision","first-page":"354","article-title":"A unified multi-scale deep convolutional neural network for fast object detection","author":"Cai","year":"2016"},{"key":"10.1016\/j.image.2021.116458_b43","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"334","article-title":"Detnet: Design backbone for object detection","author":"Li","year":"2018"},{"key":"10.1016\/j.image.2021.116458_b44","series-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","author":"Han","year":"2018"},{"key":"10.1016\/j.image.2021.116458_b45","series-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"10.1016\/j.image.2021.116458_b46","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1580","article-title":"GhostNet: More features from cheap operations","author":"Han","year":"2020"},{"key":"10.1016\/j.image.2021.116458_b47","doi-asserted-by":"crossref","unstructured":"G.S. Xia, X. Bai, J. Ding, Z. Zhu, S. Belongie, J. Luo, . \u2026, L. Zhang, DOTA: A large-scale dataset for object detection in aerial images, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 3974-3983.","DOI":"10.1109\/CVPR.2018.00418"},{"key":"10.1016\/j.image.2021.116458_b48","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1016\/j.isprsjprs.2019.11.023","article-title":"Object detection in optical remote sensing images: A survey and a new benchmark","volume":"159","author":"Li","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.image.2021.116458_b49","unstructured":"X. Glorot, A. Bordes, Y. Bengio, Deep sparse rectifier neural networks, in: Proceedings of the fourteenth international conference on artificial intelligence and statistics, 2011, June, pp. 315-323."},{"key":"10.1016\/j.image.2021.116458_b50","series-title":"18th International Conference on Enterprise Information Systems (ICEIS)","first-page":"273","article-title":"ApPoggiomarino: A context aware app for E-citizenship","author":"Annunziata","year":"2016"},{"key":"10.1016\/j.image.2021.116458_b51","doi-asserted-by":"crossref","unstructured":"L.C. Chen, Y. Zhu, G. Papandreou, F. Schroff, H. Adam, Encoder\u2013decoder with atrous separable convolution for semantic image segmentationm, in: Proceedings of the European conference on computer vision (ECCV), 2018, pp. 801-818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"10.1016\/j.image.2021.116458_b52","unstructured":"Receptive field block net for accurate and fast object detection, in: Proceedings of the European Conference on Computer Vision (ECCV), 0000, pp. 385-400."},{"key":"10.1016\/j.image.2021.116458_b53","article-title":"Res2net: A new multi-scale backbone architecture","author":"Gao","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2021.116458_b54","doi-asserted-by":"crossref","unstructured":"T. Shang, Q. Dai, S. Zhu, T. Yang, Y. Guo, Perceptual extreme super-resolution network with receptive field block, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020, pp. 440-441.","DOI":"10.1109\/CVPRW50498.2020.00228"},{"key":"10.1016\/j.image.2021.116458_b55","series-title":"2018 IEEE Winter Conference on Applications of Computer Vision (WACV)","first-page":"1451","article-title":"Understanding convolution for semantic segmentation","author":"Wang","year":"2018"},{"key":"10.1016\/j.image.2021.116458_b56","series-title":"The caltech-ucsd birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"10.1016\/j.image.2021.116458_b57","doi-asserted-by":"crossref","unstructured":"J. Krause, M. Stark, J. Deng, L. Fei-Fei, 3d object representations for fine-grained categorization, in: Proceedings of the IEEE international conference on computer vision workshops, 2013, pp. 554-561.","DOI":"10.1109\/ICCVW.2013.77"},{"key":"10.1016\/j.image.2021.116458_b58","series-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"10.1016\/j.image.2021.116458_b59","series-title":"European Conference on Computer Vision","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"He","year":"2016"},{"key":"10.1016\/j.image.2021.116458_b60","doi-asserted-by":"crossref","unstructured":"X. Wang, R. Girshick, A. Gupta, K. He, Non-local neural networks, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7794-7803.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"10.1016\/j.image.2021.116458_b61","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Signal Processing: Image Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0923596521002198?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0923596521002198?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T00:26:03Z","timestamp":1678062363000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0923596521002198"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11]]},"references-count":61,"alternative-id":["S0923596521002198"],"URL":"https:\/\/doi.org\/10.1016\/j.image.2021.116458","relation":{},"ISSN":["0923-5965"],"issn-type":[{"value":"0923-5965","type":"print"}],"subject":[],"published":{"date-parts":[[2021,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"S2-aware network for visual recognition","name":"articletitle","label":"Article Title"},{"value":"Signal Processing: Image Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.image.2021.116458","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"116458"}}