{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T17:17:31Z","timestamp":1763572651760,"version":"3.37.3"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T00:00:00Z","timestamp":1658361600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T00:00:00Z","timestamp":1658361600000},"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 Science Foundation of China","doi-asserted-by":"crossref","award":["61975124"],"award-info":[{"award-number":["61975124"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["20ZR1438500"],"award-info":[{"award-number":["20ZR1438500"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1007\/s11042-022-13447-1","type":"journal-article","created":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T12:03:47Z","timestamp":1658405027000},"page":"4063-4080","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["RISAT: real-time instance segmentation with adversarial training"],"prefix":"10.1007","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0810-1458","authenticated-orcid":false,"given":"Songwen","family":"Pei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Ni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianma","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenling","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yewang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meikang","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,21]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Al-Qizwini M, Barjasteh I, Al-Qassab H, Radha H (2017) Deep learning algorithm for autonomous driving using googlenet. In: 2017 IEEE intelligent vehicles symposium (IV). IEEE, pp 89\u201396","key":"13447_CR1","DOI":"10.1109\/IVS.2017.7995703"},{"doi-asserted-by":"crossref","unstructured":"Aqqa M, Shah S (2021) Car-dcgan: a deep convolutional generative adversarial network for compression artifact removal in video surveillance systems. In: 16th International conference on computer vision theory and applications","key":"13447_CR2","DOI":"10.5220\/0010312304550464"},{"issue":"4","key":"13447_CR3","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1007\/s40534-016-0117-3","volume":"24","author":"SA Bagloee","year":"2016","unstructured":"Bagloee S A, Tavana M, Asadi M, Oliver T (2016) Autonomous vehicles: challenges, opportunities, and future implications for transportation policies. J Modern Transp 24(4):284\u2013303","journal-title":"J Modern Transp"},{"doi-asserted-by":"crossref","unstructured":"Bolya D, Zhou C, Xiao F, Lee Y J (2019) Yolact: real-time instance segmentation. In: Proceedings of the IEEE international conference on computer vision, pp 9157\u20139166","key":"13447_CR4","DOI":"10.1109\/ICCV.2019.00925"},{"doi-asserted-by":"crossref","unstructured":"Chen L-C, Hermans A, Papandreou G, Schroff F, Wang P, Adam H (2018) Masklab: instance segmentation by refining object detection with semantic and direction features. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4013\u20134022","key":"13447_CR5","DOI":"10.1109\/CVPR.2018.00422"},{"unstructured":"Chen L-C, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587","key":"13447_CR6"},{"doi-asserted-by":"crossref","unstructured":"Dai J, He K, Sun J (2016) Instance-aware semantic segmentation via multi-task network cascades. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3150\u20133158","key":"13447_CR7","DOI":"10.1109\/CVPR.2016.343"},{"doi-asserted-by":"crossref","unstructured":"Feng D, Haase-Sch\u00fctz C, Rosenbaum L, Hertlein H, Glaeser C, Timm F, Wiesbeck W, Dietmayer K (2020) Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods, and challenges. IEEE Trans Intell Transp Syst","key":"13447_CR8","DOI":"10.1109\/TITS.2020.2972974"},{"unstructured":"Fu C-Y, Shvets M, Berg A C (2019) Retinamask: learning to predict masks improves state-of-the-art single-shot detection for free. arXiv:1901.03353","key":"13447_CR9"},{"doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 2961\u20132969","key":"13447_CR10","DOI":"10.1109\/ICCV.2017.322"},{"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","key":"13447_CR11","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"Hoermann S, Bach M, Dietmayer K (2018) Dynamic occupancy grid prediction for urban autonomous driving: a deep learning approach with fully automatic labeling. In: 2018 IEEE International conference on robotics and automation (ICRA). IEEE, pp 2056\u20132063","key":"13447_CR12","DOI":"10.1109\/ICRA.2018.8460874"},{"doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger K Q (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700\u20134708","key":"13447_CR13","DOI":"10.1109\/CVPR.2017.243"},{"doi-asserted-by":"crossref","unstructured":"Huang Z, Huang L, Gong Y, Huang C, Wang X (2019) Mask scoring r-cnn. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6409\u20136418","key":"13447_CR14","DOI":"10.1109\/CVPR.2019.00657"},{"issue":"3","key":"13447_CR15","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1109\/MCE.2019.2892286","volume":"8","author":"L Jian","year":"2019","unstructured":"Jian L, Li Z, Yang X, Wu W, Ahmad A, Jeon G (2019) Combining unmanned aerial vehicles with artificial-intelligence technology for traffic-congestion recognition: electronic eyes in the skies to spot clogged roads. IEEE Consum Electron Mag 8(3):81\u201386","journal-title":"IEEE Consum Electron Mag"},{"doi-asserted-by":"crossref","unstructured":"Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. arXiv:1603.08155","key":"13447_CR16","DOI":"10.1007\/978-3-319-46475-6_43"},{"doi-asserted-by":"crossref","unstructured":"Kawasaki A, Seki A (2021) Multimodal trajectory predictions for autonomous driving without a detailed prior map. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision (WACV), pp 3723\u20133732","key":"13447_CR17","DOI":"10.1109\/WACV48630.2021.00377"},{"doi-asserted-by":"crossref","unstructured":"Kim H, Choi Y, Kim J, Yoo S, Uh Y (2021) Stylemapgan: exploiting spatial dimensions of latent in gan for real-time image editing. arXiv:2104.14754","key":"13447_CR18","DOI":"10.1109\/CVPR46437.2021.00091"},{"doi-asserted-by":"crossref","unstructured":"Kirillov A, Levinkov E, Andres B, Savchynskyy B, Rother C (2017) Instancecut: from edges to instances with multicut. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5008\u20135017","key":"13447_CR19","DOI":"10.1109\/CVPR.2017.774"},{"issue":"3","key":"13447_CR20","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-008-0202-0","volume":"82","author":"P Kohli","year":"2009","unstructured":"Kohli P, Torr Philip HS, et al. (2009) Robust higher order potentials for enforcing label consistency. Int J Comput Vis 82(3):302\u2013324","journal-title":"Int J Comput Vis"},{"key":"13447_CR21","doi-asserted-by":"publisher","first-page":"11259","DOI":"10.1007\/s11042-022-11974-5","volume":"81","author":"S Koul","year":"2022","unstructured":"Koul S, Kumar M, Khurana S S, Mushtaq F, Kumar K (2022) An efficient approach for copy-move image forgery detection using convolution neural network. Multimed Tools Appl 81:11259\u201311277","journal-title":"Multimed Tools Appl"},{"unstructured":"Krizhevsky A, Sutskever I, Hinton G E (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105","key":"13447_CR22"},{"doi-asserted-by":"crossref","unstructured":"Lee Y, Park J (2020) Centermask: real-time anchor-free instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","key":"13447_CR23","DOI":"10.1109\/CVPR42600.2020.01392"},{"doi-asserted-by":"crossref","unstructured":"Li P, Chen X, Shen S (2019) Stereo r-cnn based 3d object detection for autonomous driving. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 7636\u20137644","key":"13447_CR24","DOI":"10.1109\/CVPR.2019.00783"},{"doi-asserted-by":"crossref","unstructured":"Li Y, Qi H, Dai J, Ji X, Wei Y (2017) Fully convolutional instance-aware semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2359\u20132367","key":"13447_CR25","DOI":"10.1109\/CVPR.2017.472"},{"doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick C L (2014) Microsoft coco: common objects in context. In: European conference on computer vision. Springer, pp 740\u2013755","key":"13447_CR26","DOI":"10.1007\/978-3-319-10602-1_48"},{"doi-asserted-by":"crossref","unstructured":"Liu R, Ge Y, Choi C, Wang X, Li H (2021) Divco: diverse conditional image synthesis via contrastive generative adversarial network. arXiv:2103.07893","key":"13447_CR27","DOI":"10.1109\/CVPR46437.2021.01611"},{"doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg A C (2016) Ssd: single shot multibox detector. In: European conference on computer vision. Springer, pp 21\u201337","key":"13447_CR28","DOI":"10.1007\/978-3-319-46448-0_2"},{"doi-asserted-by":"crossref","unstructured":"Liu Y, Zhang G, Zhang Y (2019) Vehicle detection method based on ade-yolov3 algorithm. In: 2019 4th International conference on intelligent informatics and biomedical sciences (ICIIBMS)","key":"13447_CR29","DOI":"10.1109\/ICIIBMS46890.2019.8991497"},{"unstructured":"Luc P, Couprie C, Chintala S, Verbeek J (2016) Semantic segmentation using adversarial networks. arXiv:1611.08408","key":"13447_CR30"},{"unstructured":"Miksys L, Jetley S, Sapienza M, Golodetz S, Torr P (2019) Straight to shapes++: real-time instance segmentation made more accurate. arXiv:1905.11358","key":"13447_CR31"},{"key":"13447_CR32","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.ins.2019.11.040","volume":"513","author":"S Pei","year":"2020","unstructured":"Pei S, Shen T, Wang X, Gu C, Ning Z, Ye X, Xiong N (2020) 3Dacn: 3D augmented convolutional network for time series data. Inf Sci 513:17\u201329","journal-title":"Inf Sci"},{"doi-asserted-by":"crossref","unstructured":"Pei S, Tang F, Ji Y, Fan J, Zhong N (2018) Localized traffic sign detection with multi-scale deconvolution networks. In: Proceedings of the IEEE conference on computer software and applications, pp 355\u2013360","key":"13447_CR33","DOI":"10.1109\/COMPSAC.2018.00056"},{"unstructured":"Pinheiro Pedro OO, Collobert R, Doll\u00e1r P (2015) Learning to segment object candidates. In: Advances in neural information processing systems, pp 1990\u20131998","key":"13447_CR34"},{"unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv:1804.02767","key":"13447_CR35"},{"unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91\u201399","key":"13447_CR36"},{"doi-asserted-by":"crossref","unstructured":"Richardson E, Alaluf Y, Patashnik O, Nitzan Y, Azar Y, Shapiro S, Cohen-Or D (2020) Encoding in style: a stylegan encoder for image-to-image translation. arXiv:2008.00951","key":"13447_CR37","DOI":"10.1109\/CVPR46437.2021.00232"},{"issue":"19","key":"13447_CR38","doi-asserted-by":"publisher","first-page":"70","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023","volume":"2017","author":"AhmadEL Sallab","year":"2017","unstructured":"Sallab Ahmad EL, Abdou M, Perot E, Yogamani S (2017) Deep reinforcement learning framework for autonomous driving. Electron Imaging 2017 (19):70\u201376","journal-title":"Electron Imaging"},{"doi-asserted-by":"crossref","unstructured":"Sarkar K, Liu L, Golyanik V, Theobalt C (2021) Humangan: a generative model of humans images. arXiv:2103.06902","key":"13447_CR39","DOI":"10.1109\/3DV53792.2021.00036"},{"key":"13447_CR40","doi-asserted-by":"publisher","first-page":"116288","DOI":"10.1016\/j.eswa.2021.116288","volume":"191","author":"K Shaheed","year":"2022","unstructured":"Shaheed K, Mao A, Qureshi I, Kumar M, Hussain S, Ullah I, Zhang X (2022) Ds-cnn: a pre-trained xception model based on depth-wise separable convolutional neural network for finger vein recognition. Expert Syst Appl 191:116288. https:\/\/doi.org\/10.1016\/j.eswa.2021.116288, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0957417421015943","journal-title":"Expert Syst Appl"},{"unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556","key":"13447_CR41"},{"doi-asserted-by":"crossref","unstructured":"Tan Z, Chai M, Chen D, Liao J, Chu Q, Liu B, Hua G, Yu N (2021) Diverse semantic image synthesis via probability distribution modeling. arXiv:2103.06878","key":"13447_CR42","DOI":"10.1109\/CVPR46437.2021.00787"},{"unstructured":"U\u0159ica\u0159 M, Sistu G, Rashed H, Vobeck\u00fd A, Kumar V, Kr\u00edzek P, Burger F, Yogamani S (2019) Let\u2019s get dirty: Gan based data augmentation for camera lens soiling detection in autonomous driving","key":"13447_CR43"},{"doi-asserted-by":"crossref","unstructured":"Xie E, Sun P, Song X, Wang W, Liu X, Liang D, Shen C, Luo P (2019) Polarmask: single shot instance segmentation with polar representation. arXiv:1909.13226","key":"13447_CR44","DOI":"10.1109\/CVPR42600.2020.01221"},{"unstructured":"Yao J, Yu Z, Yu J, Tao D (2020) Single pixel reconstruction for one-stage instance segmentation. IEEE Transactions on Cybernetics","key":"13447_CR45"},{"key":"13447_CR46","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1016\/j.neucom.2020.04.001","volume":"425","author":"N Zeng","year":"2021","unstructured":"Zeng N, Li H, Wang Z, Liu W, Liu S, Alsaadi F E, Liu X (2021) Deep-reinforcement-learning-based images segmentation for quantitative analysis of gold immunochromatographic strip. Neurocomputing 425:173\u2013180","journal-title":"Neurocomputing"},{"unstructured":"Zhou C, Wu M, Lam S (2019) Ssa-cnn: aemantic self-attention cnn for pedestrian detection. arXiv:1902.09080","key":"13447_CR47"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-13447-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-13447-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-13447-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T09:44:27Z","timestamp":1672825467000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-13447-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,21]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["13447"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-13447-1","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2022,7,21]]},"assertion":[{"value":"5 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This work was partially funded by the National Natural Science Foundation of China under Grant (61975124), Shanghai Natural Science Foundation(20ZR1428600), the Open Project Program of Shanghai Key Laboratory of Data Science (NO.2020090600003), and the Open Project Funding from the State Key Lab of Computer Architecture, ICT, CAS under Grant CARCHA202111. Any opinions, findings and conclusions expressed in this paper are those of the authors and do not necessarily reflect the views of the sponsors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}