{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T10:04:12Z","timestamp":1766311452645,"version":"3.37.3"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,8,14]],"date-time":"2021-08-14T00:00:00Z","timestamp":1628899200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,14]],"date-time":"2021-08-14T00:00:00Z","timestamp":1628899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s00521-021-06394-9","type":"journal-article","created":{"date-parts":[[2021,8,14]],"date-time":"2021-08-14T17:02:33Z","timestamp":1628960553000},"page":"593-606","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Context-guided feature enhancement network for automatic check-out"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4358-2800","authenticated-orcid":false,"given":"Yihan","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiejian","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,14]]},"reference":[{"key":"6394_CR1","unstructured":"Wei X-S, Cui Q, Yang L, Wang P, Liu L (2019) Rpc: a large-scale retail product checkout dataset. arXiv:1901.07249"},{"key":"6394_CR2","doi-asserted-by":"crossref","unstructured":"Li C, Du D, Zhang L, Luo T, Wu Y, Tian Q, Wen L, Lyu S (2019) Data priming network for automatic check-out. In: Proceedings of the 27th ACM international conference on multimedia, pp 2152\u20132160","DOI":"10.1145\/3343031.3350989"},{"key":"6394_CR3","doi-asserted-by":"crossref","unstructured":"Chen Z, Huang S, Tao D (2018) Context refinement for object detection. In: The European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-01237-3_5"},{"key":"6394_CR4","doi-asserted-by":"crossref","unstructured":"Chen X, Gupta A (2017) Spatial memory for context reasoning in object detection. arXiv:1704.04224","DOI":"10.1109\/ICCV.2017.440"},{"key":"6394_CR5","doi-asserted-by":"crossref","unstructured":"Carbonetto P, De\u00a0Freitas N, Barnard K (2004) A statistical model for general contextual object recognition. In: European conference on computer vision. Springer, pp 350\u2013362","DOI":"10.1007\/978-3-540-24670-1_27"},{"issue":"4","key":"6394_CR6","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017) Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"6394_CR7","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1016\/j.cviu.2010.02.004","volume":"114","author":"C Galleguillos","year":"2010","unstructured":"Galleguillos C, Belongie S (2010) Context based object categorization: a critical survey. Comput Vis Image Underst 114(6):712\u2013722","journal-title":"Comput Vis Image Underst"},{"key":"6394_CR8","doi-asserted-by":"crossref","unstructured":"Galleguillos C, Rabinovich A, Belongie S (2008) Object categorization using co-occurrence, location and appearance. In: IEEE conference on computer vision and pattern recognition, 2008. CVPR 2008. IEEE, pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587799"},{"issue":"8","key":"6394_CR9","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1038\/nrn1476","volume":"5","author":"M Bar","year":"2004","unstructured":"Bar M (2004) Visual objects in context. Nat Rev Neurosci 5(8):617\u2013629","journal-title":"Nat Rev Neurosci"},{"issue":"12","key":"6394_CR10","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.tics.2007.09.009","volume":"11","author":"A Oliva","year":"2007","unstructured":"Oliva A, Torralba A (2007) The role of context in object recognition. Trends Cogn Sci 11(12):520\u2013527","journal-title":"Trends Cogn Sci"},{"key":"6394_CR11","doi-asserted-by":"publisher","first-page":"519","DOI":"10.3758\/BF03197524","volume":"3","author":"TE Palmer","year":"1975","unstructured":"Palmer TE (1975) The effects of contextual scenes on the identification of objects. Memory Cognit 3:519\u2013526","journal-title":"Memory Cognit"},{"key":"6394_CR12","unstructured":"Alex Krizhevsky I, Hinton SG (2012) Imagenet classification with deep convolutional neural networks. In: NIPS"},{"key":"6394_CR13","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: toward real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91\u201399"},{"key":"6394_CR14","doi-asserted-by":"crossref","unstructured":"Zitnick CL, Doll\u00e1r P (2014) Edge boxes: locating object proposals from edges. In: European conference on computer vision. Springer, pp 391\u2013405","DOI":"10.1007\/978-3-319-10602-1_26"},{"issue":"2","key":"6394_CR15","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JRR Uijlings","year":"2013","unstructured":"Uijlings JRR, Van De Sande KEA, Gevers T, Smeulders AWM (2013) Selective search for object recognition. Int J Comput Vis 104(2):154\u2013171","journal-title":"Int J Comput Vis"},{"issue":"9","key":"6394_CR16","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904\u20131916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6394_CR17","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"6394_CR18","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"6394_CR19","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: single shot multibox detector. In: European conference on computer vision. Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"6394_CR20","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"6394_CR21","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv:1804.02767"},{"key":"6394_CR22","unstructured":"Bochkovskiy A, Wang C-Y, Mark Liao H-Y (2020) Yolov4: optimal speed and accuracy of object detection. arXiv:2004.10934"},{"key":"6394_CR23","doi-asserted-by":"crossref","unstructured":"Neubeck A, Van\u00a0Gool L (2006) Efficient non-maximum suppression. In: 18th international conference on pattern recognition (ICPR\u201906), vol\u00a03. IEEE, pp 850\u2013855","DOI":"10.1109\/ICPR.2006.479"},{"key":"6394_CR24","unstructured":"Fu C-Y, Liu W, Ranga A, Tyagi A, Berg AC (2017) Dssd: deconvolutional single shot detector. arXiv:1701.06659"},{"key":"6394_CR25","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. In: European conference on computer vision. Springer, pp 630\u2013645","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"6394_CR26","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"key":"6394_CR27","doi-asserted-by":"crossref","unstructured":"Yi Lin T, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: 2017 IEEE international conference on computer vision (ICCV), pp 2999\u20133007","DOI":"10.1109\/ICCV.2017.324"},{"key":"6394_CR28","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: detecting objects as paired keypoints. In: Proceedings of the European conference on computer vision (ECCV), pp 734\u2013750","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"6394_CR29","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q (2019) Centernet: Keypoint triplets for object detection. In: Proceedings of the IEEE international conference on computer vision, pp 6569\u20136578","DOI":"10.1109\/ICCV.2019.00667"},{"key":"6394_CR30","doi-asserted-by":"crossref","unstructured":"Divvala SK, Hoiem D, Hays JH, Efros AA, Hebert M (2009) An empirical study of context in object detection. In: IEEE conference on computer vision and pattern recognition, 2009. CVPR 2009. IEEE, pp 1271\u20131278","DOI":"10.1109\/CVPR.2009.5206532"},{"key":"6394_CR31","doi-asserted-by":"crossref","unstructured":"Mottaghi R, Chen X, Liu X, Cho N-G, Lee S-W, Fidler S, Urtasun R, Yuille A (2014) The role of context for object detection and semantic segmentation in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 891\u2013898","DOI":"10.1109\/CVPR.2014.119"},{"key":"6394_CR32","doi-asserted-by":"crossref","unstructured":"Yu R, Chen X, Morariu VI, Davis LS (2016) The role of context selection in object detection. arXiv:1609.02948","DOI":"10.5244\/C.30.133"},{"key":"6394_CR33","doi-asserted-by":"crossref","unstructured":"Gidaris S, Komodakis N (2015) Object detection via a multi-region and semantic segmentation-aware cnn model. In: Proceedings of the IEEE international conference on computer vision, pp 1134\u20131142","DOI":"10.1109\/ICCV.2015.135"},{"key":"6394_CR34","unstructured":"Ouyang W, Wang K, Zhu X, Wang X (2017) Learning chained deep features and classifiers for cascade in object detection. arXiv:1702.07054"},{"issue":"10","key":"6394_CR35","doi-asserted-by":"publisher","first-page":"6549","DOI":"10.1007\/s00521-018-3486-1","volume":"31","author":"J Leng","year":"2019","unstructured":"Leng J, Liu Y (2019) An enhanced ssd with feature fusion and visual reasoning for object detection. Neural Comput Appl 31(10):6549\u20136558","journal-title":"Neural Comput Appl"},{"issue":"4","key":"6394_CR36","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1109\/TITS.2019.2909275","volume":"21","author":"J Leng","year":"2019","unstructured":"Leng J, Liu Y, Dawei D, Zhang T, Quan P (2019) Robust obstacle detection and recognition for driver assistance systems. IEEE Trans Intell Transp Syst 21(4):1560\u20131571","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"6394_CR37","doi-asserted-by":"crossref","unstructured":"Bell S, Zitnick CL, Bala K, Girshick R (2016) Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2874\u20132883","DOI":"10.1109\/CVPR.2016.314"},{"issue":"5","key":"6394_CR38","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1109\/TMM.2016.2642789","volume":"19","author":"J Li","year":"2017","unstructured":"Li J, Wei Y, Liang X, Dong J, Tingfa X, Feng J, Yan S (2017) Attentive contexts for object detection. IEEE Trans Multimed 19(5):944\u2013954","journal-title":"IEEE Trans Multimed"},{"key":"6394_CR39","doi-asserted-by":"crossref","unstructured":"Chen X, Li L-J, Fei-Fei L, Gupta A (2018) Iterative visual reasoning beyond convolutions. arXiv:1803.11189","DOI":"10.1109\/CVPR.2018.00756"},{"key":"6394_CR40","doi-asserted-by":"crossref","unstructured":"Hu H, Gu J, Zhang Z, Dai J, Wei Y (2018) Relation networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3588\u20133597","DOI":"10.1109\/CVPR.2018.00378"},{"key":"6394_CR41","doi-asserted-by":"crossref","unstructured":"Gu J, Hu H, Wang L, Wei Y, Dai J (2018) Learning region features for object detection. In: Proceedings of the European conference on computer vision (ECCV), pp 381\u2013395","DOI":"10.1007\/978-3-030-01258-8_24"},{"key":"6394_CR42","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.ins.2020.04.001","volume":"528","author":"L Dong","year":"2020","unstructured":"Dong L, Zhang H, Ji Y, Ding, (2020) Crowd counting by using multi-level density-based spatial information: a multi-scale cnn framework. Inf Sci 528:79\u201391","journal-title":"Inf Sci"},{"key":"6394_CR43","doi-asserted-by":"crossref","unstructured":"Koubaroulis D, Matas J, Kittler J, CMP CTU (2002) Evaluating colour-based object recognition algorithms using the soil-47 database. In: Asian conference on computer vision, vol\u00a02","DOI":"10.1109\/ICPR.2002.1048490"},{"key":"6394_CR44","doi-asserted-by":"crossref","unstructured":"Merler M, Galleguillos C, Belongie S (2007) Recognizing groceries in situ using in vitro training data. In: 2007 IEEE conference on computer vision and pattern recognition. IEEE, pp 1\u20138","DOI":"10.1109\/CVPR.2007.383486"},{"issue":"1","key":"6394_CR45","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.compag.2009.09.002","volume":"70","author":"A Rocha","year":"2010","unstructured":"Rocha A, Hauagge DC, Wainer J, Goldenstein S (2010) Automatic fruit and vegetable classification from images. Comput Electron Agric 70(1):96\u2013104","journal-title":"Comput Electron Agric"},{"key":"6394_CR46","doi-asserted-by":"crossref","unstructured":"George M, Floerkemeier C (2014) Recognizing products: a per-exemplar multi-label image classification approach. In: European conference on computer vision. Springer, pp 440\u2013455","DOI":"10.1007\/978-3-319-10605-2_29"},{"key":"6394_CR47","unstructured":"Jund P, Abdo N, Eitel A, Burgard W (2016) The freiburg groceries dataset. arXiv:1611.05799"},{"key":"6394_CR48","doi-asserted-by":"crossref","unstructured":"Follmann P, Bottger T, Hartinger P, Konig R, Ulrich M (2018) Mvtec d2s: densely segmented supermarket dataset. In: Proceedings of the European conference on computer vision (ECCV), pp 569\u2013585","DOI":"10.1007\/978-3-030-01249-6_35"},{"key":"6394_CR49","first-page":"1","volume":"99","author":"H Zhang","year":"2019","unstructured":"Zhang H, Li D, Ji Y, Zhou H, Liu K (2019) Towards new retail: a benchmark dataset for smart unmanned vending machines. IEEE Trans Ind Inform 99:1","journal-title":"IEEE Trans Ind Inform"},{"key":"6394_CR50","doi-asserted-by":"crossref","unstructured":"Liu A, Wang J, Liu X, Cao B, Zhang C, Yu H (2020) Bias-based universal adversarial patch attack for automatic check-out. In: European conference on computer vision","DOI":"10.1007\/978-3-030-58601-0_24"},{"key":"6394_CR51","doi-asserted-by":"publisher","unstructured":"Zhang L, Du D, Li C, Wu Y, Luo T (2020) Iterative knowledge distillation for automatic check-out. In: IEEE Transactions on Multimedia. IEEE. https:\/\/doi.org\/10.1109\/TMM.2020.3037502","DOI":"10.1109\/TMM.2020.3037502"},{"issue":"18","key":"6394_CR52","doi-asserted-by":"publisher","first-page":"14613","DOI":"10.1007\/s00521-020-05148-3","volume":"32","author":"W Wang","year":"2020","unstructured":"Wang W, Cui Y, Li G, Jiang C, Deng S (2020) A self-attention-based destruction and construction learning fine-grained image classification method for retail product recognition. Neural Comput Appl 32(18):14613\u201314622","journal-title":"Neural Comput Appl"},{"key":"6394_CR53","doi-asserted-by":"crossref","unstructured":"Yang Y, Sheng L, Jiang X, Wang H, Xu D, Cao X (2021) Increaco: incrementally learned automatic check-out with photorealistic exemplar augmentation. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 626\u2013634","DOI":"10.1109\/WACV48630.2021.00067"},{"key":"6394_CR54","doi-asserted-by":"crossref","unstructured":"Zhu J-Y, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2223\u20132232","DOI":"10.1109\/ICCV.2017.244"},{"key":"6394_CR55","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"6394_CR56","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Lawrence Zitnick C (2014) Microsoft coco: common objects in context. In: European conference on computer vision. Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06394-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06394-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06394-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T14:22:28Z","timestamp":1725632548000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06394-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,14]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["6394"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06394-9","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2021,8,14]]},"assertion":[{"value":"14 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that we have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}