{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T19:17:11Z","timestamp":1772911031315,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012489","type":"print"},{"value":"9783030012496","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01249-6_35","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T15:35:46Z","timestamp":1538753746000},"page":"581-597","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":61,"title":["MVTec D2S: Densely Segmented Supermarket Dataset"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5400-2384","authenticated-orcid":false,"given":"Patrick","family":"Follmann","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5404-8662","authenticated-orcid":false,"given":"Tobias","family":"B\u00f6ttger","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7093-6280","authenticated-orcid":false,"given":"Philipp","family":"H\u00e4rtinger","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4169-6759","authenticated-orcid":false,"given":"Rebecca","family":"K\u00f6nig","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8457-5554","authenticated-orcid":false,"given":"Markus","family":"Ulrich","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"35_CR1","unstructured":"Abu-El-Haija, S., et al.: Youtube-8m: a large-scale video classification benchmark. CoRR abs\/1609.08675 (2016). https:\/\/arxiv.org\/abs\/1609.08675"},{"key":"35_CR2","doi-asserted-by":"publisher","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3213\u20133223 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.350","DOI":"10.1109\/CVPR.2016.350"},{"key":"35_CR3","unstructured":"ECRS: RAPTOR. https:\/\/www.ecrs.com\/products\/point-of-sale-pos\/accelerated-checkout\/. Accessed 7 Mar 2018"},{"issue":"1","key":"35_CR4","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.M.A., Gool, L.J.V., Williams, C.K.I., Winn, J.M., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111(1), 98\u2013136 (2015). https:\/\/doi.org\/10.1007\/s11263-014-0733-5","journal-title":"Int. J. Comput. Vis."},{"key":"35_CR5","doi-asserted-by":"publisher","unstructured":"Follmann, P., B\u00f6ttger, T.: A rotationally-invariant convolution module by feature map back-rotation. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 784\u2013792 (2018). https:\/\/doi.org\/10.1109\/WACV.2018.00091","DOI":"10.1109\/WACV.2018.00091"},{"issue":"11","key":"35_CR6","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Rob. Res. 32(11), 1231\u20131237 (2013). https:\/\/doi.org\/10.1177\/0278364913491297","journal-title":"Int. J. Rob. Res."},{"key":"35_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1007\/978-3-319-10605-2_29","volume-title":"Computer Vision \u2013 ECCV 2014","author":"M George","year":"2014","unstructured":"George, M., Floerkemeier, C.: Recognizing products: a per-exemplar multi-label image classification approach. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 440\u2013455. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_29"},{"key":"35_CR8","doi-asserted-by":"publisher","unstructured":"Gurumurthy, S., Kiran Sarvadevabhatla, R., Venkatesh Babu, R.: DeLiGAN: generative adversarial networks for diverse and limited data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 166\u2013174 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.525","DOI":"10.1109\/CVPR.2017.525"},{"key":"35_CR9","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: IEEE International Conference on Computer Vision (ICCV), pp. 1059\u20131067 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"35_CR10","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"35_CR11","doi-asserted-by":"publisher","unstructured":"Huang, X., Li, Y., Poursaeed, O., Hopcroft, J., Belongie, S.: Stacked generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5077\u20135086 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.202","DOI":"10.1109\/CVPR.2017.202"},{"key":"35_CR12","unstructured":"ITAB: HyperFLOW. https:\/\/itab.com\/en\/itab\/checkout\/self-checkouts\/. Accessed 7 Mar 2018"},{"key":"35_CR13","unstructured":"Jund, P., Abdo, N., Eitel, A., Burgard, W.: The freiburg groceries dataset. CoRR abs\/1611.05799 (2016). https:\/\/arxiv.org\/abs\/1611.05799"},{"key":"35_CR14","unstructured":"Koubaroulis, D., Matas, J., Kittler, J.: Evaluating colour-based object recognition algorithms using the SOIL-47 database. In: Asian Conference on Computer Vision, p. 2 (2002)"},{"key":"35_CR15","doi-asserted-by":"publisher","unstructured":"Lai, K., Bo, L., Fox, D.: Unsupervised feature learning for 3D scene labeling. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 3050\u20133057. IEEE (2014). https:\/\/doi.org\/10.1109\/ICRA.2014.6907298","DOI":"10.1109\/ICRA.2014.6907298"},{"key":"35_CR16","doi-asserted-by":"publisher","unstructured":"Lai, K., Bo, L., Ren, X., Fox, D.: A large-scale hierarchical multi-view RGB-D object dataset. In: 2011 IEEE International Conference on Robotics and Automation (ICRA), pp. 1817\u20131824. IEEE (2011). https:\/\/doi.org\/10.1109\/ICRA.2011.5980382","DOI":"10.1109\/ICRA.2011.5980382"},{"issue":"7553","key":"35_CR17","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015). https:\/\/doi.org\/10.1038\/nature14539","journal-title":"Nature"},{"key":"35_CR18","doi-asserted-by":"publisher","unstructured":"Li, J., Liang, X., Wei, Y., Xu, T., Feng, J., Yan, S.: Perceptual generative adversarial networks for small object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1222\u20131230 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.211","DOI":"10.1109\/CVPR.2017.211"},{"key":"35_CR19","doi-asserted-by":"publisher","unstructured":"Li, Y., Qi, H., Da, J., Ji, X., Wei, Y.: Fully convolutional instance-aware semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2359\u20132367 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.472","DOI":"10.1109\/CVPR.2017.472"},{"key":"35_CR20","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"35_CR21","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: IEEE International Conference on Computer Vision (ICCV) (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"key":"35_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"35_CR23","doi-asserted-by":"publisher","unstructured":"Merler, M., Galleguillos, C., Belongie, S.: Recognizing groceries in situ using in vitro training data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u20138 (2007). https:\/\/doi.org\/10.1109\/CVPR.2007.383486","DOI":"10.1109\/CVPR.2007.383486"},{"key":"35_CR24","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.patrec.2015.10.013","volume":"81","author":"M Minervini","year":"2016","unstructured":"Minervini, M., Fischbach, A., Scharr, H., Tsaftaris, S.A.: Finely-grained annotated datasets for image-based plant phenotyping. Pattern Recognit. Lett. 81, 80\u201389 (2016). https:\/\/doi.org\/10.1016\/j.patrec.2015.10.013","journal-title":"Pattern Recognit. Lett."},{"key":"35_CR25","doi-asserted-by":"publisher","unstructured":"Neuhold, G., Ollmann, T., Rota Bulo, S., Kontschieder, P.: The mapillary vistas dataset for semantic understanding of street scenes. In: IEEE International Conference on Computer Vision (ICCV), pp. 4990\u20134999 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.534","DOI":"10.1109\/ICCV.2017.534"},{"key":"35_CR26","doi-asserted-by":"publisher","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.690","DOI":"10.1109\/CVPR.2017.690"},{"issue":"6","key":"35_CR27","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 62\u201366 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"35_CR28","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/LRA.2016.2532924","volume":"1","author":"C Rennie","year":"2016","unstructured":"Rennie, C., Shome, R., Bekris, K.E., De Souza, A.F.: A dataset for improved RGBD-based object detection and pose estimation for warehouse pick-and-place. IEEE Rob. Autom. Lett. 1(2), 1179\u20131185 (2016). https:\/\/doi.org\/10.1109\/LRA.2016.2532924","journal-title":"IEEE Rob. Autom. Lett."},{"key":"35_CR29","doi-asserted-by":"publisher","unstructured":"Richtsfeld, A., M\u00f6rwald, T., Prankl, J., Zillich, M., Vincze, M.: Segmentation of unknown objects in indoor environments. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4791\u20134796. IEEE (2012). https:\/\/doi.org\/10.1109\/IROS.2012.6385661","DOI":"10.1109\/IROS.2012.6385661"},{"issue":"1","key":"35_CR30","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, D.C., Wainer, J., Goldenstein, S.: Automatic fruit and vegetable classification from images. Comput. Electron. Agric. 70(1), 96\u2013104 (2010). https:\/\/doi.org\/10.1016\/j.compag.2009.09.002","journal-title":"Comput. Electron. Agric."},{"issue":"3","key":"35_CR31","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNetlarge scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis."},{"key":"35_CR32","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2015","unstructured":"Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39, 640\u2013651 (2015). https:\/\/doi.org\/10.1109\/TPAMI.2016.2572683","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"35_CR33","doi-asserted-by":"publisher","unstructured":"Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 761\u2013769 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.89","DOI":"10.1109\/CVPR.2016.89"},{"key":"35_CR34","doi-asserted-by":"publisher","unstructured":"Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., Webb, R.: Learning from simulated and unsupervised images through adversarial training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2107\u20132116 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.241","DOI":"10.1109\/CVPR.2017.241"},{"key":"35_CR35","doi-asserted-by":"publisher","unstructured":"Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: IEEE International Conference on Computer Vision (ICCV), pp. 5907\u20135915 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.629","DOI":"10.1109\/ICCV.2017.629"},{"key":"35_CR36","unstructured":"Zhou, B., Khosla, A., Lapedriza, \u00c0., Torralba, A., Oliva, A.: Places: an image database for deep scene understanding. CoRR abs\/1610.02055 (2016). http:\/\/arxiv.org\/abs\/1610.02055"},{"key":"35_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Semantic understanding of scenes through the ADE20K dataset. CoRR abs\/1608.05442 (2016). http:\/\/arxiv.org\/abs\/1608.05442","DOI":"10.1109\/CVPR.2017.544"},{"key":"35_CR38","doi-asserted-by":"publisher","unstructured":"Zhou, Y., Ye, Q., Qiu, Q., Jiao, J.: Oriented response networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4961\u20134970 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.527","DOI":"10.1109\/CVPR.2017.527"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01249-6_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T00:58:30Z","timestamp":1664931510000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01249-6_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012489","9783030012496"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01249-6_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}