{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T21:54:03Z","timestamp":1774475643331,"version":"3.50.1"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030584511","type":"print"},{"value":"9783030584528","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58452-8_19","type":"book-chapter","created":{"date-parts":[[2020,11,3]],"date-time":"2020-11-03T00:34:03Z","timestamp":1604363643000},"page":"316-332","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":81,"title":["Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset"],"prefix":"10.1007","author":[{"given":"Menglin","family":"Jia","sequence":"first","affiliation":[]},{"given":"Mengyun","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Mikhail","family":"Sirotenko","sequence":"additional","affiliation":[]},{"given":"Yin","family":"Cui","sequence":"additional","affiliation":[]},{"given":"Claire","family":"Cardie","sequence":"additional","affiliation":[]},{"given":"Bharath","family":"Hariharan","sequence":"additional","affiliation":[]},{"given":"Hartwig","family":"Adam","sequence":"additional","affiliation":[]},{"given":"Serge","family":"Belongie","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,3]]},"reference":[{"key":"19_CR1","unstructured":"Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: OSDI (2016)"},{"issue":"6","key":"19_CR2","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1037\/h0044049","volume":"53","author":"F Attneave","year":"1956","unstructured":"Attneave, F., Arnoult, M.D.: The quantitative study of shape and pattern perception. Psychol. Bull. 53(6), 452\u2013471 (1956)","journal-title":"Psychol. Bull."},{"key":"19_CR3","unstructured":"Bloomsbury.com: Fashion photography archive. Retrieved from 9 May 2019. https:\/\/www.bloomsbury.com\/dr\/digital-resources\/products\/fashion-photography-archive\/"},{"key":"19_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/978-3-642-37447-0_25","volume-title":"Computer Vision \u2013 ACCV 2012","author":"L Bossard","year":"2012","unstructured":"Bossard, L., et al.: Apparel classification with style. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) Computer Vision \u2013 ACCV 2012. Lecture Notes in Computer Science, vol. 7727, pp. 321\u2013335. Springer, Berlin, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-37447-0_25"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Du, X., et al.: SpineNet: learning scale-permuted backbone for recognition and localization. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01161"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: CVPR (2009)","DOI":"10.1109\/CVPRW.2009.5206772"},{"key":"19_CR7","unstructured":"FashionAI: Retrieved from 9 May 2019 . http:\/\/fashionai.alibaba.com\/"},{"key":"19_CR8","unstructured":"Fashionary.org: Fashionpedia \u2013 the visual dictionary of fashion design. Retrieved from 9 May 2019. https:\/\/fashionary.org\/products\/fashionpedia"},{"key":"19_CR9","unstructured":"Ferrari, V., Zisserman, A.: Learning visual attributes. In: Advances in Neural Information Processing Systems (2008)"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Fu, C.Y., Berg, T.L., Berg, A.C.: IMP: instance mask projection for high accuracy semantic segmentation of things. arXiv preprint arXiv:1906.06597 (2019)","DOI":"10.1109\/ICCV.2019.00528"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Ge, Y., Zhang, R., Wang, X., Tang, X., Luo, P.: Deepfashion2: a versatile benchmark for detection, pose estimation, segmentation and re-identification of clothing images. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00548"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"19_CR13","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: training imageNet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Guo, S., et al.: The imaterialist fashion attribute dataset. In: ICCV Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00377"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Han, X., et al.: Automatic spatially-aware fashion concept discovery. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.163"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"He, R., McAuley, J.: Ups and downs: modeling the visual evolution of fashion trends with one-class collaborative filtering. In: WWW (2016)","DOI":"10.1145\/2872427.2883037"},{"key":"19_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1007\/978-3-642-33712-3_25","volume-title":"Computer Vision \u2013 ECCV 2012","author":"D Hoiem","year":"2012","unstructured":"Hoiem, D., Chodpathumwan, Y., Dai, Q.: Diagnosing error in object detectors. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) Computer Vision \u2013 ECCV 2012. Lecture Notes in Computer Science, vol. 7574, pp. 340\u2013353. Springer, Berlin, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33712-3_25"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Hsiao, W.L., Grauman, K.: Learning the latent \u201clook\u201d: unsupervised discovery of a style-coherent embedding from fashion images. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.451"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Huang, J., Feris, R., Chen, Q., Yan, S.: Cross-domain image retrieval with a dual attribute-aware ranking network. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.127"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Inoue, N., Simo-Serra, E., Yamasaki, T., Ishikawa, H.: Multi-label fashion image classification with minimal human supervision. In: ICCV (2017)","DOI":"10.1109\/ICCVW.2017.265"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Kendall, E.F., McGuinness, D.L.: Ontology Engineering (Synthesis Lectures on The Semantic Web: Theory and Technology), pp. 1\u2013136. Morgan & Claypool, San Rafael (2019)","DOI":"10.2200\/S00834ED1V01Y201802WBE018"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Kiapour, M.H., Han, X., Lazebnik, S., Berg, A.C., Berg, T.L.: Where to buy it: matching street clothing photos in online shops. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.382"},{"key":"19_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-319-10590-1_31","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MH Kiapour","year":"2014","unstructured":"Kiapour, M.H., Yamaguchi, K., Berg, A.C., Berg, T.L.: Hipster wars: discovering elements of fashion styles. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision \u2013 ECCV 2014. Lecture Notes in Computer Science, vol. 8689, pp. 472\u2013488. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_31"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00963"},{"key":"19_CR28","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. (IJCV) 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Kumar, N., Berg, A.C., Belhumeur, P.N., Nayar, S.K.: Attribute and simile classifiers for face verification. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459250"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"19_CR31","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":"TY 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.) Computer Vision \u2013 ECCV 2014. Lecture Notes in Computer Science, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Qiu, S., Wang, X., Tang, X.: Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.124"},{"key":"19_CR33","unstructured":"Lopez, A.: Fdupes is a program for identifying or deleting duplicate files residing within specified directories. Retrieved from 9 May 2019. https:\/\/github.com\/adrianlopezroche\/fdupes"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Mall, U., Matzen, K., Hariharan, B., Snavely, N., Bala, K.: Geostyle: discovering fashion trends and events. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00050"},{"key":"19_CR35","unstructured":"Matzen, K., Bala, K., Snavely, N.: StreetStyle: exploring world-wide clothing styles from millions of photos. arXiv preprint arXiv:1706.01869 (2017)"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Parikh, D., Grauman, K.: Relative attributes. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"19_CR37","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (2015)"},{"issue":"3","key":"19_CR38","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1037\/0096-3445.104.3.192","volume":"104","author":"E Rosch","year":"1975","unstructured":"Rosch, E.: Cognitive representations of semantic categories. J. Exp. Psychol. Gen. 104(3), 192\u2013233 (1975)","journal-title":"J. Exp. Psychol. Gen."},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Rubio, A., Yu, L., Simo-Serra, E., Moreno-Noguer, F.: Multi-modal embedding for main product detection in fashion. In: ICCV (2017)","DOI":"10.1109\/ICIP.2017.8296311"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Simo-Serra, E., Fidler, S., Moreno-Noguer, F., Urtasun, R.: Neuroaesthetics in fashion: modeling the perception of fashionability. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298688"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Simo-Serra, E., Ishikawa, H.: Fashion style in 128 floats: joint ranking and classification using weak data for feature extraction. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.39"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Takagi, M., Simo-Serra, E., Iizuka, S., Ishikawa, H.: What makes a style: experimental analysis of fashion prediction. In: ICCV (2017)","DOI":"10.1109\/ICCVW.2017.263"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Van Horn, G., et al.: The iNaturalist species classification and detection dataset. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00914"},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Vittayakorn, S., Yamaguchi, K., Berg, A.C., Berg, T.L.: Runway to Realway: visual analysis of fashion. In: WACV (2015)","DOI":"10.1109\/WACV.2015.131"},{"key":"19_CR45","doi-asserted-by":"crossref","unstructured":"Vrande\u010di\u0107, D., Kr\u00f6tzsch, M.: Wikidata: a free collaborative knowledge base (2014)","DOI":"10.1145\/2629489"},{"key":"19_CR46","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Technical report CNS-TR-2011-001, California Institute of Technology (2011)"},{"key":"19_CR47","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)"},{"key":"19_CR48","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 (2017)"},{"key":"19_CR49","doi-asserted-by":"crossref","unstructured":"Yamaguchi, K., Berg, T.L., Ortiz, L.E.: Chic or social: visual popularity analysis in online fashion networks. In: ACM MM (2014)","DOI":"10.1145\/2647868.2654958"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Yamaguchi, K., Kiapour, M.H., Ortiz, L.E., Berg, T.L.: Parsing clothing in fashion photographs. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248101"},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"Yu, A., Grauman, K.: Semantic jitter: dense supervision for visual comparisons via synthetic images. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.594"},{"key":"19_CR52","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: Bdd100k: a diverse driving dataset for heterogeneous multitask learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"19_CR53","doi-asserted-by":"crossref","unstructured":"Zheng, S., Yang, F., Kiapour, M.H., Piramuthu, R.: Modanet: a large-scale street fashion dataset with polygon annotations. In: ACM MM (2018)","DOI":"10.1145\/3240508.3240652"},{"key":"19_CR54","unstructured":"Zoph, B., et al.: Rethinking pre-training and self-training. arXiv preprint arXiv:2006.06882 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58452-8_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:10:33Z","timestamp":1730592633000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58452-8_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030584511","9783030584528"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58452-8_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"3 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}