{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:35:28Z","timestamp":1783697728111,"version":"3.55.0"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012151","type":"print"},{"value":"9783030012168","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\/978-3-030-01216-8_12","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T15:10:26Z","timestamp":1539011426000},"page":"185-201","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":636,"title":["Exploring the Limits of Weakly Supervised Pretraining"],"prefix":"10.1007","author":[{"given":"Dhruv","family":"Mahajan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ross","family":"Girshick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vignesh","family":"Ramanathan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiming","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manohar","family":"Paluri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashwin","family":"Bharambe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurens","family":"van der Maaten","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"key":"12_CR1","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":"12_CR2","unstructured":"Donahue, J., et al.: DeCAF: a deep convolutional activation feature for generic visual recognition. arXiv:1310.1531 (2013)"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional neural networks. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Papandreou, G., et al.: Towards accurate multi-person pose estimation in the wild. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.395"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"12_CR11","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.: ImageNet large scale visual recognition challenge. IJCV 115, 211\u2013252 (2015)","journal-title":"IJCV"},{"key":"12_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/978-3-319-10584-0_22","volume-title":"Computer Vision \u2013 ECCV 2014","author":"P Agrawal","year":"2014","unstructured":"Agrawal, P., Girshick, R., Malik, J.: Analyzing the performance of multilayer neural networks for object recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014 Part VII. LNCS, vol. 8695, pp. 329\u2013344. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_22"},{"key":"12_CR13","unstructured":"Huh, M., Agrawal, P., Efros, A.: What makes ImageNet good for transfer learning? arXiv:1608.08614 (2016)"},{"key":"12_CR14","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2017","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. PAMI 40, 1452\u20131464 (2017)","journal-title":"PAMI"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Dollar, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"12_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1007\/978-3-319-46478-7_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Joulin","year":"2016","unstructured":"Joulin, A., van der Maaten, L., Jabri, A., Vasilache, N.: Learning visual features from large weakly supervised data. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016 Part VII. LNCS, vol. 9911, pp. 67\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_5"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.97"},{"key":"12_CR18","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 Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"12_CR19","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: training ImageNet in 1 hour. In: arXiv:1706.02677 (2017)"},{"key":"12_CR20","unstructured":"WordNet: About WordNet (2010). http:\/\/wordnet.princeton.edu"},{"key":"12_CR21","unstructured":"Welinder, P., et al.: Caltech-UCSD Birds 200. Technical report, Caltech (2010)"},{"key":"12_CR22","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/978-3-319-46466-4_15","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Albert Gordo","year":"2016","unstructured":"Gordo, A., Almazan, J., Revaud, J., Larlus, D.: Deep image retrieval: learning global representations for image search. In: arXiv:1604.01325 (2016)"},{"key":"12_CR23","unstructured":"Tolias, G., Sicre, R., Jegou, H.: Particular object retrieval with integral max-pooling of CNN activations. In: ICLR (2016)"},{"key":"12_CR24","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":"12_CR25","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Weinberger, K., van der Maaten, L.: Densely connected convolutional networks. In: CVPR. (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-V4, inception-ResNet and the impact of residual connections on learning. In: arXiv:1602.07261 (2016)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"12_CR27","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Pathak, D., Girshick, R., Doll\u00e1r, P., Darrell, T., Hariharan, B.: Learning features by watching objects move. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.638"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., Le, Q.: Learning transferable architectures for scalable image recognition. In: arXiv:1707.07012 (2017)","DOI":"10.1109\/CVPR.2018.00907"},{"key":"12_CR32","unstructured":"Stock, P., Cisse, M.: Convnets and ImageNet beyond accuracy: explanations, bias detection, adversarial examples and model criticism. In: arXiv:1711.11443 (2017)"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Izadinia, H., Russell, B., Farhadi, A., Hoffman, M., Hertzmann, A.: Deep classifiers from image tags in the wild. In: Multimedia COMMONS (2015)","DOI":"10.1145\/2814815.2814821"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Misra, I., Zitnick, C.L., Mitchell, M., Girshick, R.: Seeing through the human reporting bias: visual classifiers from noisy human-centric labels. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.320"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Veit, A., Nickel, M., Belongie, S., van der Maaten, L.: Separating self-expression and visual content in hashtag supervision. In: arXiv 1711.09825 (2017)","DOI":"10.1109\/CVPR.2018.00620"},{"key":"12_CR36","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS (2013)"},{"key":"12_CR37","unstructured":"Girshick, R., Radosavovic, I., Gkioxari, G., Doll\u00e1r, P., He, K.: Detectron (2018). https:\/\/github.com\/facebookresearch\/detectron"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Li, A., Jabri, A., Joulin, A., van der Maaten, L.: Learning visual n-grams from web data. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.449"},{"issue":"2","key":"12_CR40","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/2812802","volume":"59","author":"B Thomee","year":"2016","unstructured":"Thomee, B., et al.: YFCC100M: the new data in multimedia research. Commun. ACM 59(2), 64\u201373 (2016)","journal-title":"Commun. ACM"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Gross, S., Ranzato, M., Szlam, A.: Hard mixtures of experts for large scale weakly supervised vision. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.540"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Denton, E., Weston, J., Paluri, M., Bourdev, L., Fergus, R.: User conditional hashtag prediction for images. In: Proceedings of KDD, pp. 1731\u20131740 (2015)","DOI":"10.1145\/2783258.2788576"},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"12_CR44","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Web-scale training for face identification. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298891"},{"key":"12_CR45","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. arXiv preprint arXiv:1702.08734 (2017)"},{"key":"12_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1007\/978-3-642-33709-3_48","volume-title":"Computer Vision \u2013 ECCV 2012","author":"H Stew\u00e9nius","year":"2012","unstructured":"Stew\u00e9nius, H., Gunderson, S.H., Pilet, J.: Size matters: exhaustive geometric verification for image retrieval accepted for ECCV 2012. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012 Part II. LNCS, pp. 674\u2013687. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33709-3_48"}],"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\/978-3-030-01216-8_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:19:34Z","timestamp":1665188374000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01216-8_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012151","9783030012168"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01216-8_12","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":"9 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"}]}}