{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:46:40Z","timestamp":1781797600360,"version":"3.54.5"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012182","type":"print"},{"value":"9783030012199","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\/978-3-030-01219-9_47","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T10:23:51Z","timestamp":1538821431000},"page":"793-811","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":187,"title":["Women Also Snowboard: Overcoming Bias in Captioning Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9340-5143","authenticated-orcid":false,"given":"Lisa Anne","family":"Hendricks","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5713-2774","authenticated-orcid":false,"given":"Kaylee","family":"Burns","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5704-7614","authenticated-orcid":false,"given":"Kate","family":"Saenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-8533","authenticated-orcid":false,"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1161-6006","authenticated-orcid":false,"given":"Anna","family":"Rohrbach","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"47_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and VQA. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"47_CR2","doi-asserted-by":"crossref","unstructured":"Argamon, S., Koppel, M., Pennebaker, J.W., Schler, J.: Mining the blogosphere: age, gender and the varieties of self-expression. First Monday 12(9) (2007)","DOI":"10.5210\/fm.v12i9.2003"},{"key":"47_CR3","first-page":"671","volume":"104","author":"S Barocas","year":"2016","unstructured":"Barocas, S., Selbst, A.D.: Big data\u2019s disparate impact. Calif. Law Rev. 104, 671 (2016)","journal-title":"Calif. Law Rev."},{"key":"47_CR4","unstructured":"Bolukbasi, T., Chang, K.W., Zou, J.Y., Saligrama, V., Kalai, A.T.: Man is to computer programmer as woman is to homemaker? Debiasing word embeddings. In: Advances in Neural Information Processing Systems (NIPS), pp. 4349\u20134357 (2016)"},{"key":"47_CR5","unstructured":"Buolamwini, J.A.: Gender shades: intersectional phenotypic and demographic evaluation of face datasets and gender classifiers. Ph.D. thesis, Massachusetts Institute of Technology (2017)"},{"key":"47_CR6","unstructured":"Burger, J.D., Henderson, J., Kim, G., Zarrella, G.: Discriminating gender on Twitter. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1301\u20131309. Association for Computational Linguistics (2011)"},{"key":"47_CR7","doi-asserted-by":"crossref","unstructured":"Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M., Elhadad, N.: Intelligible models for healthcare: predicting pneumonia risk and hospital 30-day readmission. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1721\u20131730. ACM (2015)","DOI":"10.1145\/2783258.2788613"},{"key":"47_CR8","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"47_CR9","doi-asserted-by":"crossref","unstructured":"Dwork, C., Hardt, M., Pitassi, T., Reingold, O., Zemel, R.: Fairness through awareness. In: Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, pp. 214\u2013226. ACM (2012)","DOI":"10.1145\/2090236.2090255"},{"issue":"12","key":"47_CR10","doi-asserted-by":"publisher","first-page":"2170","DOI":"10.1109\/TIFS.2014.2359646","volume":"9","author":"E Eidinger","year":"2014","unstructured":"Eidinger, E., Enbar, R., Hassner, T.: Age and gender estimation of unfiltered faces. IEEE Trans. Inf. For. Secur. 9(12), 2170\u20132179 (2014)","journal-title":"IEEE Trans. Inf. For. Secur."},{"key":"47_CR11","doi-asserted-by":"crossref","unstructured":"Fong, R.C., Vedaldi, A.: Interpretable explanations of black boxes by meaningful perturbation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.371"},{"key":"47_CR12","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Malik, J.: Contextual action recognition with R* CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1080\u20131088 (2015)","DOI":"10.1109\/ICCV.2015.129"},{"key":"47_CR13","doi-asserted-by":"crossref","unstructured":"Gordon, J., Van Durme, B.: Reporting bias and knowledge acquisition. In: Proceedings of the 2013 workshop on Automated Knowledge Base Construction, pp. 25\u201330. ACM (2013)","DOI":"10.1145\/2509558.2509563"},{"key":"47_CR14","unstructured":"Hardt, M., Price, E., Srebro, N., et al.: Equality of opportunity in supervised learning. In: Advances in Neural Information Processing Systems (NIPS), pp. 3315\u20133323 (2016)"},{"key":"47_CR15","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"47_CR16","doi-asserted-by":"crossref","unstructured":"Larson, B.N.: Gender as a variable in natural-language processing: Ethical considerations (2017)","DOI":"10.18653\/v1\/W17-1601"},{"key":"47_CR17","doi-asserted-by":"crossref","unstructured":"Lavie, M.D.A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), p. 376 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"47_CR18","doi-asserted-by":"crossref","unstructured":"Levi, G., Hassner, T.: Age and gender classification using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), pp. 34\u201342 (2015)","DOI":"10.1109\/CVPRW.2015.7301352"},{"issue":"1","key":"47_CR19","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/18.61115","volume":"37","author":"J Lin","year":"1991","unstructured":"Lin, J.: Divergence measures based on the shannon entropy. IEEE Trans. Inf. Theory 37(1), 145\u2013151 (1991)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"47_CR20","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":"47_CR21","unstructured":"van Miltenburg, E.: Stereotyping and bias in the Flickr30k dataset. In: Workshop on Multimodal Corpora: Computer Vision and Language Processing (2016)"},{"key":"47_CR22","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2930\u20132939. IEEE (2016)","DOI":"10.1109\/CVPR.2016.320"},{"key":"47_CR23","unstructured":"President of the United Search Engine Optimization, Podesta, J.: Big data: seizing opportunities, preserving values. White House, Executive Office of the President (2014)"},{"key":"47_CR24","unstructured":"Quadrianto, N., Petterson, J., Smola, A.J.: Distribution matching for transduction. In: Advances in Neural Information Processing Systems (NIPS), pp. 1500\u20131508 (2009)"},{"key":"47_CR25","unstructured":"Quadrianto, N., Sharmanska, V.: Recycling privileged learning and distribution matching for fairness. In: Advances in Neural Information Processing Systems (NIPS), pp. 677\u2013688 (2017)"},{"key":"47_CR26","doi-asserted-by":"crossref","unstructured":"Ramanishka, V., Das, A., Zhang, J., Saenko, K.: Top-down visual saliency guided by captions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, p. 7 (2017)","DOI":"10.1109\/CVPR.2017.334"},{"key":"47_CR27","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: Why should i trust you?: Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135\u20131144. ACM (2016)","DOI":"10.1145\/2939672.2939778"},{"key":"47_CR28","doi-asserted-by":"crossref","unstructured":"Ross, A.S., Hughes, M.C., Doshi-Velez, F.: Right for the right reasons: training differentiable models by constraining their explanations. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) (2017)","DOI":"10.24963\/ijcai.2017\/371"},{"key":"47_CR29","unstructured":"Ryu, H.J., Adam, H., Mitchell, M.: Inclusivefacenet: Improving face attribute detection with race and gender diversity. In: Workshop on Fairness, Accountability, and Transparency in Machine Learning (FAT\/ML) (2018)"},{"key":"47_CR30","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"47_CR31","unstructured":"Stock, P., Cisse, M.: ConvNets and imageNet beyond accuracy: explanations, bias detection, adversarial examples and model criticism. arXiv preprint arXiv:1711.11443 (2017)"},{"key":"47_CR32","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"47_CR33","unstructured":"Tan, S., Caruana, R., Hooker, G., Lou, Y.: Detecting bias in black-box models using transparent model distillation. In: AAAI\/ACM Conference on Artificial Intelligence, Ethics, and Society (2018)"},{"key":"47_CR34","unstructured":"Torralba, A.: Contextual modulation of target saliency. In: Advances in Neural Information Processing Systems (NIPS), pp. 1303\u20131310 (2002)"},{"key":"47_CR35","doi-asserted-by":"crossref","unstructured":"Torralba, A., Sinha, P.: Statistical context priming for object detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), vol. 1, pp. 763\u2013770. IEEE (2001)","DOI":"10.1109\/ICCV.2001.937604"},{"key":"47_CR36","doi-asserted-by":"crossref","unstructured":"Tzeng, E., Hoffman, J., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 4068\u20134076. IEEE (2015)","DOI":"10.1109\/ICCV.2015.463"},{"key":"47_CR37","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3156\u20133164. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"47_CR38","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5288\u20135296. IEEE (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"47_CR39","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 2048\u20132057 (2015)"},{"key":"47_CR40","unstructured":"Yan, X., Yan, L.: Gender classification of weblog authors. In: AAAI Spring Symposium: computational Approaches to Analyzing Weblogs, pp. 228\u2013230. Palo Alto (2006)"},{"key":"47_CR41","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Computat. Linguist. (TACL) 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Computat. Linguist. (TACL)"},{"key":"47_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"47_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, B.H., Lemoine, B., Mitchell, M.: Mitigating unwanted biases with adversarial learning. In: AAAI\/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES) (2018)","DOI":"10.1145\/3278721.3278779"},{"key":"47_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1007\/978-3-319-46493-0_33","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Zhang","year":"2016","unstructured":"Zhang, J., Lin, Z., Brandt, J., Shen, X., Sclaroff, S.: Top-down neural attention by excitation backprop. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 543\u2013559. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_33"},{"key":"47_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, K., Tan, L., Li, Z., Qiao, Y.: Gender and smile classification using deep convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), pp. 34\u201338 (2016)","DOI":"10.1109\/CVPRW.2016.97"},{"key":"47_CR46","unstructured":"Zhang, X., Yu, F.X., Chang, S.F., Wang, S.: Deep transfer network: unsupervised domain adaptation. arXiv preprint arXiv:1503.00591 (2015)"},{"key":"47_CR47","doi-asserted-by":"crossref","unstructured":"Zhao, J., Wang, T., Yatskar, M., Ordonez, V., Chang, K.W.: Men also like shopping: reducing gender bias amplification using corpus-level constraints. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (2017)","DOI":"10.18653\/v1\/D17-1323"},{"key":"47_CR48","unstructured":"Zintgraf, L.M., Cohen, T.S., Adel, T., Welling, M.: Visualizing deep neural network decisions: prediction difference analysis. In: Proceedings of the International Conference on Learning Representations (ICLR) (2017)"}],"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\/978-3-030-01219-9_47","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:47:40Z","timestamp":1775242060000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01219-9_47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012182","9783030012199"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01219-9_47","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":"7 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"}]}}