{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T09:19:54Z","timestamp":1742980794540,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030110239"},{"type":"electronic","value":"9783030110246"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-11024-6_42","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T04:29:27Z","timestamp":1548304167000},"page":"545-559","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Structured Listwise Approach to Learning to Rank for Image Tagging"],"prefix":"10.1007","author":[{"given":"Jorge","family":"S\u00e1nchez","sequence":"first","affiliation":[]},{"given":"Franco","family":"Luque","sequence":"additional","affiliation":[]},{"given":"Leandro","family":"Lichtensztein","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,1,23]]},"reference":[{"key":"42_CR1","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: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"11","key":"42_CR2","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"key":"42_CR3","doi-asserted-by":"crossref","unstructured":"Chua, T.S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.: NUS-WIDE: a real-world web image database from National University of Singapore. In: Proceedings of the ACM International Conference on Image and Video Retrieval, p. 48. ACM (2009)","DOI":"10.1145\/1646396.1646452"},{"key":"42_CR4","doi-asserted-by":"crossref","unstructured":"Huiskes, M.J., Lew, M.S.: The MIR Flickr retrieval evaluation. In: Proceedings of the 1st ACM International Conference on Multimedia Information Retrieval, pp. 39\u201343. ACM (2008)","DOI":"10.1145\/1460096.1460104"},{"key":"42_CR5","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":"42_CR6","doi-asserted-by":"crossref","unstructured":"Verbeek, J., Guillaumin, M., Mensink, T., Schmid, C.: Image annotation with TagProp on the MIRFlickr set. In: Proceedings of the International Conference on Multimedia Information Retrieval, pp. 537\u2013546. ACM (2010)","DOI":"10.1145\/1743384.1743476"},{"key":"42_CR7","doi-asserted-by":"crossref","unstructured":"Wu, P., Hoi, S.C.H., Zhao, P., He, Y.: Mining social images with distance metric learning for automated image tagging. In: Proceedings of the Fourth ACM International Conference on Web Search and Data Mining, pp. 197\u2013206. ACM (2011)","DOI":"10.1145\/1935826.1935865"},{"issue":"7","key":"42_CR8","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.1109\/TMM.2009.2030598","volume":"11","author":"X Li","year":"2009","unstructured":"Li, X., Snoek, C.G., Worring, M.: Learning social tag relevance by neighbor voting. IEEE Trans. Multimedia 11(7), 1310\u20131322 (2009)","journal-title":"IEEE Trans. Multimedia"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Zhu, G., Yan, S., Ma, Y.: Image tag refinement towards low-rank, content-tag prior and error sparsity. In: Proceedings of the 18th ACM International Conference on Multimedia, pp. 461\u2013470. ACM (2010)","DOI":"10.1145\/1873951.1874028"},{"issue":"5","key":"42_CR10","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1109\/TMM.2010.2051360","volume":"12","author":"H Ma","year":"2010","unstructured":"Ma, H., Zhu, J., Lyu, M.R.T., King, I.: Bridging the semantic gap between image contents and tags. IEEE Trans. Multimedia 12(5), 462\u2013473 (2010)","journal-title":"IEEE Trans. Multimedia"},{"issue":"1","key":"42_CR11","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1109\/TIP.2012.2202676","volume":"22","author":"Y Gao","year":"2013","unstructured":"Gao, Y., Wang, M., Zha, Z.J., Shen, J., Li, X., Wu, X.: Visual-textual joint relevance learning for tag-based social image search. IEEE Trans. Image Process. 22(1), 363\u2013376 (2013)","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"42_CR12","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1145\/2906152","volume":"49","author":"X Li","year":"2016","unstructured":"Li, X., Uricchio, T., Ballan, L., Bertini, M., Snoek, C.G., Bimbo, A.D.: Socializing the semantic gap: a comparative survey on image tag assignment, refinement, and retrieval. ACM Comput. Surv. (CSUR) 49(1), 14 (2016)","journal-title":"ACM Comput. Surv. (CSUR)"},{"issue":"3","key":"42_CR13","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1109\/TPAMI.2013.140","volume":"36","author":"CH Lampert","year":"2014","unstructured":"Lampert, C.H., Nickisch, H., Harmeling, S.: Attribute-based classification for zero-shot visual object categorization. IEEE Trans. Pattern Anal. Mach. Intell. 36(3), 453\u2013465 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"42_CR14","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Stark, M., Schiele, B.: Evaluating knowledge transfer and zero-shot learning in a large-scale setting. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1641\u20131648. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995627"},{"key":"42_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-319-46475-6_4","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W-L Chao","year":"2016","unstructured":"Chao, W.-L., Changpinyo, S., Gong, B., Sha, F.: An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 52\u201368. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_4"},{"key":"42_CR16","doi-asserted-by":"crossref","unstructured":"Akata, Z., Reed, S., Walter, D., Lee, H., Schiele, B.: Evaluation of output embeddings for fine-grained image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2927\u20132936 (2015)","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"42_CR17","doi-asserted-by":"crossref","unstructured":"Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. arXiv preprint arXiv:1707.00600 (2017)","DOI":"10.1109\/CVPR.2017.328"},{"issue":"1","key":"42_CR18","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1109\/MSP.2017.2763441","volume":"35","author":"Y Fu","year":"2018","unstructured":"Fu, Y., Xiang, T., Jiang, Y.G., Xue, X., Sigal, L., Gong, S.: Recent advances in zero-shot recognition: toward data-efficient understanding of visual content. IEEE Signal Process. Mag. 35(1), 112\u2013125 (2018)","journal-title":"IEEE Signal Process. Mag."},{"key":"42_CR19","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"42_CR20","doi-asserted-by":"crossref","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, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"7","key":"42_CR21","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.1109\/TPAMI.2015.2487986","volume":"38","author":"Z Akata","year":"2016","unstructured":"Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label-embedding for image classification. IEEE Trans. Pattern Anal. Mach. Intell. 38(7), 1425\u20131438 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"42_CR22","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"42_CR23","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111\u20133119 (2013)"},{"key":"42_CR24","doi-asserted-by":"crossref","unstructured":"Loeff, N., Alm, C.O., Forsyth, D.A.: Discriminating image senses by clustering with multimodal features. In: Proceedings of the COLING\/ACL on Main Conference Poster Sessions, pp. 547\u2013554. Association for Computational Linguistics (2006)","DOI":"10.3115\/1273073.1273144"},{"key":"42_CR25","doi-asserted-by":"crossref","unstructured":"Lazaridou, A., Bruni, E., Baroni, M.: Is this a wampimuk? Cross-modal mapping between distributional semantics and the visual world. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), vol. 1, pp. 1403\u20131414 (2014)","DOI":"10.3115\/v1\/P14-1132"},{"key":"42_CR26","doi-asserted-by":"crossref","unstructured":"Lazaridou, A., Pham, N.T., Baroni, M.: Combining language and vision with a multimodal skip-gram model. arXiv preprint arXiv:1501.02598 (2015)","DOI":"10.3115\/v1\/N15-1016"},{"issue":"11","key":"42_CR27","doi-asserted-by":"publisher","first-page":"2284","DOI":"10.1109\/TPAMI.2016.2635138","volume":"39","author":"C Silberer","year":"2017","unstructured":"Silberer, C., Ferrari, V., Lapata, M.: Visually grounded meaning representations. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2284\u20132297 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"42_CR28","doi-asserted-by":"crossref","unstructured":"Xia, F., Liu, T.Y., Wang, J., Zhang, W., Li, H.: Listwise approach to learning to rank: theory and algorithm. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1192\u20131199. ACM (2008)","DOI":"10.1145\/1390156.1390306"},{"key":"42_CR29","unstructured":"Rashtchian, C., Young, P., Hodosh, M., Hockenmaier, J.: Collecting image annotations using Amazon\u2019s Mechanical Turk. In: Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon\u2019s Mechanical Turk, pp. 139\u2013147. Association for Computational Linguistics (2010)"},{"issue":"2","key":"42_CR30","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"42_CR31","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"42_CR32","doi-asserted-by":"crossref","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. arXiv preprint arXiv:1607.04606 (2016)","DOI":"10.1162\/tacl_a_00051"},{"key":"42_CR33","unstructured":"Honnibal, M., Montani, I.: spaCy 2: natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing (2017, to appear)"},{"key":"42_CR34","unstructured":"Tolias, G., Sicre, R., J\u00e9gou, H.: Particular object retrieval with integral max-pooling of CNN activations. arXiv preprint arXiv:1511.05879 (2015)"},{"key":"42_CR35","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS-W (2017)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11024-6_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T01:06:37Z","timestamp":1674349597000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-11024-6_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030110239","9783030110246"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11024-6_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"23 January 2019","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"}]}}