{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:58:01Z","timestamp":1783529881206,"version":"3.55.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030208868","type":"print"},{"value":"9783030208875","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-20887-5_34","type":"book-chapter","created":{"date-parts":[[2019,5,27]],"date-time":"2019-05-27T08:03:59Z","timestamp":1558944239000},"page":"547-563","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":70,"title":["Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7169-0318","authenticated-orcid":false,"given":"Shafin","family":"Rahman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9502-1749","authenticated-orcid":false,"given":"Salman","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1520-4466","authenticated-orcid":false,"given":"Fatih","family":"Porikli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,5,28]]},"reference":[{"key":"34_CR1","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: CVPR, 07\u201312 June 2015, pp. 2927\u20132936 (2015). \n                      https:\/\/doi.org\/10.1109\/CVPR.2015.7298911","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Akata, Z., Malinowski, M., Fritz, M., Schiele, B.: Multi-cue zero-shot learning with strong supervision. In: CVPR, June 2016","DOI":"10.1109\/CVPR.2016.14"},{"issue":"7","key":"34_CR3","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). \n                      https:\/\/doi.org\/10.1109\/TPAMI.2015.2487986","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR4","unstructured":"Changpinyo, S., Chao, W.L., Gong, B., Sha, F.: Synthesized classifiers for zero-shot learning. In: CVPR, 2016 January, pp. 5327\u20135336 (2016)"},{"key":"34_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1007\/978-3-319-10590-1_4","volume-title":"Computer Vision \u2013 ECCV 2014","author":"J Deng","year":"2014","unstructured":"Deng, J., et al.: Large-scale object classification using label relation graphs. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 48\u201364. Springer, Cham (2014). \n                      https:\/\/doi.org\/10.1007\/978-3-319-10590-1_4"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Deutsch, S., Kolouri, S., Kim, K., Owechko, Y., Soatto, S.: Zero shot learning via multi-scale manifold regularization. In: CVPR, July 2017","DOI":"10.1109\/CVPR.2017.562"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: CVPR, pp. 1778\u20131785. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"34_CR8","unstructured":"Frome, A., et al.: DeVISE: a deep visual-semantic embedding model. In: Burges, C.J.C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K.Q. (eds.) NIPS, pp. 2121\u20132129. Curran Associates, Inc. (2013)"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Fu, Y., Yang, Y., Hospedales, T., Xiang, T., Gong, S.: Transductive multi-label zero-shot learning. arXiv preprint \n                      arXiv:1503.07790\n                      \n                     (2015)","DOI":"10.5244\/C.28.7"},{"issue":"99","key":"34_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2017.2737007","volume":"PP","author":"Z Fu","year":"2017","unstructured":"Fu, Z., Xiang, T., Kodirov, E., Gong, S.: Zero-shot learning on semantic class prototype graph. IEEE Trans. Pattern Anal. Mach. Intell. PP(99), 1 (2017). \n                      https:\/\/doi.org\/10.1109\/TPAMI.2017.2737007","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR11","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition, 2016 January, pp. 770\u2013778 (2016). Cited by 107"},{"key":"34_CR12","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. arXiv preprint \n                      arXiv:1605.06409\n                      \n                     (2016)"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Kodirov, E., Xiang, T., Fu, Z., Gong, S.: Unsupervised domain adaptation for zero-shot learning. In: ICCV, December 2015","DOI":"10.1109\/ICCV.2015.282"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Kodirov, E., Xiang, T., Gong, S.: Semantic autoencoder for zero-shot learning. In: CVPR, July 2017","DOI":"10.1109\/CVPR.2017.473"},{"issue":"3","key":"34_CR15","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). \n                      https:\/\/doi.org\/10.1109\/TPAMI.2013.140","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR16","doi-asserted-by":"publisher","unstructured":"Lampert, C., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: CVPR Workshops, pp. 951\u2013958 (2009). \n                      https:\/\/doi.org\/10.1109\/CVPRW.2009.5206594","DOI":"10.1109\/CVPRW.2009.5206594"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Lei Ba, J., Swersky, K., Fidler, S., et al.: Predicting deep zero-shot convolutional neural networks using textual descriptions. In: CVPR, pp. 4247\u20134255 (2015)","DOI":"10.1109\/ICCV.2015.483"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, D., Hu, H., Lin, Y., Zhuang, Y.: Zero-shot recognition using dual visual-semantic mapping paths. In: CVPR, July 2017","DOI":"10.1109\/CVPR.2017.553"},{"key":"34_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"34_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1007\/978-3-319-46454-1_44","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Bucher","year":"2016","unstructured":"Bucher, M., Herbin, S., Jurie, F.: Improving semantic embedding consistency by metric learning for zero-shot classiffication. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 730\u2013746. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46454-1_44"},{"key":"34_CR21","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Burges, C.J.C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K.Q. (eds.) NIPS, pp. 3111\u20133119. Curran Associates, Inc. (2013)"},{"issue":"11","key":"34_CR22","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":"34_CR23","doi-asserted-by":"crossref","unstructured":"Morgado, P., Vasconcelos, N.: Semantically consistent regularization for zero-shot recognition. In: CVPR, July 2017","DOI":"10.1109\/CVPR.2017.220"},{"key":"34_CR24","unstructured":"Norouzi, M., et al.: Zero-shot learning by convex combination of semantic embeddings. In: ICLR (2014)"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: EMNLP, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Rahman, S., Khan, S.H., Porikli, F.: A unified approach for conventional zero-shot, generalized zero-shot and few-shot learning. arXiv preprint \n                      arXiv:1706.08653\n                      \n                     (2017)","DOI":"10.1109\/TIP.2018.2861573"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.690"},{"issue":"6","key":"34_CR28","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017). \n                      https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR29","unstructured":"Romera-Paredes, B., Torr, P.: An embarrassingly simple approach to zero-shot learning. In: ICML, pp. 2152\u20132161 (2015)"},{"issue":"3","key":"34_CR30","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(3), 211\u2013252 (2015). \n                      https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"IJCV"},{"key":"34_CR31","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint \n                      arXiv:1409.1556\n                      \n                     (2014)"},{"key":"34_CR32","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":"34_CR33","doi-asserted-by":"crossref","unstructured":"Xian, Y., Akata, Z., Sharma, G., Nguyen, Q., Hein, M., Schiele, B.: Latent embeddings for zero-shot classification. In: CVPR, June 2016","DOI":"10.1109\/CVPR.2016.15"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"Xian, Y., Schiele, B., Akata, Z.: Zero-shot learning - the good, the bad and the ugly. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.328"},{"key":"34_CR35","doi-asserted-by":"crossref","unstructured":"Xu, X., Shen, F., Yang, Y., Zhang, D., Shen, H.T., Song, J.: Matrix tri-factorization with manifold regularizations for zero-shot learning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.217"},{"key":"34_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, L., Xiang, T., Gong, S.: Learning a deep embedding model for zero-shot learning. In: CVPR, July 2017","DOI":"10.1109\/CVPR.2017.321"},{"key":"34_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Saligrama, V.: Zero-shot learning via semantic similarity embedding. In: ICCV, December 2015","DOI":"10.1109\/ICCV.2015.474"},{"key":"34_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Saligrama, V.: Zero-shot learning via joint latent similarity embedding. In: CVPR, June 2016","DOI":"10.1109\/CVPR.2016.649"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20887-5_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,27]],"date-time":"2019-05-27T08:23:19Z","timestamp":1558945399000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20887-5_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208868","9783030208875"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20887-5_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"28 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","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"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"979","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"28% - 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"}},{"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"}},{"value":"2.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}