{"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":1783529881624,"version":"3.55.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030695347","type":"print"},{"value":"9783030695354","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","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":[[2021]]},"DOI":"10.1007\/978-3-030-69535-4_10","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T15:13:11Z","timestamp":1614179591000},"page":"155-170","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["Synthesizing the Unseen for Zero-Shot Object Detection"],"prefix":"10.1007","author":[{"given":"Nasir","family":"Hayat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Munawar","family":"Hayat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shafin","family":"Rahman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salman","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syed Waqas","family":"Zamir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"10_CR1","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, pp. 91\u201399 (2015)"},{"key":"10_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1007\/978-3-030-20887-5_34","volume-title":"Computer Vision \u2013 ACCV 2018","author":"S Rahman","year":"2019","unstructured":"Rahman, S., Khan, S., Porikli, F.: Zero-shot object detection: learning to simultaneously recognize and localize novel concepts. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11361, pp. 547\u2013563. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20887-5_34"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Bansal, A., Sikka, K., Sharma, G., Chellappa, R., Divakaran, A.: Zero-shot object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 384\u2013400 (2018)","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"10_CR4","unstructured":"Demirel, B., Cinbis, R.G., Ikizler-Cinbis, N.: Zero-shot object detection by hybrid region embedding. arXiv preprint arXiv:1805.06157 (2018)"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Li, Z., Yao, L., Zhang, X., Wang, X., Kanhere, S., Zhang, H.: Zero-shot object detection with textual descriptions. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8690\u20138697 (2019)","DOI":"10.1609\/aaai.v33i01.33018690"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Hayat, M., Khan, S., Zamir, S.W., Shen, J., Shao, L.: Gaussian affinity for max-margin class imbalanced learning. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00657"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Khan, S., Hayat, M., Zamir, S.W., Shen, J., Shao, L.: Striking the right balance with uncertainty. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00019"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, L., Xiang, T., Gong, S.: Learning a deep embedding model for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2021\u20132030 (2017)","DOI":"10.1109\/CVPR.2017.321"},{"key":"10_CR9","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 4247\u20134255 (2015)","DOI":"10.1109\/ICCV.2015.483"},{"key":"10_CR10","unstructured":"Annadani, Y., Biswas, S.: Preserving semantic relations for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7603\u20137612 (2018)"},{"key":"10_CR11","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1109\/TPAMI.2013.140","volume":"36","author":"CH Lampert","year":"2013","unstructured":"Lampert, C.H., Nickisch, H., Harmeling, S.: Attribute-based classification for zero-shot visual object categorization. IEEE Trans. Pattern Anal. Mach. Intell. 36, 453\u2013465 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR12","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":"10_CR13","unstructured":"Dinu, G., Lazaridou, A., Baroni, M.: Improving zero-shot learning by mitigating the hubness problem. arXiv preprint arXiv:1412.6568 (2014)"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, H., Xiao, J., Liu, W., Chang, S.F.: Zero-shot visual recognition using semantics-preserving adversarial embedding networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1043\u20131052 (2018)","DOI":"10.1109\/CVPR.2018.00115"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Xian, Y., Lorenz, T., Schiele, B., Akata, Z.: Feature generating networks for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5542\u20135551 (2018)","DOI":"10.1109\/CVPR.2018.00581"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Elhoseiny, M., Liu, B., Peng, X., Elgammal, A.: A generative adversarial approach for zero-shot learning from noisy texts. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1004\u20131013 (2018)","DOI":"10.1109\/CVPR.2018.00111"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Khan, S.H., Hayat, M., Barnes, N.: Adversarial training of variational auto-encoders for high fidelity image generation. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (2018)","DOI":"10.1109\/WACV.2018.00148"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Zhao, S., Gao, C., Shao, Y., Li, L., Yu, C., Ji, Z., Sang, N.: GTNet: generative transfer network for zero-shot object detection. arXiv arXiv:2001 (2020)","DOI":"10.1609\/aaai.v34i07.6996"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Rahman, S., Khan, S., Barnes, N.: Polarity loss for zero-shot object detection. arXiv preprint arXiv:1811.08982 (2018)","DOI":"10.1109\/ICCV.2019.00618"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, L., Xiang, T., Gong, S.: Learning a deep embedding model for zero-shot learning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.321"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: 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":"10_CR22","doi-asserted-by":"crossref","unstructured":"Joulin, A., Grave, \u00c9., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient text classification. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pp. 427\u2013431 (2017)","DOI":"10.18653\/v1\/E17-2068"},{"key":"10_CR23","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Advances in Neural Information Processing Systems, pp. 5767\u20135777 (2017)"},{"key":"10_CR24","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems, pp. 2234\u20132242 (2016)"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Mao, Q., Lee, H.Y., Tseng, H.Y., Ma, S., Yang, M.H.: Mode seeking generative adversarial networks for diverse image synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1429\u20131437 (2019)","DOI":"10.1109\/CVPR.2019.00152"},{"key":"10_CR26","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"},{"issue":"3","key":"10_CR27","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. Int. J. Comp. Vis. 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comp. Vis."},{"key":"10_CR28","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, 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"10_CR29","unstructured":"Chen, K., et al.: MMDetection: open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"10_CR30","unstructured":"Mikolov, T., Grave, E., Bojanowski, P., Puhrsch, C., Joulin, A.: Advances in pre-training distributed word representations. In: Proceedings of the International Conference on Language Resources and Evaluation (LREC 2018) (2018)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69535-4_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T15:37:44Z","timestamp":1614181064000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69535-4_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695347","9783030695354"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69535-4_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","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":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","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":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","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":"254","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":"33% - 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":"3","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.","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)"}}]}}