{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T16:52:24Z","timestamp":1767891144117,"version":"3.49.0"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T00:00:00Z","timestamp":1618790400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T00:00:00Z","timestamp":1618790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Research Grants Council of the Hong Kong, ECS Grant","award":["CityU 21209119"],"award-info":[{"award-number":["CityU 21209119"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1007\/s11263-021-01451-1","type":"journal-article","created":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T04:02:54Z","timestamp":1618804974000},"page":"1893-1909","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Visual Structure Constraint for Transductive Zero-Shot Learning in the Wild"],"prefix":"10.1007","volume":"129","author":[{"given":"Ziyu","family":"Wan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongdong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7014-5377","authenticated-orcid":false,"given":"Jing","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,4,19]]},"reference":[{"key":"1451_CR1","doi-asserted-by":"crossref","unstructured":"Akata, Z., Perronnin, F., Harchaoui, Z., & Schmid, C. (2013). Label-embedding for attribute-based classification. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 819-826).","DOI":"10.1109\/CVPR.2013.111"},{"key":"1451_CR2","doi-asserted-by":"crossref","unstructured":"Akata, Z., Perronnin, F., Harchaoui, Z., & Schmid, C. (2016). Label-embedding for image classification. TPAMI.","DOI":"10.1109\/TPAMI.2015.2487986"},{"key":"1451_CR3","doi-asserted-by":"crossref","unstructured":"Akata, Z., Reed, S., Walter, D., Lee, H., & Schiele, B. (2015). Evaluation of output embeddings for fine-grained image classification. In: CVPR.","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"1451_CR4","unstructured":"Annadani, Y., & Biswas, S. (2018). Preserving semantic relations for zero-shot learning.In: CVPR."},{"key":"1451_CR5","unstructured":"Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein gan. arXiv preprint arXiv:1701.07875."},{"key":"1451_CR6","doi-asserted-by":"crossref","unstructured":"Chang, J., Wang, L., Meng, G., Xiang, S., & Pan, C. (2017). Deep adaptive image clustering. In: Proceedings of the IEEE international conference on computer vision, pp. 5879\u20135887.","DOI":"10.1109\/ICCV.2017.626"},{"key":"1451_CR7","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Chao, W.L., Gong, B., & Sha, F. (2016). Synthesized classifiers for zero-shot learning.In: CVPR.","DOI":"10.1109\/CVPR.2016.575"},{"key":"1451_CR8","unstructured":"Changpinyo, S., Chao, W.L., Gong, B., & Sha, F. (2018). Classifier and exemplar synthesis for zero-shot learning. arXiv preprint arXiv:1812.06423."},{"key":"1451_CR9","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Chao, W.L., & Sha, F. (2017). Predicting visual exemplars of unseen classes for zero-shot learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3476\u20133485.","DOI":"10.1109\/ICCV.2017.376"},{"key":"1451_CR10","unstructured":"Cuturi, M. (2013). Sinkhorn distances: Lightspeed computation of optimal transport. In: Advances in neural information processing systems, pp. 2292\u20132300."},{"key":"1451_CR11","doi-asserted-by":"crossref","unstructured":"Elhoseiny, M., Saleh, B., & Elgammal, A. (2013). Write a classifier: Zero-shot learning using purely textual descriptions. In: ICCV.","DOI":"10.1109\/ICCV.2013.321"},{"key":"1451_CR12","doi-asserted-by":"crossref","unstructured":"Fan, H., Su, H., & Guibas, L. (2017). A point set generation network for 3d object reconstruction from a single image. In: CVPR.","DOI":"10.1109\/CVPR.2017.264"},{"key":"1451_CR13","doi-asserted-by":"crossref","unstructured":"Farhadi, A., Endres, I., Hoiem, D., & Forsyth, D. (2009). Describing objects by their attributes. In: CVPR.","DOI":"10.1109\/CVPRW.2009.5206772"},{"key":"1451_CR14","doi-asserted-by":"crossref","unstructured":"Felix, R., Kumar, V.B., Reid, I., & Carneiro, G. (2018). Multi-modal cycle-consistent generalized zero-shot learning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 21\u201337.","DOI":"10.1007\/978-3-030-01231-1_2"},{"key":"1451_CR15","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., & Mikolov, T., et\u00a0al. (2013). Devise: A deep visual-semantic embedding model. In: NIPS."},{"key":"1451_CR16","doi-asserted-by":"crossref","unstructured":"Fu, Y., Hospedales, T.M., Xiang, T., Fu, Z., & Gong, S. (2014). Transductive multi-view embedding for zero-shot recognition and annotation. In: ECCV.","DOI":"10.1007\/978-3-319-10605-2_38"},{"key":"1451_CR17","doi-asserted-by":"crossref","unstructured":"Fu, Y., Hospedales, T.M., Xiang, T., & Gong, S. (2015). Transductive multi-view zero-shot learning. TPAMI.","DOI":"10.5244\/C.28.7"},{"key":"1451_CR18","doi-asserted-by":"crossref","unstructured":"Fu, Y., & Sigal, L. (2016). Semi-supervised vocabulary-informed learning. In: CVPR.","DOI":"10.1109\/CVPR.2016.576"},{"key":"1451_CR19","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. In: Advances in neural information processing systems, pp. 2672\u20132680."},{"key":"1451_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1451_CR21","doi-asserted-by":"crossref","unstructured":"Huang, H., Wang, C., Yu, P.S., & Wang, C.D. (2019). Generative dual adversarial network for generalized zero-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 801\u2013810.","DOI":"10.1109\/CVPR.2019.00089"},{"key":"1451_CR22","unstructured":"Kingma, D.P., & Welling, M. (2013). Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114."},{"key":"1451_CR23","doi-asserted-by":"crossref","unstructured":"Kodirov, E., Xiang, T., Fu, Z., & Gong, S. (2015). Unsupervised domain adaptation for zero-shot learning.In: ICCV.","DOI":"10.1109\/ICCV.2015.282"},{"key":"1451_CR24","doi-asserted-by":"crossref","unstructured":"Kodirov, E., Xiang, T., & Gong, S. (2017). Semantic autoencoder for zero-shot learning. In: CVPR.","DOI":"10.1109\/CVPR.2017.473"},{"key":"1451_CR25","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Nickisch, H., & Harmeling, S. (2009). Learning to detect unseen object classes by between-class attribute transfer. In: CVPR.","DOI":"10.1109\/CVPRW.2009.5206594"},{"key":"1451_CR26","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Nickisch, H., & Harmeling, S. (2014). Attribute-based classification for zero-shot visual object categorization. TPAMI.","DOI":"10.1109\/TPAMI.2013.140"},{"key":"1451_CR27","doi-asserted-by":"crossref","unstructured":"Lei\u00a0Ba, J., Swersky, K., & Fidler, S., et\u00a0al. (2015). Predicting deep zero-shot convolutional neural networks using textual descriptions. In: ICCV.","DOI":"10.1109\/ICCV.2015.483"},{"key":"1451_CR28","doi-asserted-by":"crossref","unstructured":"Li, J., Jing, M., Lu, K., Ding, Z., Zhu, L., & Huang, Z. (2019). Leveraging the invariant side of generative zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7402\u20137411.","DOI":"10.1109\/CVPR.2019.00758"},{"key":"1451_CR29","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, D., Hu, H., Lin, Y., & Zhuang, Y. (2017). Zero-shot recognition using dual visual-semantic mapping paths. In: CVPR.","DOI":"10.1109\/CVPR.2017.553"},{"key":"1451_CR30","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, J., Zhang, J., & Huang, K. (2018). Discriminative learning of latent features for zero-shot recognition. In: CVPR.","DOI":"10.1109\/CVPR.2018.00779"},{"key":"1451_CR31","unstructured":"Liu, S., Long, M., Wang, J., & Jordan, M.I. (2018). Generalized zero-shot learning with deep calibration network.In: Advances in Neural Information Processing Systems, pp. 2005\u20132015."},{"issue":"10","key":"1451_CR32","doi-asserted-by":"publisher","first-page":"2498","DOI":"10.1109\/TPAMI.2017.2762295","volume":"40","author":"Y Long","year":"2017","unstructured":"Long, Y., Liu, L., Shen, F., Shao, L., & Li, X. (2017). Zero-shot learning using synthesised unseen visual data with diffusion regularisation. IEEE transactions on pattern analysis and machine intelligence, 40(10), 2498\u20132512.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"1451_CR33","unstructured":"Lu, Y. (2016). Unsupervised learning on neural network outputs: with application in zero-shot learning. IJCAI."},{"key":"1451_CR34","doi-asserted-by":"crossref","unstructured":"Miller, G. A. (1995). Wordnet: a lexical database for english. Communications of the ACM.","DOI":"10.3115\/1075812.1075938"},{"key":"1451_CR35","doi-asserted-by":"crossref","unstructured":"Morgado, P., & Vasconcelos, N. (2017). Semantically consistent regularization for zero-shot recognition. In: CVPR.","DOI":"10.1109\/CVPR.2017.220"},{"key":"1451_CR36","unstructured":"Norouzi, M., Mikolov, T., Bengio, S., Singer, Y., Shlens, J., Frome, A., Corrado, G.S., & Dean, J. (2014). Zero-shot learning by convex combination of semantic embeddings. ICLR."},{"key":"1451_CR37","doi-asserted-by":"crossref","unstructured":"Patterson, G., Xu, C., Su, H., & Hays, J. (2014). The sun attribute database: Beyond categories for deeper scene understanding. IJCV.","DOI":"10.1007\/s11263-013-0695-z"},{"key":"1451_CR38","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., & Manning, C.D. (2014). Glove: Global vectors for word representation. In: EMNLP.","DOI":"10.3115\/v1\/D14-1162"},{"key":"1451_CR39","doi-asserted-by":"crossref","unstructured":"Radovanovi\u0107, M., Nanopoulos, A., & Ivanovi\u0107, M. (2010). Hubs in space: Popular nearest neighbors in high-dimensional data.JMLR.","DOI":"10.1145\/1553374.1553485"},{"key":"1451_CR40","doi-asserted-by":"crossref","unstructured":"Reed, S., Akata, Z., Lee, H., & Schiele, B. (2016). Learning deep representations of fine-grained visual descriptions. In: CVPR.","DOI":"10.1109\/CVPR.2016.13"},{"key":"1451_CR41","unstructured":"Romera-Paredes, B., & Torr, P. (2015). An embarrassingly simple approach to zero-shot learning. In: ICML."},{"key":"1451_CR42","doi-asserted-by":"crossref","unstructured":"Shigeto, Y., Suzuki, I., Hara, K., Shimbo, M., & Matsumoto, Y. (2015). Ridge regression, hubness, and zero-shot learning.In: ECML.","DOI":"10.1007\/978-3-319-23528-8_9"},{"key":"1451_CR43","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. CoRR."},{"key":"1451_CR44","doi-asserted-by":"crossref","unstructured":"Song, J., Shen, C., Yang, Y., Liu, Y., & Song, M. (2018). Transductive unbiased embedding for zero-shot learning.In: CVPR.","DOI":"10.1109\/CVPR.2018.00113"},{"key":"1451_CR45","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions.In: CVPR.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1451_CR46","doi-asserted-by":"crossref","unstructured":"Vyas, M.R., Venkateswara, H., & Panchanathan, S. (2020). Leveraging seen and unseen semantic relationships for generative zero-shot learning. arXiv preprint arXiv:2007.09549.","DOI":"10.1007\/978-3-030-58577-8_5"},{"key":"1451_CR47","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., & Belongie, S. (2011). The caltech-ucsd birds-200-2011 dataset."},{"key":"1451_CR48","first-page":"9972","volume":"32","author":"Z Wan","year":"2019","unstructured":"Wan, Z., Chen, D., Li, Y., Yan, X., Zhang, J., Yu, Y., et al. (2019). Transductive zero-shot learning with visual structure constraint. Advances in Neural Information Processing Systems, 32, 9972\u20139982.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1451_CR49","doi-asserted-by":"crossref","unstructured":"Wang, W., Pu, Y., Verma, V.K., Fan, K., Zhang, Y., Chen, C., Rai, P., & Carin, L. (2018). Zero-shot learning via class-conditioned deep generative models. AAAI.","DOI":"10.1609\/aaai.v32i1.11600"},{"key":"1451_CR50","doi-asserted-by":"crossref","unstructured":"Wang, X., Ye, Y., & Gupta, A. (2018). Zero-shot recognition via semantic embeddings and knowledge graphs. In: CVPR.","DOI":"10.1109\/CVPR.2018.00717"},{"key":"1451_CR51","doi-asserted-by":"crossref","unstructured":"Xian, Y., Lampert, C.H., Schiele, B., & Akata, Z. (2018). Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. TPAMI.","DOI":"10.1109\/CVPR.2017.328"},{"key":"1451_CR52","doi-asserted-by":"crossref","unstructured":"Xian, Y., Lorenz, T., Schiele, B., & Akata, Z. (2018). Feature generating networks for zero-shot learning. In: CVPR.","DOI":"10.1109\/CVPR.2018.00581"},{"key":"1451_CR53","doi-asserted-by":"crossref","unstructured":"Xian, Y., Sharma, S., Schiele, B., & Akata, Z. (2019). f-vaegan-d2: A feature generating framework for any-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10275\u201310284.","DOI":"10.1109\/CVPR.2019.01052"},{"key":"1451_CR54","doi-asserted-by":"crossref","unstructured":"Ye, M., & Guo, Y. (2017). Zero-shot classification with discriminative semantic representation learning. In: CVPR.","DOI":"10.1109\/CVPR.2017.542"},{"key":"1451_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, L., Xiang, T., & Gong, S. (2017). Learning a deep embedding model for zero-shot learning. In: CVPR.","DOI":"10.1109\/CVPR.2017.321"},{"key":"1451_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, L., Xiang, T., & Gong, S. (2017). Learning a deep embedding model for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2021\u20132030.","DOI":"10.1109\/CVPR.2017.321"},{"key":"1451_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, Z., & Saligrama, V. (2015). Zero-shot learning via semantic similarity embedding. In: ICCV.","DOI":"10.1109\/ICCV.2015.474"},{"key":"1451_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, Z., & Saligrama, V. (2016). Zero-shot learning via joint latent similarity embedding. In: CVPR.","DOI":"10.1109\/CVPR.2016.649"},{"key":"1451_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, Z., & Saligrama, V. (2016). Zero-shot recognition via structured prediction. In: ECCV.","DOI":"10.1007\/978-3-319-46478-7_33"},{"key":"1451_CR60","unstructured":"Zhao, A., Ding, M., Guan, J., Lu, Z., Xiang, T., & Wen, J.R. (2018). Domain-invariant projection learning for zero-shot recognition. In: Advances in Neural Information Processing Systems, pp. 1019\u20131030."},{"key":"1451_CR61","unstructured":"Zhu, X., & Ghahramani, Z. (2002). Learning from labeled and unlabeled data with label propagation. Technical Report, Carnegie Mellon University."},{"key":"1451_CR62","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Elhoseiny, M., Liu, B., Peng, X., & Elgammal, A. (2018). A generative adversarial approach for zero-shot learning from noisy texts. In: CVPR.","DOI":"10.1109\/CVPR.2018.00111"},{"key":"1451_CR63","unstructured":"Zhu, Y., Xie, J., Tang, Z., Peng, X., & Elgammal, A. (2019). Learning where to look: Semantic-guided multi-attention localization for zero-shot learning. arXiv preprint arXiv:1903.00502."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01451-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01451-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01451-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,24]],"date-time":"2022-12-24T16:55:39Z","timestamp":1671900939000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01451-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,19]]},"references-count":63,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["1451"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01451-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,19]]},"assertion":[{"value":"21 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}