{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:17:19Z","timestamp":1782314239721,"version":"3.54.5"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030208929","type":"print"},{"value":"9783030208936","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\/978-3-030-20893-6_7","type":"book-chapter","created":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T07:25:52Z","timestamp":1559028352000},"page":"100-116","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":119,"title":["Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings"],"prefix":"10.1007","author":[{"given":"Kevin","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher B.","family":"Choy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manolis","family":"Savva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angel X.","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Funkhouser","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Silvio","family":"Savarese","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,5,29]]},"reference":[{"key":"7_CR1","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN. \n                      arXiv:1701.07875\n                      \n                     (2017)"},{"key":"7_CR2","unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. Technical report \n                      arXiv:1512.03012\n                      \n                     [cs.GR], Stanford University \u2013 Princeton University \u2013 Toyota Technological Institute at Chicago (2015)"},{"key":"7_CR3","unstructured":"Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 539\u2013546. IEEE (2005)"},{"key":"7_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1007\/978-3-319-46484-8_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"CB Choy","year":"2016","unstructured":"Choy, C.B., Xu, D., Gwak, J.Y., Chen, K., Savarese, S.: 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 628\u2013644. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46484-8_38"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Tobias Springenberg, J., Brox, T.: Learning to generate chairs with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1538\u20131546 (2015)","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"7_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1007\/978-3-319-46466-4_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Girdhar","year":"2016","unstructured":"Girdhar, R., Fouhey, D.F., Rodriguez, M., Gupta, A.: Learning a predictable and generative vector representation for objects. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 484\u2013499. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46466-4_29"},{"key":"7_CR7","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"7_CR8","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved training of Wasserstein GANs. \n                      arXiv:1704.00028\n                      \n                     (2017)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Haeusser, P., Frerix, T., Mordvintsev, A., Cremers, D.: Associative domain adaptation. \n                      arXiv:1708.00938\n                      \n                     (2017)","DOI":"10.1109\/ICCV.2017.301"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Haeusser, P., Mordvintsev, A., Cremers, D.: Learning by association-a versatile semi-supervised training method for neural networks. \n                      arXiv:1706.00909\n                      \n                     (2017)","DOI":"10.1109\/CVPR.2017.74"},{"issue":"4","key":"7_CR11","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1145\/582415.582418","volume":"20","author":"K J\u00e4rvelin","year":"2002","unstructured":"J\u00e4rvelin, K., Kek\u00e4l\u00e4inen, J.: Cumulated gain-based evaluation of IR techniques. ACM Trans. Inf. Syst. (TOIS) 20(4), 422\u2013446 (2002)","journal-title":"ACM Trans. Inf. Syst. (TOIS)"},{"key":"7_CR12","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. \n                      arXiv:1411.2539\n                      \n                     (2014)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Klein, B., Lev, G., Sadeh, G., Wolf, L.: Associating neural word embeddings with deep image representations using Fisher vectors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4437\u20134446 (2015)","DOI":"10.1109\/CVPR.2015.7299073"},{"issue":"4","key":"7_CR14","first-page":"52","volume":"36","author":"J Li","year":"2017","unstructured":"Li, J., Xu, K., Chaudhuri, S., Yumer, E., Zhang, H., Guibas, L.: GRASS: generative recursive autoencoders for shape structures. ACM Trans. Graph. (TOG) 36(4), 52 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"6","key":"7_CR15","first-page":"234:1","volume":"34","author":"Y Li","year":"2015","unstructured":"Li, Y., Su, H., Qi, C.R., Fish, N., Cohen-Or, D., Guibas, L.J.: Joint embeddings of shapes and images via CNN image purification. ACM Trans. Graph. 34(6), 234:1 (2015)","journal-title":"ACM Trans. Graph."},{"key":"7_CR16","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":"7_CR17","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. \n                      arXiv:1411.1784\n                      \n                     (2014)"},{"key":"7_CR18","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: Proceedings of the 28th International Conference on Machine Learning (ICML 2011), pp. 689\u2013696 (2011)"},{"key":"7_CR19","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. \n                      arXiv:1511.06434\n                      \n                     (2015)"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Reed, S., Akata, Z., Lee, H., Schiele, B.: Learning deep representations of fine-grained visual descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 49\u201358 (2016)","DOI":"10.1109\/CVPR.2016.13"},{"key":"7_CR21","unstructured":"Reed, S., Akata, Z., Mohan, S., Tenka, S., Schiele, B., Lee, H.: Learning what and where to draw. In: NIPS (2016)"},{"key":"7_CR22","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text-to-image synthesis. In: Proceedings of the 33rd International Conference on Machine Learning (2016)"},{"key":"7_CR23","unstructured":"Reed, S., van den Oord, A., Kalchbrenner, N., Bapst, V., Botvinick, M., de Freitas, N.: Generating interpretable images with controllable structure. Technical report, Google DeepMind (2016)"},{"key":"7_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":"7_CR25","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"7_CR26","unstructured":"Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. In: Advances in Neural Information Processing Systems, pp. 1857\u20131865 (2016)"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Song, H.O., Xiang, Y., Jegelka, S., Savarese, S.: Deep metric learning via lifted structured feature embedding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.434"},{"key":"7_CR28","unstructured":"Srivastava, N., Salakhutdinov, R.R.: Multimodal learning with deep Boltzmann machines. In: Advances in Neural Information Processing Systems (2012)"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Huang, L.K., Salakhutdinov, R.: Learning robust visual-semantic embeddings. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.386"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5005\u20135013 (2016)","DOI":"10.1109\/CVPR.2016.541"},{"key":"7_CR31","unstructured":"Weinberger, K.Q., Blitzer, J., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. In: Advances in Neural Information Processing Systems, pp. 1473\u20131480 (2006)"},{"key":"7_CR32","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, W.T., Tenenbaum, J.B.: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In: Advances in Neural Information Processing Systems, pp. 82\u201390 (2016)"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: Attngan: fine-grained text to image generation with attentional generative adversarial networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Stackgan++: realistic image synthesis with stacked generative adversarial networks. \n                      arXiv:1710.10916\n                      \n                     (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Stackgan: text to photo-realistic image synthesis with stacked generative adversarial networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xie, Y., Yang, L.: Photographic text-to-image synthesis with a hierarchically-nested adversarial network. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00649"}],"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\/978-3-030-20893-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T07:32:08Z","timestamp":1559028728000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20893-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208929","9783030208936"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20893-6_7","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":"29 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"}}]}}