{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:59:54Z","timestamp":1790877594054,"version":"4.1.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012366","type":"print"},{"value":"9783030012373","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01237-3_37","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T18:42:18Z","timestamp":1538851338000},"page":"610-626","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":55,"title":["Imagine This! Scripts to Compositions to Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6551-7455","authenticated-orcid":false,"given":"Tanmay","family":"Gupta","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1666-6889","authenticated-orcid":false,"given":"Dustin","family":"Schwenk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7249-2380","authenticated-orcid":false,"given":"Ali","family":"Farhadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6260-5708","authenticated-orcid":false,"given":"Derek","family":"Hoiem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7608-7443","authenticated-orcid":false,"given":"Aniruddha","family":"Kembhavi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"issue":"11","key":"37_CR1","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","volume":"34","author":"R Achanta","year":"2012","unstructured":"Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., S\u00fcsstrunk, S.: Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274\u20132282 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37_CR2","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein gan. CoRR abs\/1701.07875 (2017)"},{"issue":"3","key":"37_CR3","first-page":"24","volume":"28","author":"C Barnes","year":"2009","unstructured":"Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: Patchmatch: a randomized correspondence algorithm for structural image editing. ACM Trans. Graph.-TOG 28(3), 24 (2009)","journal-title":"ACM Trans. Graph.-TOG"},{"key":"37_CR4","unstructured":"Bengio, Y., Mesnil, G., Dauphin, Y., Rifai, S.: Better mixing via deep representations. In: ICML (2013)"},{"key":"37_CR5","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/978-1-4615-5529-2_5","volume-title":"Learning to Learn","author":"R Caruana","year":"1998","unstructured":"Caruana, R.: Multitask learning. In: Thrun, S., Pratt, L. (eds.) Learning to Learn, pp. 95\u2013133. Springer, Boston (1998). https:\/\/doi.org\/10.1007\/978-1-4615-5529-2_5"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Q., Koltun, V.: Photographic image synthesis with cascaded refinement networks. CoRR abs\/1707.09405 (2017)","DOI":"10.1109\/ICCV.2017.168"},{"key":"37_CR7","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: Vse++: Improved visual-semantic embeddings. arXiv preprint arXiv:1707.05612 (2017)"},{"key":"37_CR8","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Mikolov, T., et al.: Devise: a deep visual-semantic embedding model. In: Advances in Neural Information Processing Systems, pp. 2121\u20132129 (2013)"},{"key":"37_CR9","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: NIPS (2014)"},{"key":"37_CR10","unstructured":"Gregor, K., Danihelka, I., Graves, A., Rezende, D.J., Wierstra, D.: Draw: a recurrent neural network for image generation. In: ICML (2015)"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Gupta, T., et al.: Aligned image-word representations improve inductive transfer across vision-language tasks. arXiv preprint arXiv:1704.00260 (2017)","DOI":"10.1109\/ICCV.2017.452"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Hong, S., Yang, D., Choi, J., Lee, H.: Inferring semantic layout for hierarchical text-to-image synthesis. CoRR abs\/1801.05091 (2018)","DOI":"10.1109\/CVPR.2018.00833"},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. CoRR abs\/1611.07004 (2016)","DOI":"10.1109\/CVPR.2017.632"},{"key":"37_CR14","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of gans for improved quality, stability, and variation. CoRR abs\/1710.10196 (2017)"},{"key":"37_CR15","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. CoRR abs\/1312.6114 (2013)"},{"key":"37_CR16","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)"},{"key":"37_CR17","unstructured":"Kwak, H., Zhang, B.T.: Generating images part by part with composite generative adversarial networks. CoRR abs\/1607.05387 (2016)"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Min, M.R., Shen, D., Carlson, D., Carin, L.: Video generation from text. arXiv preprint arXiv:1710.00421 (2017)","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Y., Qin, Z., Luo, Z., Wang, H.: Auto-painter: Cartoon image generation from sketch by using conditional generative adversarial networks. CoRR abs\/1705.01908 (2017)","DOI":"10.1016\/j.neucom.2018.05.045"},{"key":"37_CR20","unstructured":"Mansimov, E., Parisotto, E., Ba, J., Salakhutdinov, R.: Generating images from captions with attention. In: ICLR (2016)"},{"key":"37_CR21","doi-asserted-by":"crossref","unstructured":"Marwah, T., Mittal, G., Balasubramanian, V.N.: Attentive semantic video generation using captions. CoRR abs\/1708.05980 (2017)","DOI":"10.1109\/ICCV.2017.159"},{"key":"37_CR22","unstructured":"Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier gans. In: ICML (2017)"},{"key":"37_CR23","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2641\u20132649. IEEE (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"37_CR24","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. CoRR abs\/1511.06434 (2015)"},{"key":"37_CR25","unstructured":"Reed, S., van den Oord, A., Kalchbrenner, N., Bapst, V., Botvinick, M., de Freitas, N.: Generating interpretable images with controllable structure. In: OpenReview.net (2017)"},{"key":"37_CR26","unstructured":"Reed, S.E., Akata, Z., Mohan, S., Tenka, S., Schiele, B., Lee, H.: Learning what and where to draw. In: NIPS (2016)"},{"key":"37_CR27","unstructured":"Reed, S.E., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: ICML (2016)"},{"key":"37_CR28","doi-asserted-by":"crossref","unstructured":"Rother, C., Kolmogorov, V., Blake, A.: Grabcut: Interactive foreground extraction using iterated graph cuts. In: ACM Transactions on Graphics (TOG), vol. 23, pp. 309\u2013314. ACM (2004)","DOI":"10.1145\/1015706.1015720"},{"key":"37_CR29","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Huang, L.K., Salakhutdinov, R.: Learning robust visual-semantic embeddings. arXiv preprint arXiv:1703.05908 (2017)","DOI":"10.1109\/ICCV.2017.386"},{"key":"37_CR30","unstructured":"Villegas, R., Yang, J., Zou, Y., Sohn, S., Lin, X., Lee, H.: Learning to generate long-term future via hierarchical prediction. arXiv preprint arXiv:1704.05831 (2017)"},{"key":"37_CR31","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: NIPS (2016)"},{"key":"37_CR32","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":"37_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-319-46493-0_47","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Yan","year":"2016","unstructured":"Yan, X., Yang, J., Sohn, K., Lee, H.: Attribute2Image: conditional image generation from visual attributes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 776\u2013791. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_47"},{"key":"37_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. CoRR abs\/1612.03242 (2016)","DOI":"10.1109\/ICCV.2017.629"},{"key":"37_CR35","doi-asserted-by":"crossref","unstructured":"Zitnick, C.L., Parikh, D.: Bringing semantics into focus using visual abstraction. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3009\u20133016 (2013)","DOI":"10.1109\/CVPR.2013.387"},{"key":"37_CR36","doi-asserted-by":"crossref","unstructured":"Zitnick, C.L., Parikh, D., Vanderwende, L.: Learning the visual interpretation of sentences. In: 2013 IEEE International Conference on Computer Vision, pp. 1681\u20131688 (2013)","DOI":"10.1109\/ICCV.2013.211"},{"key":"37_CR37","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1109\/TPAMI.2014.2366143","volume":"38","author":"CL Zitnick","year":"2016","unstructured":"Zitnick, C.L., Vedantam, R., Parikh, D.: Adopting abstract images for semantic scene understanding. IEEE Trans. Pattern Anal. Mach. Intell. 38, 627\u2013638 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01237-3_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:15:21Z","timestamp":1665015321000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01237-3_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012366","9783030012373"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01237-3_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"7 October 2018","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"}]}}