{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:16:50Z","timestamp":1791303410300,"version":"4.1.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012151","type":"print"},{"value":"9783030012168","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\/978-3-030-01216-8_45","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T15:10:26Z","timestamp":1539011426000},"page":"747-763","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["Diverse and Coherent Paragraph Generation from Images"],"prefix":"10.1007","author":[{"given":"Moitreya","family":"Chatterjee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander G.","family":"Schwing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"key":"45_CR1","doi-asserted-by":"crossref","unstructured":"Aneja, J., Deshpande, A., Schwing, A.G.: Convolutional image captioning. In: Proceedings CVPR (2018)","DOI":"10.1109\/CVPR.2018.00583"},{"key":"45_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"45_CR3","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN. arXiv preprint 2017"},{"key":"45_CR4","doi-asserted-by":"crossref","unstructured":"Chatterjee, M., Leuski, A.: A novel statistical approach for image and video retrieval and its adaption for active learning. In: Proceedings ACM Multimedia (2015)","DOI":"10.1145\/2733373.2806368"},{"key":"45_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Lawrence Zitnick, C.: Mind\u2019s eye: a recurrent visual representation for image caption generation. In: Proceedings CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"45_CR6","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint 2014"},{"key":"45_CR7","unstructured":"Chung, J., Kastner, K., Dinh, L., Goel, K., Courville, A.C., Bengio, Y.: A recurrent latent variable model for sequential data. In: Proceedings NIPS (2015)"},{"key":"45_CR8","doi-asserted-by":"crossref","unstructured":"Dai, B., Fidler, S., Urtasun, R., Lin, D.: Towards diverse and natural image descriptions via a conditional GAN. arXiv preprint 2017","DOI":"10.1109\/ICCV.2017.323"},{"key":"45_CR9","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor Universal: language specific translation evaluation for any target language. In: Proceedings Ninth Workshop on Statistical Machine Translation (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"45_CR10","doi-asserted-by":"crossref","unstructured":"Deshpande, A., Aneja, J., Wang, L., Schwing, A.G., Forsyth, D.A.: Diverse and controllable image captioning with part-of-speech guidance (2018). https:\/\/arxiv.org\/abs\/1805.12589","DOI":"10.1109\/CVPR.2019.01095"},{"key":"45_CR11","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings CVPR (2015)","DOI":"10.21236\/ADA623249"},{"key":"45_CR12","unstructured":"Gao, H., Mao, J., Zhou, J., Huang, Z., Wang, L., Xu, W.: Are you talking to a machine? Dataset and methods for multilingual image question. In: Proceedings NIPS (2015)"},{"key":"45_CR13","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Proceedings NIPS (2014)"},{"key":"45_CR14","unstructured":"Gregor, K., Danihelka, I., Graves, A., Rezende, D.J., Wierstra, D.: Draw: a recurrent neural network for image generation. arXiv preprint 2015"},{"key":"45_CR15","doi-asserted-by":"crossref","unstructured":"Jain, U., Lazebnik, S., Schwing, A.G.: Two can play this game: visual dialog with discriminative question generation and answering. In: Proceedings CVPR (2018)","DOI":"10.1109\/CVPR.2018.00603"},{"key":"45_CR16","doi-asserted-by":"crossref","unstructured":"Jain, U., Zhang, Z., Schwing, A.: Creativity: generating diverse questions using variational autoencoders. In: Proceedings CVPR (2017)","DOI":"10.1109\/CVPR.2017.575"},{"key":"45_CR17","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: DenseCap: fully convolutional localization networks for dense captioning. In: Proceedings CVPR (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"45_CR18","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"45_CR19","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint 2014"},{"key":"45_CR20","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint 2013"},{"key":"45_CR21","unstructured":"Klambauer, G., Unterthiner, T., Mayr, A., Hochreiter, S.: Self-normalizing neural networks. In: Proceedings NIPS (2017)"},{"key":"45_CR22","doi-asserted-by":"crossref","unstructured":"Krause, J., Johnson, J., Krishna, R., Fei-Fei, L.: A hierarchical approach for generating descriptive image paragraphs. In: Proceedings CVPR (2017)","DOI":"10.1109\/CVPR.2017.356"},{"issue":"1","key":"45_CR23","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R.: Visual genome: connecting language and vision using crowdsourced dense image annotations. IJCV 123(1), 32\u201373 (2017)","journal-title":"IJCV"},{"key":"45_CR24","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings NIPS (2012)"},{"key":"45_CR25","unstructured":"Lavrenko, V., Manmatha, R., Jeon, J.: A model for learning the semantics of pictures. In: Proceedings NIPS (2004)"},{"key":"45_CR26","doi-asserted-by":"crossref","unstructured":"Liang, X., Hu, Z., Zhang, H., Gan, C., Xing, E.P.: Recurrent topic-transition GAN for visual paragraph generation. In: Proceedings ICCV (2017)","DOI":"10.1109\/ICCV.2017.364"},{"key":"45_CR27","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., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: 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"},{"key":"45_CR28","doi-asserted-by":"crossref","unstructured":"Malinowski, M., Rohrbach, M., Fritz, M.: Ask your neurons: a neural-based approach to answering questions about images. In: Proceedings ICCV (2015)","DOI":"10.1109\/ICCV.2015.9"},{"key":"45_CR29","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-RNN). arXiv preprint 2014"},{"key":"45_CR30","doi-asserted-by":"crossref","unstructured":"McAuley, J., Targett, C., Shi, Q., Van Den Hengel, A.: Image-based recommendations on styles and substitutes. In: Proceedings ACM SIGIR (2015)","DOI":"10.1145\/2766462.2767755"},{"key":"45_CR31","unstructured":"Pan, J.Y., Yang, H.J., Duygulu, P., Faloutsos, C.: Automatic image captioning. In: Proceedings ICME (2004)"},{"key":"45_CR32","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings ACL (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"45_CR33","unstructured":"Ren, M., Kiros, R., Zemel, R.: Exploring models and data for image question answering. In: Proceedings NIPS (2015)"},{"key":"45_CR34","unstructured":"Schwartz, I., Schwing, A.G., Hazan, T.: High-order attention models for visual question answering. In: Proceedings NIPS (2017)"},{"key":"45_CR35","doi-asserted-by":"crossref","unstructured":"Shih, K.J., Singh, S., Hoiem, D.: Where to look: focus regions for visual question answering. In: Proceedings CVPR (2016)","DOI":"10.1109\/CVPR.2016.499"},{"key":"45_CR36","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint 2014"},{"key":"45_CR37","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Proceedings CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"45_CR38","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"45_CR39","unstructured":"Wang, L., Schwing, A.G., Lazebnik, S.: Diverse and accurate image description using a variational auto-encoder with an additive gaussian encoding space. In: Proceedings NIPS (2017)"},{"key":"45_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-540-69423-6_25","volume-title":"Advances in Multimedia Modeling","author":"Y Xiao","year":"2006","unstructured":"Xiao, Y., Chua, T.-S., Lee, C.-H.: Fusion of region and image-based techniques for automatic image annotation. In: Cham, T.-J., Cai, J., Dorai, C., Rajan, D., Chua, T.-S., Chia, L.-T. (eds.) MMM 2007. LNCS, vol. 4351, pp. 247\u2013258. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/978-3-540-69423-6_25"},{"key":"45_CR41","unstructured":"Xie, P.: Diversity-promoting and large-scale machine learning for healthcare (2018). http:\/\/www.cs.cmu.edu\/~pengtaox\/thesis_proposal_pengtaoxie.pdf. Accessed 25 July 2018"},{"key":"45_CR42","unstructured":"Xiong, C., Merity, S., Socher, R.: Dynamic memory networks for visual and textual question answering. In: Proceedings ICML (2016)"},{"key":"45_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-319-46478-7_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"H Xu","year":"2016","unstructured":"Xu, H., Saenko, K.: Ask, attend and answer: exploring question-guided spatial attention for visual question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 451\u2013466. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_28"},{"key":"45_CR44","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: Proceedings ICML (2015)"},{"key":"45_CR45","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings CVPR (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"45_CR46","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: Proceedings CVPR (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"45_CR47","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, J., Huang, Z., Yang, Y., Xu, W.: Video paragraph captioning using hierarchical recurrent neural networks. In: Proceedings CVPR (2016)","DOI":"10.1109\/CVPR.2016.496"}],"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\/978-3-030-01216-8_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:29:36Z","timestamp":1665188976000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01216-8_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012151","9783030012168"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01216-8_45","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":"9 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"}]}}