{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T10:52:47Z","timestamp":1742986367139,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031082221"},{"type":"electronic","value":"9783031082238"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-08223-8_20","type":"book-chapter","created":{"date-parts":[[2022,6,14]],"date-time":"2022-06-14T14:11:04Z","timestamp":1655215864000},"page":"235-246","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Image Captioning as\u00a0a\u00a0Structured Transduction Task"],"prefix":"10.1007","author":[{"given":"Davide","family":"Bacciu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Davide","family":"Serramazza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,6,10]]},"reference":[{"key":"20_CR1","series-title":"Proceedings of the International Neural Networks Society","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1007\/978-3-030-16841-4_25","volume-title":"Recent Advances in Big Data and Deep Learning","author":"D Bacciu","year":"2020","unstructured":"Bacciu, D., Bruno, A.: Deep tree transductions - a short survey. In: Oneto, L., Navarin, N., Sperduti, A., Anguita, D. (eds.) INNSBDDL 2019. PINNS, vol. 1, pp. 236\u2013245. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-16841-4_25"},{"issue":"12","key":"20_CR2","doi-asserted-by":"publisher","first-page":"1987","DOI":"10.1109\/TNNLS.2012.2222044","volume":"23","author":"D Bacciu","year":"2012","unstructured":"Bacciu, D., Micheli, A., Sperduti, A.: Compositional generative mapping for tree-structured data-part I: bottom-up probabilistic modeling of trees. IEEE Trans. Neural Netw. Learn. Syst. 23(12), 1987\u20132002 (2012). https:\/\/doi.org\/10.1109\/TNNLS.2012.2222044","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"20_CR3","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.neucom.2012.12.044","volume":"112","author":"D Bacciu","year":"2013","unstructured":"Bacciu, D., Micheli, A., Sperduti, A.: An input-output hidden Markov model for tree transductions. Neurocomputing 112, 34\u201346 (2013)","journal-title":"Neurocomputing"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Cho, K., et al: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Dong, L., Lapata, M.: Language to logical form with neural attention. arXiv preprint arXiv:1601.01280 (2016)","DOI":"10.18653\/v1\/P16-1004"},{"issue":"5","key":"20_CR6","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1109\/72.712151","volume":"9","author":"P Frasconi","year":"1998","unstructured":"Frasconi, P., Gori, M., Sperduti, A.: A general framework for adaptive processing of data structures. IEEE Trans. Neural Netw. 9(5), 768\u2013786 (1998). https:\/\/doi.org\/10.1109\/72.712151","journal-title":"IEEE Trans. Neural Netw."},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arxiv 2015. arXiv preprint arXiv:1512.03385 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"20_CR8","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"20_CR9","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456. PMLR (2015)"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Klein, D., Manning, C.D.: Accurate unlexicalized parsing. In: Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pp. 423\u2013430 (2003)","DOI":"10.3115\/1075096.1075150"},{"key":"20_CR11","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1162\/tacl_a_00188","volume":"2","author":"P Kuznetsova","year":"2014","unstructured":"Kuznetsova, P., Ordonez, V., Berg, T.L., Choi, Y.: TreeTalk: composition and compression of trees for image descriptions. Trans. Assoc. Comput. Linguist. 2, 351\u2013362 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"20_CR12","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":"10","key":"20_CR13","doi-asserted-by":"publisher","first-page":"4596","DOI":"10.1109\/TIP.2016.2592704","volume":"25","author":"T Liu","year":"2016","unstructured":"Liu, T., Seyedhosseini, M., Tasdizen, T.: Image segmentation using hierarchical merge tree. IEEE Trans. Image Process. 25(10), 4596\u20134607 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. arxiv 2015. arXiv preprint arXiv:1512.00567 1512 (2015)","DOI":"10.1109\/CVPR.2016.308"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Tai, K.S., Socher, R., Manning, C.D.: Improved semantic representations from tree-structured long short-term memory networks. arXiv preprint arXiv:1503.00075 (2015)","DOI":"10.3115\/v1\/P15-1150"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. corr abs\/1411.4555 (2014). arXiv preprint arXiv:1411.4555 (2014)","DOI":"10.1109\/CVPR.2015.7298935"},{"issue":"4","key":"20_CR18","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2016.2587640","volume":"39","author":"O Vinyals","year":"2016","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: lessons learned from the 2015 MSCOCO image captioning challenge. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 652\u2013663 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR19","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"20_CR20","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. TACL 2, 67\u201378 (2014)","journal-title":"TACL"}],"container-title":["Communications in Computer and Information Science","Engineering Applications of Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-08223-8_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,14]],"date-time":"2022-06-14T14:13:54Z","timestamp":1655216034000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-08223-8_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031082221","9783031082238"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-08223-8_20","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 June 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Engineering Applications of Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chersonisos, Crete","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eann2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eannconf.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}