{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T13:45:43Z","timestamp":1726062343008},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030367176"},{"type":"electronic","value":"9783030367183"}],"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\/978-3-030-36718-3_18","type":"book-chapter","created":{"date-parts":[[2019,12,10]],"date-time":"2019-12-10T03:03:52Z","timestamp":1575947032000},"page":"209-221","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Watch and Ask: Video Question Generation"],"prefix":"10.1007","author":[{"given":"Shenglei","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaohan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bencheng","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,12,9]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Denkowski, M.J., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: WMT@ACL, pp. 376\u2013380 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Du, X., Shao, J., Cardie, C.: Learning to ask: neural question generation for reading comprehension. In: ACL, vol. 1, pp.1342\u20131352 (2017)","DOI":"10.18653\/v1\/P17-1123"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Fan, Z., Wei, Z., Li, P., Lan, Y., Huang, X.: A question type driven framework to diversify visual question generation. In: IJCAI, pp. 4048\u20134054 (2018)","DOI":"10.24963\/ijcai.2018\/563"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Gao, J., Ge, R., Chen, K., Nevatia, R.: Motion-appearance co-memory networks for video question answering. In: CVPR, pp. 6576\u20136585 (2018)","DOI":"10.1109\/CVPR.2018.00688"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Jang, Y., Song, Y., Yu, Y., Kim, Y., Kim, G.: TGIF-QA: toward spatio-temporal reasoning in visual question answering. In: CVPR, pp. 1359\u20131367 (2017)","DOI":"10.1109\/CVPR.2017.149"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Kim, K., Heo, M., Choi, S., Zhang, B.: Deepstory: video story QA by deep embedded memory networks. In: IJCAI, pp. 2016\u20132022 (2017)","DOI":"10.24963\/ijcai.2017\/280"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Visual question generation as dual task of visual question answering. In: CVPR, pp. 6116\u20136124 (2018)","DOI":"10.1109\/CVPR.2018.00640"},{"key":"18_CR10","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out (2004)"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Maharaj, T., Ballas, N., Rohrbach, A., Courville, A.C., Pal, C.J.: A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering. In: CVPR, pp. 7359\u20137368 (2017)","DOI":"10.1109\/CVPR.2017.778"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Mostafazadeh, N., Misra, I., Devlin, J., Mitchell, M., He, X., Vanderwende, L.: Generating natural questions about an image. In: ACL (2016)","DOI":"10.18653\/v1\/P16-1170"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Mun, J., Seo, P.H., Jung, I., Han, B.: Marioqa: answering questions by watching gameplay videos. In: ICCV, pp. 2886\u20132894 (2017)","DOI":"10.1109\/ICCV.2017.312"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: ACL, pp. 311\u2013318. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"18_CR15","unstructured":"Skalban, Y.: Automatic generation of factual questions from video documentaries. Ph.D. thesis, University of Wolverhampton, UK (2013)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., Fidler, S.: Movieqa: understanding stories in movies through question-answering. In: CVPR, pp. 4631\u20134640 (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Uehara, K., Tejero-de-Pablos, A., Ushiku, Y., Harada, T.: Visual question generation for class acquisition of unknown objects. In: ECCV, pp. 492\u2013507 (2018)","DOI":"10.1007\/978-3-030-01258-8_30"},{"key":"18_CR18","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 6000\u20136010 (2017)"},{"key":"18_CR19","unstructured":"Xiong, C., Merity, S., Socher, R.: Dynamic memory networks for visual and textual question answering. In: ICML, pp. 2397\u20132406 (2016)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: Mattnet: modular attention network for referring expression comprehension. In: CVPR, pp. 1307\u20131315 (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, S., Qu, L., You, S., Yang, Z., Zhang, J.: Automatic generation of grounded visual questions. In: IJCAI, pp. 4235\u20134243 (2017)","DOI":"10.24963\/ijcai.2017\/592"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Groth, O., Bernstein, M.S., Fei-Fei, L.: Visual7w: grounded question answering in images. In: CVPR, pp. 4995\u20135004 (2016)","DOI":"10.1109\/CVPR.2016.540"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-36718-3_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,10]],"date-time":"2019-12-10T03:12:37Z","timestamp":1575947557000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-36718-3_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030367176","9783030367183"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-36718-3_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ajiips.com.au\/iconip2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}