{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T09:12:25Z","timestamp":1760346745116,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030012274"},{"type":"electronic","value":"9783030012281"}],"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\/978-3-030-01228-1_12","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T05:03:51Z","timestamp":1538802231000},"page":"189-204","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Goal-Oriented Visual Question Generation via Intermediate Rewards"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0033-0494","authenticated-orcid":false,"given":"Junjie","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3631-256X","authenticated-orcid":false,"given":"Qi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8648-8718","authenticated-orcid":false,"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7240-3541","authenticated-orcid":false,"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9190-507X","authenticated-orcid":false,"given":"Jianfeng","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3027-8364","authenticated-orcid":false,"given":"Anton","family":"van den Hengel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Learning to compose neural networks for question answering. In: NAACL HLT 2016, The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego California, USA, 12\u201317 June 2016, pp. 1545\u20131554 (2016)","DOI":"10.18653\/v1\/N16-1181"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"12_CR3","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/978-3-7908-2604-3_16","volume-title":"Proceedings of COMPSTAT 2010","author":"L Bottou","year":"2010","unstructured":"Bottou, L.: Large-scale machine learning with stochastic gradient descent. In: Lechevallier, Y., Saporta, G. (eds.) Proceedings of COMPSTAT 2010, pp. 177\u2013186. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-7908-2604-3_16"},{"key":"12_CR4","unstructured":"Das, A., et al.: Visual dialog. CoRR abs\/1611.08669 (2016)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Das, A., Kottur, S., Moura, J.M.F., Lee, S., Batra, D.: Learning cooperative visual dialog agents with deep reinforcement learning. In: Proceedings of IEEE International Conferernce on Computer Vision, pp. 2970\u20132979 (2017)","DOI":"10.1109\/ICCV.2017.321"},{"key":"12_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/978-3-642-39593-2_8","volume-title":"Statistical Language and Speech Processing","author":"L El Asri","year":"2013","unstructured":"El Asri, L., Laroche, R., Pietquin, O.: Reward shaping for statistical optimisation of dialogue management. In: Dediu, A.-H., Mart\u00edn-Vide, C., Mitkov, R., Truthe, B. (eds.) SLSP 2013. LNCS (LNAI), vol. 7978, pp. 93\u2013101. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-39593-2_8"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Hu, R., Andreas, J., Rohrbach, M., Darrell, T., Saenko, K.: Learning to reason: end-to-end module networks for visual question answering. In: Proceedings of IEEE International Conferernce on Computer Vision, pp. 804\u2013813 (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: DenseCap: fully convolutional localization networks for dense captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4565\u20134574 (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"12_CR9","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Arti. Intell. Res. 4, 237\u2013285 (1996)","journal-title":"J. Arti. Intell. Res."},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Li, Y., Duan, N., Zhou, B., Chu, X., Ouyang, W., Wang, X.: Visual question generation as dual task of visual question answering. CoRR abs\/1709.07192 (2017)","DOI":"10.1109\/CVPR.2018.00640"},{"key":"12_CR11","unstructured":"Liu, S., Zhu, Z., Ye, N., Guadarrama, S., Murphy, K.: Optimization of image description metrics using policy gradient methods. CoRR abs\/1612.00370 (2016)"},{"key":"12_CR12","unstructured":"Lu, J., Kannan, A., Yang, J., Parikh, D., Batra, D.: Best of both worlds: transferring knowledge from discriminative learning to a generative visual dialog model. In: Proceedings of Advances in Neural Information Processing Systems, pp. 313\u2013323 (2017)"},{"key":"12_CR13","unstructured":"Mora, I.M., de la Puente, S.P., Giro-i Nieto, X.: Towards automatic generation of question answer pairs from images (2016)"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Mostafazadeh, N., Misra, I., Devlin, J., Mitchell, M., He, X., Vanderwende, L.: Generating natural questions about an image. In: Proceedings of Conference Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/P16-1170"},{"key":"12_CR15","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: theory and application to reward shaping. In: Proceedings of the International Conference on Machine Learning, vol. 99, pp. 278\u2013287 (1999)"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Ren, Z., Wang, X., Zhang, N., Lv, X., Li, L.J.: Deep reinforcement learning-based image captioning with embedding reward. In: Proceedings of the IEEE Conferernce on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.128"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: Proceedings of the IEEE Conferernce on Computer Vision and Pattern Recognition, pp. 1179\u20131195 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Strub, F., de Vries, H., Mary, J., Piot, B., Courville, A.C., Pietquin, O.: End-to-end optimization of goal-driven and visually grounded dialogue systems. In: Proceedings of the International Joint Conferences on Artificial Intelligence (2017)","DOI":"10.24963\/ijcai.2017\/385"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Su, P., Vandyke, D., Gasic, M., Mrksic, N., Wen, T., Young, S.J.: Reward shaping with recurrent neural networks for speeding up on-line policy learning in spoken dialogue systems. In: Proceedings of the SIGDIAL 2015 Conference, The 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 417\u2013421 (2015)","DOI":"10.18653\/v1\/W15-4655"},{"key":"12_CR20","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1. MIT press, Cambridge (1998)"},{"key":"12_CR21","unstructured":"Sutton, R.S., McAllester, D.A., Singh, S.P., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, pp. 1057\u20131063 (2000)"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"de Vries, H., Strub, F., Chandar, S., Pietquin, O., Larochelle, H., Courville, A.C.: Guesswhat?! visual object discovery through multi-modal dialogue. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.475"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wang, P., Shen, C., Dick, A., van den Hengel, A.: Ask me anything: free-form visual question answering based on knowledge from external sources. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 2016","DOI":"10.1109\/CVPR.2016.500"},{"key":"12_CR24","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":"12_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, S., Qu, L., You, S., Yang, Z., Zhang, J.: Automatic generation of grounded visual questions. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 4235\u20134243 (2017)","DOI":"10.24963\/ijcai.2017\/592"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Lim, J.J., Fei-Fei, L.: Knowledge acquisition for visual question answering via iterative querying. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.651"}],"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\/978-3-030-01228-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:23:24Z","timestamp":1665015804000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01228-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012274","9783030012281"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01228-1_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 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"}]}}