{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:11:28Z","timestamp":1743120688677,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030841850"},{"type":"electronic","value":"9783030841867"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-84186-7_12","type":"book-chapter","created":{"date-parts":[[2021,8,7]],"date-time":"2021-08-07T10:03:42Z","timestamp":1628330622000},"page":"177-192","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Category-Based Strategy-Driven Question Generator for Visual Dialogue"],"prefix":"10.1007","author":[{"given":"Yanan","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanxin","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangxiang","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunping","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,8]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), December 2015","DOI":"10.1109\/ICCV.2015.279"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Chattopadhyay, P., et al.: Evaluating visual conversational agents via cooperative human-AI games. arXiv:1708.05122 [cs], August 2017","DOI":"10.1609\/hcomp.v5i1.13312"},{"key":"12_CR3","unstructured":"Chen, Q., Zhuo, Z., Wang, W.: BERT for joint intent classification and slot filling. arXiv preprint arXiv:1902.10909 (2019)"},{"key":"12_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":"12_CR5","unstructured":"Das, A., et al.: Visual Dialog. arXiv:1611.08669 [cs], August 2017"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Deng, C., Wu, Q., Wu, Q., Hu, F., Lyu, F., Tan, M.: Visual grounding via accumulated attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00808"},{"key":"12_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Du\u0161ek, O., Jur\u010d\u00ed\u010dek, F.: A context-aware natural language generator for dialogue systems. arXiv preprint arXiv:1608.07076 (2016)","DOI":"10.18653\/v1\/W16-3622"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Freitag, M., Al-Onaizan, Y.: Beam search strategies for neural machine translation. arXiv preprint arXiv:1702.01806 (2017)","DOI":"10.18653\/v1\/W17-3207"},{"key":"12_CR10","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 315\u2013323 (2011)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Krishna, R., Bernstein, M., Fei-Fei, L.: Information maximizing visual question generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2008\u20132018 (2019)","DOI":"10.1109\/CVPR.2019.00211"},{"key":"12_CR13","unstructured":"Lin, C.: Recall-oriented understudy for gisting evaluation (rouge) (2005). Accessed 20 Aug 2005"},{"key":"12_CR14","unstructured":"Pang, W., Wang, X.: Visual dialogue state tracking for question generation. arXiv:1911.07928 [cs], November 2019"},{"key":"12_CR15","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 of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"issue":"6","key":"12_CR16","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Saha, A., Khapra, M., Sankaranarayanan, K.: Towards building large scale multimodal domain-aware conversation systems. arXiv:1704.00200 [cs], January 2018","DOI":"10.1609\/aaai.v32i1.11331"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Serban, I., Sordoni, A., Bengio, Y., Courville, A., Pineau, J.: Building end-to-end dialogue systems using generative hierarchical neural network models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)","DOI":"10.1609\/aaai.v30i1.9883"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Shan, Y., et al.: A contextual hierarchical attention network with adaptive objective for dialogue state tracking. arXiv preprint arXiv:2006.01554 (2020)","DOI":"10.18653\/v1\/2020.acl-main.563"},{"key":"12_CR20","unstructured":"Shekhar, R., Baumgartner, T., Venkatesh, A., Bruni, E., Bernardi, R., Fern\u00e1ndez, R.: Ask no more: deciding when to guess in referential visual dialogue. arXiv preprint arXiv:1805.06960 (2018)"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Shekhar, R., et al.: Beyond task success: a closer look at jointly learning to see, ask, and guesswhat. arXiv preprint arXiv:1809.03408 (2018)","DOI":"10.18653\/v1\/N19-1265"},{"key":"12_CR22","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"12_CR23","unstructured":"Smith, E.M., Gonzalez-Rico, D., Dinan, E., Boureau, Y.L.: Controlling style in generated dialogue. arXiv preprint arXiv:2009.10855 (2020)"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Strub, F., De Vries, H., Mary, J., Piot, B., Courville, A., Pietquin, O.: End-to-end optimization of goal-driven and visually grounded dialogue systems. arXiv preprint arXiv:1703.05423 (2017)","DOI":"10.24963\/ijcai.2017\/385"},{"key":"12_CR25","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. arXiv preprint arXiv:1409.3215 (2014)"},{"key":"12_CR26","doi-asserted-by":"publisher","unstructured":"Tan, Y., Ou, Z., Liu, K., Shi, Y., Song, M.: Turn-level recurrence self-attention for joint dialogue action prediction and response generation. In: Wang, X., Zhang, R., Lee, Y.K., Sun, L., Moon, Y.S. (eds.) Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data, pp. 309\u2013316. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-60290-1_24","DOI":"10.1007\/978-3-030-60290-1_24"},{"key":"12_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"de Vries, H., Strub, F., Chandar, S., Pietquin, O., Larochelle, H., Courville, A.: GuessWhat?! Visual object discovery through multi-modal dialogue. arXiv:1611.08481 [cs], February 2017","DOI":"10.1109\/CVPR.2017.475"},{"key":"12_CR29","doi-asserted-by":"publisher","unstructured":"Xu, Z., Feng, F., Wang, X., Yang, Y., Jiang, H., Wang, Z.: Answer-driven visual state estimator for goal-oriented visual dialogue. In: Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA, pp. 4271\u20134279. ACM, October 2020. https:\/\/doi.org\/10.1145\/3394171.3413668","DOI":"10.1145\/3394171.3413668"},{"key":"12_CR30","doi-asserted-by":"publisher","unstructured":"Zhang, J., Wu, Q., Shen, C., Zhang, J., Lu, J., Van Den Hengel, A.: Goal-oriented visual question generation via intermediate rewards. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Proceedings of the European Conference on Computer Vision (ECCV), pp. 186\u2013201. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_12","DOI":"10.1007\/978-3-030-01228-1_12"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, R., Tresp, V.: Learning goal-oriented visual dialog via tempered policy gradient. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 868\u2013875. IEEE (2018)","DOI":"10.1109\/SLT.2018.8639546"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Wu, Q., Shen, C., Reid, I., van den Hengel, A.: Parallel attention: a unified framework for visual object discovery through dialogs and queries. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00447"}],"container-title":["Lecture Notes in Computer Science","Chinese Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-84186-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T21:44:40Z","timestamp":1673041480000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-84186-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030841850","9783030841867"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-84186-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"8 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China National Conference on Chinese Computational Linguistics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hohhot","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 August 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cncl2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cips-cl.org\/static\/CCL2021\/en\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"www.softconf.com","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"90","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"34% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}