{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:28:43Z","timestamp":1763202523960,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030865337"},{"type":"electronic","value":"9783030865344"}],"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\/978-3-030-86534-4_7","type":"book-chapter","created":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T06:05:57Z","timestamp":1630735557000},"page":"81-93","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory"],"prefix":"10.1007","author":[{"given":"Xuejiao","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Travers B.","family":"Child","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiong","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,5]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Hirschman, L., Gaizauskas, R.: Natural language question answering: the view from here. Nat. Lang. Eng. 7(4), 275 (2001)","key":"7_CR1","DOI":"10.1017\/S1351324901002807"},{"doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2556\u20132565 (2018)","key":"7_CR2","DOI":"10.18653\/v1\/P18-1238"},{"doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","key":"7_CR3","DOI":"10.1109\/ICCV.2015.279"},{"doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., et al.: From recognition to cognition: visual commonsense reasoning. In: Proceedings of the IEEE Conference on CVPR (2019)","key":"7_CR4","DOI":"10.1109\/CVPR.2019.00688"},{"doi-asserted-by":"crossref","unstructured":"Ben-younes, H., Cad\u00e8ne, R., Cord, M., Thome, N.: MUTAN: multimodal tucker fusion for visual question answering, CoRR (2017)","key":"7_CR5","DOI":"10.1109\/ICCV.2017.285"},{"unstructured":"Lin, J., Jain, U., et al.: TAB-VCR: tags and attributes based VCR baselines","key":"7_CR6"},{"doi-asserted-by":"crossref","unstructured":"Yu, F., Tang, J., et al.: ERNIE-ViL: knowledge enhanced vision-language representations through scene graph (2020)","key":"7_CR7","DOI":"10.1609\/aaai.v35i4.16431"},{"unstructured":"Lu, J., Batra, D., et al.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, pp. 13\u201323 (2019)","key":"7_CR8"},{"doi-asserted-by":"crossref","unstructured":"Lee, D.B., Lee, S., Jeong, W.T., Kim, D., Hwang, S.J.: Generating diverse and consistent QA pairs from contexts with information-maximizing hierarchical conditional VAEs, arXiv preprint arXiv:2005.13837 (2020)","key":"7_CR9","DOI":"10.18653\/v1\/2020.acl-main.20"},{"doi-asserted-by":"crossref","unstructured":"Chen, Y.-C., Li, L., et al.: UNITER: Learning universal image-text representations (2019)","key":"7_CR10","DOI":"10.1007\/978-3-030-58577-8_7"},{"unstructured":"Sabes, P.N., Jordan, M.I.: Advances in neural information processing systems. In: Tesauro, G., Touretzky, D., Leed, T. (eds.) Advances in Neural Information Processing Systems. Citeseer (1995)","key":"7_CR11"},{"unstructured":"Xiong, C., Merity, S., Socher, R.: Dynamic memory networks for visual and textual question answering. In: International Conference on Machine Learning. PMLR, pp. 2397\u20132406 (2016)","key":"7_CR12"},{"doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., et al.: Auto-encoding scene graphs for image captioning. In: Proceedings of the IEEE Conference on CVPR, pp. 10 685\u201310 694 (2019)","key":"7_CR13","DOI":"10.1109\/CVPR.2019.01094"},{"unstructured":"Kumar, A., et al.: Ask me anything: dynamic memory networks for natural language processing. In: International Conference on Machine Learning. PMLR, pp. 1378\u20131387 (2016)","key":"7_CR14"},{"unstructured":"Huang, Z., Xu, et al.: Bidirectional LSTM-CRF models for sequence tagging, arXiv preprint arXiv:1508.01991 (2015)","key":"7_CR15"},{"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 CVPR, pp. 770\u2013778 (2016)","key":"7_CR16","DOI":"10.1109\/CVPR.2016.90"},{"unstructured":"Devlin, J., Chang, M.-W., et al.: BERT: pre-training of deep bidirectional transformers for language understanding, arXiv preprint arXiv:1810.04805 (2018)","key":"7_CR17"},{"issue":"3","key":"7_CR18","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1093\/aob\/mcg029","volume":"91","author":"X Yin","year":"2003","unstructured":"Yin, X., Goudriaan, J., Lantinga, E.A., Vos, J., Spiertz, H.J.: A flexible sigmoid function of determinate growth. Ann. Bot. 91(3), 361\u2013371 (2003)","journal-title":"Ann. Bot."},{"key":"7_CR19","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, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"issue":"2","key":"7_CR20","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1023\/A:1010091220143","volume":"1","author":"R Rubinstein","year":"1999","unstructured":"Rubinstein, R.: The cross-entropy method for combinatorial and continuous optimization. Methodol. Comput. Appl. Probab. 1(2), 127\u2013190 (1999)","journal-title":"Methodol. Comput. Appl. Probab."},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization, arXiv preprint arXiv:1412.6980 (2014)","key":"7_CR21"},{"key":"7_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1007\/978-3-319-54193-8_13","volume-title":"Computer Vision \u2013 ACCV 2016","author":"P Henderson","year":"2017","unstructured":"Henderson, P., Ferrari, V.: End-to-end training of object class detectors for mean average precision. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10115, pp. 198\u2013213. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54193-8_13"},{"key":"7_CR23","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1007\/978-3-319-46448-0","volume-title":"ECCV 2016","author":"A Jabri","year":"2016","unstructured":"Jabri, A., Joulin, A., Van Der Maaten, L.: Revisiting visual question answering baselines. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 727\u2013739. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0"},{"doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","key":"7_CR24","DOI":"10.1109\/CVPR.2018.00636"},{"unstructured":"Kim, J.-H., On, K.-W., Lim, W., Kim, J., Ha, J.-W., Zhang, B.-T.: Hadamard product for low-rank bilinear pooling (2016)","key":"7_CR25"},{"doi-asserted-by":"crossref","unstructured":"Ben-Younes, H., Cadene, R., Cord, M., Thome, N.: MUTAN: multimodal tucker fusion for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2612\u20132620 (2017)","key":"7_CR26","DOI":"10.1109\/ICCV.2017.285"}],"container-title":["Lecture Notes in Computer Science","Big Data Analytics and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86534-4_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T19:49:24Z","timestamp":1725738564000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86534-4_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030865337","9783030865344"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86534-4_7","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":"5 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DaWaK","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Big Data Analytics and Knowledge Discovery","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2021","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":"dawak2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.dexa.org\/dawak2021","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"71","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":"12","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":"15","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":"17% - 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":"4","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)"}}]}}