{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:39:46Z","timestamp":1780497586907,"version":"3.54.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030898199","type":"print"},{"value":"9783030898205","type":"electronic"}],"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\/978-3-030-89820-5_3","type":"book-chapter","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T20:35:26Z","timestamp":1634762126000},"page":"31-45","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Question Answering for Visual Navigation in Human-Centered Environments"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4835-9413","authenticated-orcid":false,"given":"Daniil E.","family":"Kirilenko","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2180-0990","authenticated-orcid":false,"given":"Alexey K.","family":"Kovalev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0069-640X","authenticated-orcid":false,"given":"Evgeny","family":"Osipov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9747-3837","authenticated-orcid":false,"given":"Aleksandr I.","family":"Panov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,10,21]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. arXiv e-prints arXiv:1707.07998, July 2017","DOI":"10.1109\/CVPR.2018.00636"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"3_CR3","unstructured":"Bahdanau, D., Cho, K.H., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, pp. 1\u201315 (2015)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Das, A., et al.: Visual dialog. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.121"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Eliasmith, C.: How to Build a Brain: A Neural Architecture for Biological Cognition. Oxford University Press, New York (2013)","DOI":"10.1093\/acprof:oso\/9780199794546.001.0001"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in Visual Question Answering. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 2019, pp. 5351\u20135359 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: VizWiz grand challenge: answering visual questions from blind people. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3608\u20133617 (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"issue":"1","key":"3_CR9","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1016\/0167-2789(90)90087-6","volume":"42","author":"S Harnad","year":"1990","unstructured":"Harnad, S.: The symbol grounding problem. Physica D 42(1), 335\u2013346 (1990)","journal-title":"Physica D"},{"key":"3_CR10","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.215"},{"issue":"2","key":"3_CR12","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/s12559-009-9009-8","volume":"1","author":"P Kanerva","year":"2009","unstructured":"Kanerva, P.: Hyperdimensional computing: an introduction to computing in distributed representation with high-dimensional random vectors. Cogn. Comput. 1(2), 139\u2013159 (2009)","journal-title":"Cogn. Comput."},{"key":"3_CR13","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-00617-4_1","volume-title":"Artificial Intelligence","author":"G Kiselev","year":"2018","unstructured":"Kiselev, G., Kovalev, A., Panov, A.I.: Spatial reasoning and planning in sign-based world model. In: Kuznetsov, S.O., Osipov, G.S., Stefanuk, V.L. (eds.) RCAI 2018. CCIS, vol. 934, pp. 1\u201310. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00617-4_1"},{"key":"3_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1007\/978-3-030-26118-4_15","volume-title":"Interactive Collaborative Robotics","author":"G Kiselev","year":"2019","unstructured":"Kiselev, G., Panov, A.: Hierarchical psychologically inspired planning for human-robot interaction tasks. In: Ronzhin, A., Rigoll, G., Meshcheryakov, R. (eds.) ICR 2019. LNCS (LNAI), vol. 11659, pp. 150\u2013160. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-26118-4_15"},{"key":"3_CR15","unstructured":"Komer, B., Stewart, T.C., Voelker, A.R., Eliasmith, C.: A neural representation of continuous space using fractional binding. In: 41st Annual Meeting of the Cognitive Science Society. Cognitive Science Society, QC (2019)"},{"key":"3_CR16","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-27005-6_12","volume-title":"Artificial General Intelligence","author":"AK Kovalev","year":"2019","unstructured":"Kovalev, A.K., Panov, A.I.: Mental actions and modelling of reasoning in semiotic approach to AGI. In: Hammer, P., Agrawal, P., Goertzel, B., Ikl\u00e9, M. (eds.) AGI 2019. LNCS (LNAI), vol. 11654, pp. 121\u2013131. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-27005-6_12"},{"key":"3_CR17","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/978-3-030-52152-3_24","volume-title":"Artificial General Intelligence","author":"AK Kovalev","year":"2020","unstructured":"Kovalev, A.K., Panov, A.I., Osipov, E.: Hyperdimensional representations in semiotic approach to AGI. In: Goertzel, B., Panov, A.I., Potapov, A., Yampolskiy, R. (eds.) AGI 2020. LNCS (LNAI), vol. 12177, pp. 231\u2013241. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-52152-3_24"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Ku, A., Anderson, P., Patel, R., Ie, E., Baldridge, J.: Room-across-room: multilingual vision-and-language navigation with dense spatiotemporal grounding. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 4392\u20134412, November 2020","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"3_CR19","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"},{"key":"3_CR20","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1162\/1064546053278973","volume":"11","author":"MG Linda Smith","year":"2005","unstructured":"Linda Smith, M.G.: The development of embodied cognition: six lessons from babies. Artif. Life 11, 13\u201329 (2005)","journal-title":"Artif. Life"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Savva, M., et al.: Habitat: a platform for embodied AI research. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00943"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Osipov, G.S., Panov, A.I., Chudova, N.V.: Behavior control as a function of consciousness. I. world model and goal setting. J. Comput. Syst. Sci. Int. 53(4), 517\u2013529 (2014)","DOI":"10.1134\/S1064230714040121"},{"issue":"5","key":"3_CR23","doi-asserted-by":"publisher","first-page":"317","DOI":"10.3103\/S0147688218050040","volume":"45","author":"GS Osipov","year":"2018","unstructured":"Osipov, G.S., Panov, A.I.: Relationships and operations in a sign-based world model of the actor. Sci. Tech. Inf. Process. 45(5), 317\u2013330 (2018). https:\/\/doi.org\/10.3103\/S0147688218050040","journal-title":"Sci. Tech. Inf. Process."},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Osipov, G.S., Panov, A.I.: Rational behaviour planning of cognitive semiotic agent in dynamic environment. Sci. Tech. Inf. Process. 48(6) (2021)","DOI":"10.3103\/S0147688221060113"},{"issue":"6","key":"3_CR25","doi-asserted-by":"publisher","first-page":"404","DOI":"10.3103\/S0147688219060066","volume":"46","author":"AI Panov","year":"2019","unstructured":"Panov, A.I.: Goal setting and behavior planning for cognitive agents. Sci. Tech. Inf. Process. 46(6), 404\u2013415 (2019)","journal-title":"Sci. Tech. Inf. Process."},{"key":"3_CR26","first-page":"21","volume":"19","author":"AI Panov","year":"2017","unstructured":"Panov, A.I.: Behavior planning of intelligent agent with sign world model. Biol. Inspired Cogn. Archit. 19, 21\u201331 (2017)","journal-title":"Biol. Inspired Cogn. Archit."},{"issue":"3","key":"3_CR27","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1109\/72.377968","volume":"6","author":"TA Plate","year":"1995","unstructured":"Plate, T.A.: Holographic reduced representations. IEEE Trans. Neural Networks 6(3), 623\u2013641 (1995). https:\/\/doi.org\/10.1109\/72.377968","journal-title":"IEEE Trans. Neural Networks"},{"key":"3_CR28","doi-asserted-by":"publisher","first-page":"195608","DOI":"10.1109\/ACCESS.2020.3034524","volume":"8","author":"A Staroverov","year":"2020","unstructured":"Staroverov, A., Yudin, D.A., Belkin, I., Adeshkin, V., Solomentsev, Y.K., Panov, A.I.: Real-time object navigation with deep neural networks and hierarchical reinforcement learning. IEEE Access 8, 195608\u2013195621 (2020)","journal-title":"IEEE Access"},{"key":"3_CR29","first-page":"229","volume":"8","author":"RJ Williams","year":"2004","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (2004)","journal-title":"Mach. Learn."},{"key":"3_CR30","unstructured":"Yi, K., Wu, J., Gan, C., Torralba, A., Kohli, P., Tenenbaum, J.B.: Neural-symbolic VQA: disentangling reasoning from vision and language understanding. arXiv e-prints arXiv:1810.02338, October 2018"},{"key":"3_CR31","doi-asserted-by":"publisher","first-page":"107563","DOI":"10.1016\/j.patcog.2020.107563","volume":"108","author":"J Yu","year":"2020","unstructured":"Yu, J., Zhu, Z., Wang, Y., Zhang, W., Hu, Y., Tan, J.: Cross-modal knowledge reasoning for knowledge-based visual question answering. Pattern Recogn. 108, 107563 (2020)","journal-title":"Pattern Recogn."},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. CoRR abs\/1811.10830 (2018)","DOI":"10.1109\/CVPR.2019.00688"}],"container-title":["Lecture Notes in Computer Science","Advances in Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-89820-5_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T01:08:21Z","timestamp":1673572101000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-89820-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030898199","9783030898205"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-89820-5_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"21 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Mexican International Conference on Artificial Intelligence","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":"25 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 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":"micai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.micai.org\/2021\/","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":"129","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":"58","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":"45% - 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)"}}]}}