{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T20:43:21Z","timestamp":1754599401617,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031199066"},{"type":"electronic","value":"9783031199073"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-19907-3_9","type":"book-chapter","created":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T06:07:32Z","timestamp":1673590052000},"page":"86-99","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Graph Strategy for\u00a0Interpretable Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Christina","family":"Sarkisyan","sequence":"first","affiliation":[]},{"given":"Mikhail","family":"Savelov","sequence":"additional","affiliation":[]},{"given":"Alexey K.","family":"Kovalev","sequence":"additional","affiliation":[]},{"given":"Aleksandr I.","family":"Panov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,14]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, V., Shetty, R., Fritz, M.: Towards causal VQA: revealing and reducing spurious correlations by invariant and covariant semantic editing. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00971"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D., Kembhavi, A.: Don\u2019t just assume; look and answer: overcoming priors for visual question answering. In: CVPR (2017)","DOI":"10.1109\/CVPR.2018.00522"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: CVPR (2015)","DOI":"10.1109\/ICCV.2015.279"},{"issue":"3","key":"9_CR4","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1109\/TPAMI.2019.2943456","volume":"43","author":"Q Cao","year":"2019","unstructured":"Cao, Q., Liang, X., Li, B., Lin, L.: Interpretable visual question answering by reasoning on dependency trees. IEEE Trans.Pattern Anal. Mach. Intell. 43(3), 887\u2013901 (2019)","journal-title":"IEEE Trans.Pattern Anal. Mach. Intell."},{"key":"9_CR5","unstructured":"Damodaran, V., et al.: Understanding the role of scene graphs in visual question answering. arXiv:2101.05479 (2021)"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Gordon, D., Kembhavi, A., Rastegari, M., Redmon, J., Fox, D., Farhadi, A.: IQA: visual question answering in interactive environments. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00430"},{"key":"9_CR7","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"9_CR8","doi-asserted-by":"publisher","first-page":"6730","DOI":"10.1109\/TIP.2021.3097180","volume":"30","author":"W Guo","year":"2021","unstructured":"Guo, W., Zhang, Y., Yang, J., Yuan, X.: Re-attention for visual question answering. IEEE Trans. Image Process. 30, 6730\u20136743 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: Vizwiz grand challenge: Answering visual questions from blind people. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"key":"9_CR10","doi-asserted-by":"publisher","first-page":"104194","DOI":"10.1016\/j.imavis.2021.104194","volume":"112","author":"F He","year":"2021","unstructured":"He, F., Wang, Y., Miao, X., Sun, X.: Interpretable visual reasoning: a survey. Image Vis. Comput. 112, 104194 (2021)","journal-title":"Image Vis. Comput."},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, Y., Mou, L., Xing, E., Xie, P.: PathVQA: 30000+ questions for medical visual question answering. arXiv:2003.10286 (2020)","DOI":"10.36227\/techrxiv.13127537"},{"key":"9_CR13","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: ICCV (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Hussain, Z., et al.: Automatic understanding of image and video advertisements. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.123"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., Van Der Maaten, L., Fei-Fei, L., Lawrence Zitnick, C., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"9_CR16","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/978-3-030-89820-5_3","volume-title":"Advances in Soft Computing","author":"DE Kirilenko","year":"2021","unstructured":"Kirilenko, D.E., Kovalev, A.K., Osipov, E., Panov, A.I.: Question answering for visual navigation in human-centered environments. In: Batyrshin, I., Gelbukh, A., Sidorov, G. (eds.) MICAI 2021. LNCS (LNAI), vol. 13068, pp. 31\u201345. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-89820-5_3"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Klein, G., Kim, Y., Deng, Y., Senellart, J., Rush, A.: OpenNMT: open-source toolkit for neural machine translation. In: ACL (2017)","DOI":"10.18653\/v1\/P17-4012"},{"key":"9_CR18","unstructured":"Kolve, E., et al.: Ai2-THOR: an interactive 3D environment for visual AI. arXiv:1712.05474 (2017)"},{"key":"9_CR19","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/978-3-030-86271-8_21","volume-title":"Hybrid Artificial Intelligent Systems","author":"AK Kovalev","year":"2021","unstructured":"Kovalev, A.K., Shaban, M., Chuganskaya, A.A., Panov, A.I.: Applying vector symbolic architecture and semiotic approach to visual dialog. In: Sanjurjo Gonz\u00e1lez, H., Pastor L\u00f3pez, I., Garc\u00eda Bringas, P., Quinti\u00e1n, H., Corchado, E. (eds.) HAIS 2021. LNCS (LNAI), vol. 12886, pp. 243\u2013255. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86271-8_21"},{"key":"9_CR20","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.cogsys.2021.09.001","volume":"71","author":"AK Kovalev","year":"2022","unstructured":"Kovalev, A.K., Shaban, M., Osipov, E., Panov, A.I.: Vector semiotic model for visual question answering. Cogn. Syst. Res. 71, 52\u201363 (2022)","journal-title":"Cogn. Syst. Res."},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Li, Q., Fu, J., Yu, D., Mei, T., Luo, J.: Tell-and-answer: towards explainable visual question answering using attributes and captions. arXiv:1801.09041 (2018)","DOI":"10.18653\/v1\/D18-1164"},{"key":"9_CR22","unstructured":"Lin, Z., et al.: Medical visual question answering: a survey. arXiv:2111.10056"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Lou, C., Han, W., Lin, Y., Zheng, Z.: Unsupervised vision-language parsing: Seamlessly bridging visual scene graphs with language structures via dependency relationships. arXiv:2203.14260 (2022)","DOI":"10.1109\/CVPR52688.2022.01516"},{"key":"9_CR24","unstructured":"Molnar, C.: Interpretable Machine Learning (2022)"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X.S., Wen, J.R.: Counterfactual vqa: A cause-effect look at language bias. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"9_CR26","series-title":"Studies in Computational Intelligence","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/978-3-030-60577-3_34","volume-title":"Advances in Neural Computation, Machine Learning, and Cognitive Research IV","author":"A Podtikhov","year":"2021","unstructured":"Podtikhov, A., Shaban, M., Kovalev, A.K., Panov, A.I.: Error analysis for visual question answering. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V., Tiumentsev, Y. (eds.) NEUROINFORMATICS 2020. SCI, vol. 925, pp. 283\u2013292. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-60577-3_34"},{"key":"9_CR27","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Shah, M., Chen, X., Rohrbach, M., Parikh, D.: Cycle-consistency for robust visual question answering. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00681"},{"key":"9_CR29","unstructured":"Su, W., Zhu, X., Cao, Y., Li, B., Lu, L., Wei, F., Dai, J.: Vl-BERT: pre-training of generic visual-linguistic representations. arXiv:1908.08530 (2019)"},{"key":"9_CR30","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.patrec.2018.02.013","volume":"126","author":"AS Toor","year":"2019","unstructured":"Toor, A.S., Wechsler, H., Nappi, M.: Biometric surveillance using visual question answering. Pattern Recogn. Lett. 126, 111\u2013118 (2019)","journal-title":"Pattern Recogn. Lett."},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Vatashsky, B.Z., Ullman, S.: VQA with no questions-answers training. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01039"},{"key":"9_CR32","unstructured":"Vedantam, R., Desai, K., Lee, S., Rohrbach, M., Batra, D., Parikh, D.: Probabilistic neural symbolic models for interpretable visual question answering. In: ICML (2019)"},{"key":"9_CR33","unstructured":"Xiong, P., You, Q., Yu, P., Liu, Z., Wu, Y.: Sa-VQA: structured alignment of visual and semantic representations for visual question answering. arXiv:2201.10654 (2022)"},{"key":"9_CR34","unstructured":"Yi, K., Wu, J., Gan, C., Torralba, A., Kohli, P., Tenenbaum, J.B.: Neural-symbolic VQA: disentangling reasoning from vision and language understanding. In: NIPS (2018)"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, P., Goyal, Y., Summers-Stay, D., Batra, D., Parikh, D.: Yin and Yang: balancing and answering binary visual questions. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.542"},{"key":"9_CR36","unstructured":"Zhou, B., Tian, Y., Sukhbaatar, S., Szlam, A., Fergus, R.: Simple baseline for visual question answering. arXiv:1512.02167 (2015)"}],"container-title":["Lecture Notes in Computer Science","Artificial General Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19907-3_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T07:04:29Z","timestamp":1673593469000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19907-3_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031199066","9783031199073"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19907-3_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"14 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial General Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Seattle, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2022","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":"agi2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/agi-conf.org\/2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"61","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":"51% - 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":"2,54","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":"3,6","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"13 additional posters were included","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}