{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T19:34:07Z","timestamp":1783712047276,"version":"3.55.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T00:00:00Z","timestamp":1705363200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T00:00:00Z","timestamp":1705363200000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s00530-023-01240-5","type":"journal-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T21:03:14Z","timestamp":1705352594000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Video question answering via traffic knowledge database and question classification"],"prefix":"10.1007","volume":"30","author":[{"given":"Xiaoyong","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weifeng","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuefen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,16]]},"reference":[{"key":"1240_CR1","doi-asserted-by":"crossref","unstructured":"Jang, Y., Song, Y., Yu, Y., Kim, Y., Kim, G.: \u201cTgif-qa: Toward spatio-temporal reasoning in visual question answering,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, pp.\u00a02758\u20132766, (2017)","DOI":"10.1109\/CVPR.2017.149"},{"key":"1240_CR2","doi-asserted-by":"crossref","unstructured":"Xu, L., Huang, H., Liu, J.: \u201cSutd-trafficqa: A question answering benchmark and an efficient network for video reasoning over traffic events,\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.\u00a09878\u20139888, (2021)","DOI":"10.1109\/CVPR46437.2021.00975"},{"key":"1240_CR3","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/s11263-017-1033-7","volume":"124","author":"L Zhu","year":"2017","unstructured":"Zhu, L., Xu, Z., Yang, Y., Hauptmann, A.G.: Uncovering the temporal context for video question answering. Int. J. Comput. Vision 124, 409\u2013421 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"1240_CR4","doi-asserted-by":"crossref","unstructured":"Xiao, J., Zhou, P., Chua, T.-S., Yan, S.: \u201cVideo graph transformer for video question answering,\u201d in Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXVI, pp.\u00a039\u201358, Springer, (2022)","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"1240_CR5","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhao, Z., Xiao, J., Wu, F., Zhang, H., He, X., Zhuang, Y.: \u201cVideo question answering via gradually refined attention over appearance and motion,\u201d in Proceedings of the 25th ACM international conference on Multimedia, pp.\u00a01645\u20131653, (2017)","DOI":"10.1145\/3123266.3123427"},{"key":"1240_CR6","doi-asserted-by":"crossref","unstructured":"Jin, W., Zhao, Z., Li, Y., Li, J., Xiao, J., Zhuang, Y.: \u201cVideo question answering via knowledge-based progressive spatial-temporal attention network,\u201d ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), vol.\u00a015, no.\u00a02s, pp.\u00a01\u201322, (2019)","DOI":"10.1145\/3321505"},{"key":"1240_CR7","doi-asserted-by":"crossref","unstructured":"Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.: \u201cDbpedia: A nucleus for a web of open data,\u201d in The Semantic Web: 6th International Semantic Web Conference, 2nd Asian Semantic Web Conference, ISWC 2007+ ASWC 2007, Busan, Korea, November 11-15, 2007. Proceedings, pp.\u00a0722\u2013735, Springer, (2007)","DOI":"10.1007\/978-3-540-76298-0_52"},{"key":"1240_CR8","doi-asserted-by":"crossref","unstructured":"Bollacker, K., Evans, C., Paritosh, P., Sturge, T., Taylor, J.: \u201cFreebase: a collaboratively created graph database for structuring human knowledge,\u201d in Proceedings of the 2008 ACM SIGMOD international conference on Management of data, pp.\u00a01247\u20131250, (2008)","DOI":"10.1145\/1376616.1376746"},{"key":"1240_CR9","unstructured":"Malinowski, M., Fritz, M.: \u201cA multi-world approach to question answering about real-world scenes based on uncertain input,\u201d Advances in neural information processing systems, vol.\u00a027, (2014)"},{"issue":"12","key":"1240_CR10","doi-asserted-by":"publisher","first-page":"3618","DOI":"10.1073\/pnas.1422953112","volume":"112","author":"D Geman","year":"2015","unstructured":"Geman, D., Geman, S., Hallonquist, N., Younes, L.: Visual turing test for computer vision systems. Proc. Natl. Acad. Sci. 112(12), 3618\u20133623 (2015)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"1240_CR11","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne\u00a0Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: \u201cLong-term recurrent convolutional networks for visual recognition and description,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, pp.\u00a02625\u20132634, (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"1240_CR12","unstructured":"Karpathy, A., Joulin, A., Fei-Fei, L.\u00a0F.: \u201cDeep fragment embeddings for bidirectional image sentence mapping,\u201d Advances in neural information processing systems, vol.\u00a027, (2014)"},{"key":"1240_CR13","doi-asserted-by":"crossref","unstructured":"Malinowski, M., Rohrbach, M., Fritz, M.: \u201cAsk your neurons: A neural-based approach to answering questions about images,\u201d in Proceedings of the IEEE international conference on computer vision, pp.\u00a01\u20139, (2015)","DOI":"10.1109\/ICCV.2015.9"},{"key":"1240_CR14","unstructured":"Liu, R., Zhuang, L., Yu, Z., Jiang, Z., Bai, T.: \u201cQuestion-relationship guided graph attention network for visual question answer,\u201d Multimedia Systems, pp.\u00a01\u201312, (2022)"},{"key":"1240_CR15","doi-asserted-by":"crossref","unstructured":"Li, Q., Xiao, F., Bhanu, B., Sheng, B., Hong, R.: \u201cInner knowledge-based img2doc scheme for visual question answering,\u201d ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), vol.\u00a018, no.\u00a03, pp.\u00a01\u201321, (2022)","DOI":"10.1145\/3489142"},{"key":"1240_CR16","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.\u00a0H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: \u201cMultimodal compact bilinear pooling for visual question answering and visual grounding,\u201d arXiv preprint arXiv:1606.01847, (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"1240_CR17","unstructured":"Kim, J.-H., Lee, S.-W., Kwak, D., Heo, M.-O., Kim, J., Ha, J.-W., Zhang, B.-T.: \u201cMultimodal residual learning for visual QA,\u201d Advances in neural information processing systems, vol.\u00a029, (2016)"},{"key":"1240_CR18","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: \u201cShow, attend and tell: Neural image caption generation with visual attention,\u201d in International conference on machine learning, pp.\u00a02048\u20132057, PMLR, (2015)"},{"key":"1240_CR19","doi-asserted-by":"crossref","unstructured":"Lin, X., Parikh, D.: \u201cLeveraging visual question answering for image-caption ranking,\u201d in Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14, pp.\u00a0261\u2013277, Springer, (2016)","DOI":"10.1007\/978-3-319-46475-6_17"},{"key":"1240_CR20","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Groth, O., Bernstein, M., Fei-Fei, L.: \u201cVisual7w: Grounded question answering in images,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, pp.\u00a04995\u20135004, (2016)","DOI":"10.1109\/CVPR.2016.540"},{"key":"1240_CR21","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: \u201cStacked attention networks for image question answering,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, pp.\u00a021\u201329, (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"1240_CR22","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., Zhang, L.: \u201cBottom-up and top-down attention for image captioning and visual question answering,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, pp.\u00a06077\u20136086, (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"1240_CR23","doi-asserted-by":"crossref","unstructured":"Ye, Y., Zhao, Z., Li, Y., Chen, L., Xiao, J., Zhuang, Y.: \u201cVideo question answering via attribute-augmented attention network learning,\u201d in Proceedings of the 40th International ACM SIGIR conference on Research and Development in Information Retrieval, pp.\u00a0829\u2013832, (2017)","DOI":"10.1145\/3077136.3080655"},{"key":"1240_CR24","doi-asserted-by":"crossref","unstructured":"Na, S., Lee, S., Kim, J., Kim, G.: \u201cA read-write memory network for movie story understanding,\u201d in Proceedings of the IEEE International Conference on Computer Vision, pp.\u00a0677\u2013685, (2017)","DOI":"10.1109\/ICCV.2017.80"},{"key":"1240_CR25","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Zhang, Z., Xiao, S., Yu, Z., Yu, J., Cai, D., Wu, F., Zhuang, Y.: \u201cOpen-ended long-form video question answering via adaptive hierarchical reinforced networks.,\u201d in IJCAI, vol.\u00a02, p.\u00a08, (2018)","DOI":"10.24963\/ijcai.2018\/512"},{"key":"1240_CR26","doi-asserted-by":"crossref","unstructured":"Gao, J., Ge, R., Chen, K., Nevatia, R.: \u201cMotion-appearance co-memory networks for video question answering,\u201d in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a06576\u20136585, (2018)","DOI":"10.1109\/CVPR.2018.00688"},{"key":"1240_CR27","unstructured":"Guo, Z., Zhao, J., Jiao, L., Liu, X., Liu, F.: \u201cA universal quaternion hypergraph network for multimodal video question answering,\u201d IEEE Transactions on Multimedia, (2021)"},{"issue":"1","key":"1240_CR28","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s00530-021-00805-6","volume":"28","author":"X Li","year":"2022","unstructured":"Li, X., Wu, A., Han, Y.: Complementary spatiotemporal network for video question answering. Multimed. Syst. 28(1), 161\u2013169 (2022)","journal-title":"Multimed. Syst."},{"key":"1240_CR29","doi-asserted-by":"publisher","first-page":"108959","DOI":"10.1016\/j.patcog.2022.108959","volume":"132","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Zhang, X., Huang, F., Shen, S., Tian, P., Li, L., Li, Z.: Dynamic self-attention with vision synchronization networks for video question answering. Pattern Recogn. 132, 108959 (2022)","journal-title":"Pattern Recogn."},{"key":"1240_CR30","doi-asserted-by":"crossref","unstructured":"Lei, J., Li, L., Zhou, L., Gan, Z., Berg, T.\u00a0L., Bansal, M., Liu, J.: \u201cLess is more: Clipbert for video-and-language learning via sparse sampling,\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.\u00a07331\u20137341, (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"issue":"10","key":"1240_CR31","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1145\/2629489","volume":"57","author":"D Vrande\u010di\u0107","year":"2014","unstructured":"Vrande\u010di\u0107, D., Kr\u00f6tzsch, M.: Wikidata: a free collaborative knowledgebase. Commun. ACM 57(10), 78\u201385 (2014)","journal-title":"Commun. ACM"},{"key":"1240_CR32","unstructured":"Kipf, T.\u00a0N., Welling, M.: \u201cSemi-supervised classification with graph convolutional networks,\u201d arXiv preprint arXiv:1609.02907, (2016)"},{"key":"1240_CR33","unstructured":"Mahdisoltani, F., Biega, J., Suchanek, F.: \u201cYago3: A knowledge base from multilingual wikipedias,\u201d in 7th biennial conference on innovative data systems research, CIDR Conference, (2014)"},{"key":"1240_CR34","doi-asserted-by":"crossref","unstructured":"Chen, X., Shrivastava, A., Gupta, A.: \u201cNeil: Extracting visual knowledge from web data,\u201d in Proceedings of the IEEE international conference on computer vision, pp.\u00a01409\u20131416, (2013)","DOI":"10.1109\/ICCV.2013.178"},{"issue":"12","key":"1240_CR35","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1145\/1409360.1409378","volume":"51","author":"O Etzioni","year":"2008","unstructured":"Etzioni, O., Banko, M., Soderland, S., Weld, D.S.: Open information extraction from the web. Commun. ACM 51(12), 68\u201374 (2008)","journal-title":"Commun. ACM"},{"issue":"4","key":"1240_CR36","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d","volume":"22","author":"H Liu","year":"2004","unstructured":"Liu, H., Singh, P.: Conceptnet-a practical commonsense reasoning tool-kit. BT Technol. J. 22(4), 211\u2013226 (2004)","journal-title":"BT Technol. J."},{"key":"1240_CR37","unstructured":"Bordes, A., Usunier, N., Chopra, S., Weston, J.: \u201cLarge-scale simple question answering with memory networks,\u201d arXiv preprint arXiv:1506.02075, (2015)"},{"key":"1240_CR38","doi-asserted-by":"crossref","unstructured":"Bordes, A., Weston, J., Usunier, N.: \u201cOpen question answering with weakly supervised embedding models,\u201d in Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2014, Nancy, France, September 15-19, 2014. Proceedings, Part I 14, pp.\u00a0165\u2013180, Springer, (2014)","DOI":"10.1007\/978-3-662-44848-9_11"},{"key":"1240_CR39","doi-asserted-by":"crossref","unstructured":"Iyyer, M., Yih, W.-t., Chang, M.-W.: \u201cSearch-based neural structured learning for sequential question answering,\u201d in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp.\u00a01821\u20131831, (2017)","DOI":"10.18653\/v1\/P17-1167"},{"key":"1240_CR40","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1162\/tacl_a_00088","volume":"4","author":"S Reddy","year":"2016","unstructured":"Reddy, S., T\u00e4ckstr\u00f6m, O., Collins, M., Kwiatkowski, T., Das, D., Steedman, M., Lapata, M.: Transforming dependency structures to logical forms for semantic parsing. Trans. Assoc. Comput. Linguist. 4, 127\u2013140 (2016)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"1240_CR41","doi-asserted-by":"crossref","unstructured":"Xiao, C., Dymetman, M., Gardent, C.: \u201cSequence-based structured prediction for semantic parsing,\u201d in Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp.\u00a01341\u20131350, (2016)","DOI":"10.18653\/v1\/P16-1127"},{"key":"1240_CR42","first-page":"127","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: \u201cTowards real-time object detection with region proposal networks\u201d. Adv Neural inf Proc Syst. 28 (2015)","journal-title":"Advances in neural information processing systems."},{"key":"1240_CR43","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: \u201cBert: Pre-training of deep bidirectional transformers for language understanding,\u201d arXiv preprint arXiv:1810.04805, (2018)"},{"key":"1240_CR44","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: \u201cFaster r-cnn: Towards real-time object detection with region proposal networks,\u201d Advances in neural information processing systems, vol.\u00a028, (2015)"},{"key":"1240_CR45","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: \u201cDeep residual learning for image recognition,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, pp.\u00a0770\u2013778, (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1240_CR46","first-page":"2804","volume":"36","author":"J Xiao","year":"2022","unstructured":"Xiao, J., Yao, A., Liu, Z., Li, Y., Ji, W., Chua, T.-S.: Video as conditional graph hierarchy for multi-granular question answering. Proc AAAI Conf Artif Intell 36, 2804\u20132812 (2022)","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"1240_CR47","unstructured":"Ren, M., Kiros, R., Zemel, R.: \u201cExploring models and data for image question answering,\u201d Advances in neural information processing systems, vol.\u00a028, (2015)"},{"key":"1240_CR48","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: \u201cQuo vadis, action recognition? a new model and the kinetics dataset,\u201d in proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a06299\u20136308, (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"1240_CR49","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.\u00a0L.: \u201cTvqa: Localized, compositional video question answering,\u201d arXiv preprint arXiv:1809.01696, (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"1240_CR50","doi-asserted-by":"crossref","unstructured":"Le, T.\u00a0M., Le, V., Venkatesh, S., Tran, T.: \u201cHierarchical conditional relation networks for video question answering,\u201d in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp.\u00a09972\u20139981, (2020)","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"1240_CR51","doi-asserted-by":"crossref","unstructured":"Yang, Z., Garcia, N., Chu, C., Otani, M., Nakashima, Y., Takemura, H.: \u201cBert representations for video question answering,\u201d in Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp.\u00a01556\u20131565, (2020)","DOI":"10.1109\/WACV45572.2020.9093596"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01240-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-023-01240-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01240-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T06:33:04Z","timestamp":1708151584000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-023-01240-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,16]]},"references-count":51,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["1240"],"URL":"https:\/\/doi.org\/10.1007\/s00530-023-01240-5","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2880996\/v1","asserted-by":"object"}]},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,16]]},"assertion":[{"value":"1 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"14"}}