{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T04:59:07Z","timestamp":1742965147199,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819985364"},{"type":"electronic","value":"9789819985371"}],"license":[{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8537-1_39","type":"book-chapter","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:02:17Z","timestamp":1703530937000},"page":"485-496","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EKGRL: Entity-Based Knowledge Graph Representation Learning for\u00a0Fact-Based Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Yongjian","family":"Ren","sequence":"first","affiliation":[]},{"given":"Xiaotang","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Kaiqi","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,26]]},"reference":[{"key":"39_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., Zhang, L.: 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 (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"39_CR3","unstructured":"Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Burges, C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol. 26. Curran Associates, Inc. (2013). https:\/\/proceedings.neurips.cc\/paper\/2013\/file\/1cecc7a77928ca8133fa24680a88d2f9-Paper.pdf"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Chen, J., Geng, Y., Pan, J.Z., Chen, H.: Zero-shot visual question answering using knowledge graph (2021)","DOI":"10.1007\/978-3-030-88361-4_9"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. In: EMNLP (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"39_CR6","doi-asserted-by":"publisher","unstructured":"Goyal, Y., Khot, T., Summers\u00a0Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering, pp. 6325\u20136334 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.670","DOI":"10.1109\/CVPR.2017.670"},{"key":"39_CR7","doi-asserted-by":"crossref","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 (2015). https:\/\/api.semanticscholar.org\/CorpusID:206594692","DOI":"10.1109\/CVPR.2016.90"},{"key":"39_CR8","unstructured":"Hochreiter, S.: Long short term memory (1995). https:\/\/api.semanticscholar.org\/CorpusID:261210188"},{"key":"39_CR9","doi-asserted-by":"publisher","unstructured":"Kafle, K., Kanan, C.: Answer-type prediction for visual question answering. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4976\u20134984 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.538","DOI":"10.1109\/CVPR.2016.538"},{"key":"39_CR10","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31. Curran Associates, Inc. (2018). https:\/\/proceedings.neurips.cc\/paper\/2018\/file\/96ea64f3a1aa2fd00c72faacf0cb8ac9-Paper.pdf"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"39_CR12","unstructured":"Malinowski, M., Fritz, M.: A multi-world approach to question answering about real-world scenes based on uncertain input. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol. 27. Curran Associates, Inc. (2014). https:\/\/proceedings.neurips.cc\/paper\/2014\/file\/d516b13671a4179d9b7b458a6ebdeb92-Paper.pdf"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: OK-VQA: a visual question answering benchmark requiring external knowledge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"39_CR14","unstructured":"Narasimhan, M., Lazebnik, S., Schwing, A.: Out of the box: reasoning with graph convolution nets for factual visual question answering. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31. Curran Associates, Inc. (2018). https:\/\/proceedings.neurips.cc\/paper\/2018\/file\/c26820b8a4c1b3c2aa868d6d57e14a79-Paper.pdf"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Narasimhan, M., Schwing, A.G.: Straight to the facts: learning knowledge base retrieval for factual visual question answering. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 451\u2013468 (2018)","DOI":"10.1007\/978-3-030-01237-3_28"},{"key":"39_CR16","doi-asserted-by":"publisher","unstructured":"Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, pp. 1532\u20131543. Association for Computational Linguistics (2014). https:\/\/doi.org\/10.3115\/v1\/D14-1162. https:\/\/aclanthology.org\/D14-1162","DOI":"10.3115\/v1\/D14-1162"},{"key":"39_CR17","unstructured":"Ren, M., Kiros, R., Zemel, R.S.: Exploring models and data for image question answering. In: Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 2, NIPS 2015. pp. 2953\u20132961. MIT Press, Cambridge (2015)"},{"key":"39_CR18","doi-asserted-by":"publisher","unstructured":"Shah, S., Mishra, A., Yadati, N., Talukdar, P.P.: KVQA: knowledge-aware visual question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, pp. 8876\u20138884 (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.33018876. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/4915","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"39_CR19","doi-asserted-by":"publisher","unstructured":"Shih, K.J., Singh, S., Hoiem, D.: Where to look: focus regions for visual question answering. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4613\u20134621 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.499","DOI":"10.1109\/CVPR.2016.499"},{"issue":"10","key":"39_CR20","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1109\/TPAMI.2017.2754246","volume":"40","author":"P Wang","year":"2018","unstructured":"Wang, P., Wu, Q., Shen, C., Dick, A., van den Hengel, A.: FVQA: fact-based visual question answering. IEEE Trans. Pattern Anal. Mach. Intell. 40(10), 2413\u20132427 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2754246","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., Shen, C., Dick, A., Van Den\u00a0Henge, A.: Explicit knowledge-based reasoning for visual question answering. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence, IJCAI 2017, pp. 1290\u20131296. AAAI Press (2017)","DOI":"10.24963\/ijcai.2017\/179"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wang, P., Shen, C., Dick, A., van\u00a0den Hengel, A.: Ask me anything: free-form visual question answering based on knowledge from external sources. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.500"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"39_CR24","unstructured":"Zhou, B., Tian, Y., Sukhbaatar, S., Szlam, A., Fergus, R.: Simple baseline for visual question answering. CoRR abs\/1512.02167 (2015). http:\/\/arxiv.org\/abs\/1512.02167"},{"key":"39_CR25","doi-asserted-by":"publisher","unstructured":"Zhu, Z., Yu, J., Wang, Y., Sun, Y., Hu, Y., Wu, Q.: Mucko: multi-layer cross-modal knowledge reasoning for fact-based visual question answering. In: Bessiere, C. (ed.) Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020, pp. 1097\u20131103. International Joint Conferences on Artificial Intelligence Organization (2020). https:\/\/doi.org\/10.24963\/ijcai.2020\/153","DOI":"10.24963\/ijcai.2020\/153"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8537-1_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:12:10Z","timestamp":1703531530000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8537-1_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,26]]},"ISBN":["9789819985364","9789819985371"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8537-1_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,26]]},"assertion":[{"value":"26 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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)"}}]}}