{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T15:42:30Z","timestamp":1782574950329,"version":"3.54.5"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030883607","type":"print"},{"value":"9783030883614","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\/978-3-030-88361-4_9","type":"book-chapter","created":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T07:07:22Z","timestamp":1632899242000},"page":"146-162","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["Zero-Shot Visual Question Answering Using Knowledge Graph"],"prefix":"10.1007","author":[{"given":"Zhuo","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaoyan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxia","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeff Z.","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zonggang","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huajun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,30]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Kembhavi, A., Batra, D., Parikh, D.: C-VQA: a compositional split of the visual question answering (VQA) v1.0 dataset. CoRR arXiv:1704.08243 (2017)","DOI":"10.1007\/s11263-016-0966-6"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"9_CR4","unstructured":"Bordes, A., Usunier, N., Garc\u00eda-Dur\u00e1n, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: NIPS, pp. 2787\u20132795 (2013)"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Chen, J., Geng, Y., Chen, Z., Horrocks, I., Pan, J.Z., Chen, H.: Knowledge-aware zero-shot learning: survey and perspective. In: IJCAI Survey Track (2021)","DOI":"10.24963\/ijcai.2021\/597"},{"key":"9_CR6","unstructured":"Chen, L., Gan, Z., Cheng, Y., Li, L., Carin, L., Liu, J.: Graph optimal transport for cross-domain alignment. In: ICML, vol. 119, pp. 1542\u20131553 (2020)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Chen, W., Zha, H., Chen, Z., Xiong, W., Wang, H., Wang, W.Y.: HybridQA: a dataset of multi-hop question answering over tabular and textual data. In: EMNLP, pp. 1026\u20131036 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.91"},{"key":"9_CR8","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL, pp. 4171\u20134186 (2019)"},{"key":"9_CR9","doi-asserted-by":"publisher","first-page":"103985","DOI":"10.1016\/j.imavis.2020.103985","volume":"103","author":"MR Farazi","year":"2020","unstructured":"Farazi, M.R., Khan, S.H., Barnes, N.: From known to the unknown: transferring knowledge to answer questions about novel visual and semantic concepts. Image Vis. Comput. 103, 103985 (2020)","journal-title":"Image Vis. Comput."},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Geng, Y., et al.: OntoZSL: ontology-enhanced zero-shot learning. In: WWW, pp. 3325\u20133336 (2021)","DOI":"10.1145\/3442381.3450042"},{"key":"9_CR11","unstructured":"Geng, Y., Chen, J., Chen, Z., Pan, J.Z., Yuan, Z., Chen, H.: K-ZSL: resources for knowledge-driven zero-shot learning. CoRR arXiv:2106.15047 (2021)"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Hu, H., Chao, W., Sha, F.: Learning answer embeddings for visual question answering. In: CVPR, pp. 5428\u20135436 (2018)","DOI":"10.1109\/CVPR.2018.00569"},{"key":"9_CR13","unstructured":"Kim, J., Jun, J., Zhang, B.: Bilinear attention networks. In: NeurIPS, pp. 1571\u20131581 (2018)"},{"key":"9_CR14","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: NIPS, pp. 289\u2013297 (2016)"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Malaviya, C., Bhagavatula, C., Bosselut, A., Choi, Y.: Commonsense knowledge base completion with structural and semantic context. In: AAAI, pp. 2925\u20132933 (2020)","DOI":"10.1609\/aaai.v34i03.5684"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: OK-VQA: A visual question answering benchmark requiring external knowledge. In: CVPR, pp. 3195\u20133204 (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"9_CR17","unstructured":"Narasimhan, M., Lazebnik, S., Schwing, A.G.: Out of the box: reasoning with graph convolution nets for factual visual question answering. In: NeurIPS, pp. 2659\u20132670 (2018)"},{"key":"9_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1007\/978-3-030-01237-3_28","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Narasimhan","year":"2018","unstructured":"Narasimhan, M., Schwing, A.G.: Straight to the facts: learning knowledge base retrieval for factual visual question answering. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 460\u2013477. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_28"},{"key":"9_CR19","doi-asserted-by":"publisher","unstructured":"Pan, J., et al. (eds.): Reasoning Web: Logical Foundation of Knowledge Graph Construction and Querying Answering. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-49493-7","DOI":"10.1007\/978-3-319-49493-7"},{"key":"9_CR20","doi-asserted-by":"publisher","unstructured":"Pan, J., Vetere, G., Gomez-Perez, J., Wu, H. (eds.): Exploiting Linked Data and Knowledge Graphs for Large Organisations. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-45654-6","DOI":"10.1007\/978-3-319-45654-6"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: EMNLP, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Ramakrishnan, S.K., Pal, A., Sharma, G., Mittal, A.: An empirical evaluation of visual question answering for novel objects. In: CVPR, pp. 7312\u20137321 (2017)","DOI":"10.1109\/CVPR.2017.773"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Shah, S., Mishra, A., Yadati, N., Talukdar, P.P.: KVQA: knowledge-aware visual question answering. In: AAAI, pp. 8876\u20138884 (2019)","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"9_CR24","unstructured":"Shevchenko, V., Teney, D., Dick, A.R., van den Hengel, A.: Visual question answering with prior class semantics. CoRR arXiv:2005.01239 (2020)"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Teney, D., van den Hengel, A.: Zero-shot visual question answering. CoRR arXiv:1611.05546 (2016)","DOI":"10.1109\/MSP.2017.2739826"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., Shen, C., Dick, A.R., van den Hengel, A.: Explicit knowledge-based reasoning for visual question answering. In: IJCAI, pp. 1290\u20131296 (2017)","DOI":"10.24963\/ijcai.2017\/179"},{"issue":"10","key":"9_CR27","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.R., van den Hengel, A.: FVQA: fact-based visual question answering. IEEE TPAMI 40(10), 2413\u20132427 (2018)","journal-title":"IEEE TPAMI"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wang, P., Shen, C., Dick, A.R., van den Hengel, A.: Ask me anything: free-form visual question answering based on knowledge from external sources. In: CVPR, pp. 4622\u20134630 (2016)","DOI":"10.1109\/CVPR.2016.500"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.J.: Stacked attention networks for image question answering. In: CVPR, pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"9_CR30","unstructured":"Ye, Z., Chen, Q., Wang, W., Ling, Z.: Align, mask and select: a simple method for incorporating commonsense knowledge into language representation models. CoRR arXiv:1908.06725 (2019)"},{"key":"9_CR31","doi-asserted-by":"crossref","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: IJCAI, pp. 1097\u20131103 (2020)","DOI":"10.24963\/ijcai.2020\/153"}],"container-title":["Lecture Notes in Computer Science","The Semantic Web \u2013 ISWC 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-88361-4_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T00:09:41Z","timestamp":1725840581000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-88361-4_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030883607","9783030883614"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-88361-4_9","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":"30 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISWC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Semantic Web Conference","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":"24 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 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":"semweb2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iswc2021.semanticweb.org\/","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":"202","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":"42","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":"21% - 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":"3.5","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":"2.5","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)"}}]}}