{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T03:59:56Z","timestamp":1768708796244,"version":"3.49.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031059803","type":"print"},{"value":"9783031059810","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-05981-0_1","type":"book-chapter","created":{"date-parts":[[2022,5,9]],"date-time":"2022-05-09T12:02:50Z","timestamp":1652097770000},"page":"3-15","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["NewsKVQA: Knowledge-Aware News Video Question Answering"],"prefix":"10.1007","author":[{"given":"Pranay","family":"Gupta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manish","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,10]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Acharya, M., Kafle, K., Kanan, C.: TallyQA: answering complex counting questions. In: AAAI, vol. 33, pp. 8076\u20138084 (2019)","DOI":"10.1609\/aaai.v33i01.33018076"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Aditya, S., Yang, Y., Baral, C.: Explicit reasoning over end-to-end neural architectures for visual question answering. In: AAAI, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11324"},{"key":"1_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":"1_CR4","doi-asserted-by":"crossref","unstructured":"Fan, C., Zhang, X., Zhang, S., Wang, W., Zhang, C., Huang, H.: Heterogeneous memory enhanced multimodal attention model for video question answering. In: CVPR, pp. 1999\u20132007 (2019)","DOI":"10.1109\/CVPR.2019.00210"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Garcia, N., Otani, M., Chu, C., Nakashima, Y.: KnowIT VQA: answering knowledge-based questions about videos. In: AAAI, vol. 34, pp. 10826\u201310834 (2020)","DOI":"10.1609\/aaai.v34i07.6713"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Guadarrama, S., et al.: YouTube2Text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In: ICCV, pp. 2712\u20132719 (2013)","DOI":"10.1109\/ICCV.2013.337"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR8","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, pp. 804\u2013813 (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Jang, Y., Song, Y., Yu, Y., Kim, Y., Kim, G.: TGIF-QA: toward spatio-temporal reasoning in visual question answering. In: CVPR, pp. 2758\u20132766 (2017)","DOI":"10.1109\/CVPR.2017.149"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, J., Chen, Z., Lin, H., Zhao, X., Gao, Y.: Divide and conquer: question-guided spatio-temporal contextual attention for video question answering. In: AAAI, vol. 34, pp. 11101\u201311108 (2020)","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Kembhavi, A., Seo, M., Schwenk, D., Choi, J., Farhadi, A., Hajishirzi, H.: Are you smarter than a sixth grader? Textbook question answering for multimodal machine comprehension. In: CVPR, pp. 4999\u20135007 (2017)","DOI":"10.1109\/CVPR.2017.571"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Kim, J., Ma, M., Kim, K., Kim, S., Yoo, C.D.: Progressive attention memory network for movie story question answering. In: CVPR, pp. 8337\u20138346 (2019)","DOI":"10.1109\/CVPR.2019.00853"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Kim, K.M., Heo, M.O., Choi, S.H., Zhang, B.T.: DeepStory: video story QA by deep embedded memory networks. In: IJCAI, pp. 2016\u20132022 (2017)","DOI":"10.24963\/ijcai.2017\/280"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.L.: TVQA: localized, compositional video question answering. arXiv:1809.01696 (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Berg, T., Bansal, M.: TVQA+: spatio-temporal grounding for video question answering. In: ACL, pp. 8211\u20138225 (2020)","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"1_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Lu, P., Ji, L., Zhang, W., Duan, N., Zhou, M., Wang, J.: R-VQA: learning visual relation facts with semantic attention for visual question answering. In: KDD, pp. 1880\u20131889 (2018)","DOI":"10.1145\/3219819.3220036"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Maharaj, T., Ballas, N., Rohrbach, A., Courville, A., Pal, C.: A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering. In: CVPR, pp. 6884\u20136893 (2017)","DOI":"10.1109\/CVPR.2017.778"},{"key":"1_CR19","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":"1_CR20","doi-asserted-by":"crossref","unstructured":"Mun, J., Hongsuck Seo, P., Jung, I., Han, B.: MarioQA: answering questions by watching gameplay videos. In: ICCV, pp. 2867\u20132875 (2017)","DOI":"10.1109\/ICCV.2017.312"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"1_CR22","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399 (2015)"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Shah, S., Mishra, A., Yadati, N., Talukdar, P.P.: KVQA: knowledge-aware visual question answering. In: AAAI, vol. 33, pp. 8876\u20138884 (2019)","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: CVPR, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., Fidler, S.: MovieQA: understanding stories in movies through question-answering. In: CVPR, pp. 4631\u20134640 (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., Shen, C., Dick, A., 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":"1_CR27","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1109\/TPAMI.2017.2754246","volume":"40","author":"P Wang","year":"2017","unstructured":"Wang, P., Wu, Q., Shen, C., Dick, A., Van Den Hengel, A.: FVQA: fact-based visual question answering. TPAMI 40(10), 2413\u20132427 (2017)","journal-title":"TPAMI"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wang, P., Shen, C., Dick, A., 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":"1_CR29","doi-asserted-by":"crossref","unstructured":"Xu, D., et al.: Video question answering via gradually refined attention over appearance and motion. In: ACM MM, pp. 1645\u20131653 (2017)","DOI":"10.1145\/3123266.3123427"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: CVPR, pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: ActivityNet-QA: a dataset for understanding complex web videos via question answering. In: AAAI, vol. 33, pp. 9127\u20139134 (2019)","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chan, M., Liang, P.P., Tong, E., Morency, L.P.: Social-IQ: a question answering benchmark for artificial social intelligence. In: CVPR, pp. 8807\u20138817 (2019)","DOI":"10.1109\/CVPR.2019.00901"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: CVPR, pp. 6720\u20136731 (2019)","DOI":"10.1109\/CVPR.2019.00688"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Zeng, K.H., Chen, T.H., Chuang, C.Y., Liao, Y.H., Niebles, J.C., Sun, M.: Leveraging video descriptions to learn video question answering. In: AAAI, vol. 31 (2017)","DOI":"10.1609\/aaai.v31i1.11238"},{"key":"1_CR35","unstructured":"Zhu, Y., Zhang, C., R\u00e9, C., Fei-Fei, L.: Building a large-scale multimodal knowledge base system for answering visual queries. arXiv:1507.05670 (2015)"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-05981-0_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T13:36:07Z","timestamp":1710336967000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-05981-0_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031059803","9783031059810"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-05981-0_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chengdu","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/pakdd.net\/index.html","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"558","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":"121","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":"22% - 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":"3.75","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":"6.45","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)"}}]}}