{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T19:57:06Z","timestamp":1742932626645,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031203084"},{"type":"electronic","value":"9783031203091"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20309-1_33","type":"book-chapter","created":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T06:11:35Z","timestamp":1670393495000},"page":"380-392","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Alternative Attention for\u00a0Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Xumeng","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenya","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,8]]},"reference":[{"key":"33_CR1","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, pp. 4971\u20134980. Computer Vision Foundation\/IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00522"},{"key":"33_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. Computer Vision Foundation \/ IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV, pp. 2425\u20132433. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Ben-younes, H., Cad\u00e8ne, R., Cord, M., Thome, N.: MUTAN: multimodal tucker fusion for visual question answering. In: ICCV, pp. 2631\u20132639. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.285"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Bigham, J.P., et al.: Vizwiz: nearly real-time answers to visual questions. In: ACM, pp. 333\u2013342 (2010)","DOI":"10.1145\/1866029.1866080"},{"key":"33_CR6","unstructured":"Bordes, A., Usunier, N., Garc\u00eda-Dur\u00e1n, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Advances in Neural Information Processing Systems, pp. 2787\u20132795 (2013)"},{"key":"33_CR7","unstructured":"Bruna, J., Zaremba, W., Szlam, A., LeCun, Y.: Spectral networks and locally connected networks on graphs. In: ICLR (2014)"},{"key":"33_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/978-3-030-58452-8_6","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Chen","year":"2020","unstructured":"Chen, S., Jiang, M., Yang, J., Zhao, Q.: AiR: attention with reasoning capability. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 91\u2013107. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_6"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merrienboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. In: EMNLP, pp. 103\u2013111. Association for Computational Linguistics (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"33_CR10","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.cviu.2017.10.001","volume":"163","author":"A Das","year":"2017","unstructured":"Das, A., Agrawal, H., Zitnick, L., Parikh, D., Batra, D.: Human attention in visual question answering: do humans and deep networks look at the same regions? Comput. Vis. Image Underst. 163, 90\u2013100 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"33_CR11","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, pp. 457\u2013468. The Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Gao, P., et al.: Dynamic fusion with intra- and inter-modality attention flow for visual question answering. In: CVPR, pp. 6639\u20136648. Computer Vision Foundation \/ IEEE (2019)","DOI":"10.1109\/CVPR.2019.00680"},{"key":"33_CR13","unstructured":"Gao, P., You, H., Zhang, Z., Wang, X., Li, H.: Multi-modality latent interaction network for visual question answering. In: ICCV, pp. 5824\u20135834. IEEE (2019)"},{"key":"33_CR14","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, pp. 6325\u20136334. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Gui, L., Wang, B., Huang, Q., Hauptmann, A., Bisk, Y., Gao, J.: Kat: a knowledge augmented transformer for vision-and-language. NAACL (2022)","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"33_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/978-3-030-87571-8_28","volume-title":"Web Information Systems and Applications","author":"Q Guo","year":"2021","unstructured":"Guo, Q., et al.: Constructing Chinese historical literature knowledge graph based on\u00a0BERT. In: Xing, C., Fu, X., Zhang, Y., Zhang, G., Borjigin, C. (eds.) WISA 2021. LNCS, vol. 12999, pp. 323\u2013334. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87571-8_28"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Haurilet, M., Roitberg, A., Stiefelhagen, R.: It\u2019s not about the journey; it\u2019s about the destination: following soft paths under question-guidance for visual reasoning. In: CVPR, pp. 1930\u20131939. Computer Vision Foundation\/IEEE (2019)","DOI":"10.1109\/CVPR.2019.00203"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Huang, P., Huang, J., Guo, Y., Qiao, M., Zhu, Y.: Multi-grained attention with object-level grounding for visual question answering. In: ACL, pp. 3595\u20133600. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1349"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: CVPR, pp. 6700\u20136709. Computer Vision Foundation \/ IEEE (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.B.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: CVPR, pp. 1988\u20131997. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Kafle, K., Price, B.L., Cohen, S., Kanan, C.: DVQA: understanding data visualizations via question answering. In: CVPR, pp. 5648\u20135656. Computer Vision Foundation \/ IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00592"},{"key":"33_CR22","unstructured":"Kahou, S.E., Michalski, V., Atkinson, A., K\u00e1d\u00e1r, \u00c1., Trischler, A., Bengio, Y.: Figureqa: an annotated figure dataset for visual reasoning. In: ICLR. OpenReview.net (2018)"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Li, L., Gan, Z., Cheng, Y., Liu, J.: Relation-aware graph attention network for visual question answering. In: ICCV, pp. 10312\u201310321. IEEE (2019)","DOI":"10.1109\/ICCV.2019.01041"},{"key":"33_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/978-3-319-46475-6_17","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Lin","year":"2016","unstructured":"Lin, X., Parikh, D.: Leveraging visual question answering for image-caption ranking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 261\u2013277. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_17"},{"key":"33_CR25","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: Advances in Neural Information Processing Systems, pp. 289\u2013297 (2016)"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Patro, B.N., Anupriy, S., Namboodiri, V.: Explanation vs attention: a two-player game to obtain attention for VQA. In: AAAI, pp. 11848\u201311855. AAAI Press (2020)","DOI":"10.1609\/aaai.v34i07.6858"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Qiao, T., Dong, J., Xu, D.: Exploring human-like attention supervision in visual question answering. In: AAAI, pp. 7300\u20137307. AAAI Press (2018)","DOI":"10.1609\/aaai.v32i1.12272"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Shi, J., Zhang, H., Li, J.: Explainable and explicit visual reasoning over scene graphs. In: CVPR, pp. 8376\u20138384. Computer Vision Foundation \/ IEEE (2019)","DOI":"10.1109\/CVPR.2019.00857"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Shih, K.J., Singh, S., Hoiem, D.: Where to look: focus regions for visual question answering. In: CVPR, pp. 4613\u20134621. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.499"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Tang, K., Zhang, H., Wu, B., Luo, W., Liu, W.: Learning to compose dynamic tree structures for visual contexts. In: CVPR, pp. 6619\u20136628. Computer Vision Foundation \/ IEEE (2019)","DOI":"10.1109\/CVPR.2019.00678"},{"key":"33_CR31","doi-asserted-by":"crossref","unstructured":"Vo, N., et al.: Composing text and image for image retrieval - an empirical odyssey. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00660"},{"key":"33_CR32","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. ijcai.org (2017)","DOI":"10.24963\/ijcai.2017\/179"},{"issue":"10","key":"33_CR33","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 Trans. Pattern Anal. Mach. Intell. 40(10), 2413\u20132427 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR34","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.ins.2022.01.013","volume":"591","author":"F Wu","year":"2022","unstructured":"Wu, F., Jing, X., Wei, P., Lan, C., Ji, Y., Jiang, G., Huang, Q.: Semi-supervised multi-view graph convolutional networks with application to webpage classification. Inf. Sci. 591, 142\u2013154 (2022)","journal-title":"Inf. Sci."},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"Wu, J., Hu, Z., Mooney, R.J.: Generating question relevant captions to aid visual question answering. In: ACL, pp. 3585\u20133594. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1348"},{"key":"33_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-319-46478-7_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"H Xu","year":"2016","unstructured":"Xu, H., Saenko, K.: Ask, attend and answer: exploring question-guided spatial attention for visual question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 451\u2013466. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_28"},{"key":"33_CR37","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. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Fan, J., Tao, D.: Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In: ICCV, pp. 1821\u20131830 (2017)","DOI":"10.1109\/ICCV.2017.202"},{"key":"33_CR39","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, pp. 5014\u20135022. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.542"},{"key":"33_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Niebles, J.C., Soto, A.: Interpretable visual question answering by visual grounding from attention supervision mining. In: WACV, pp. 349\u2013357. IEEE (2019)","DOI":"10.1109\/WACV.2019.00043"}],"container-title":["Lecture Notes in Computer Science","Web Information Systems and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20309-1_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T20:07:33Z","timestamp":1674590853000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20309-1_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031203084","9783031203091"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20309-1_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"8 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WISA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Web Information Systems and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dalian","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 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wisa22022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conf.ccf.org.cn\/web\/html7\/index.html?globalId=m9475032704175349761645943983427&type=1","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":"212","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":"45","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":"19","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","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":"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)"}}]}}