{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T20:52:44Z","timestamp":1743022364545,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030841850"},{"type":"electronic","value":"9783030841867"}],"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\/978-3-030-84186-7_15","type":"book-chapter","created":{"date-parts":[[2021,8,7]],"date-time":"2021-08-07T10:03:42Z","timestamp":1628330622000},"page":"226-236","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LRRA:A Transparent Neural-Symbolic Reasoning Framework for Real-World Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Zhang","family":"Wan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,8]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: Learning cross-modality encoder representations from transformers. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 5100\u20135111. Hong Kong, China, Association for Computational Linguistics, November 2019","DOI":"10.18653\/v1\/D19-1514"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Lu, J., Goswami, V., Rohrbach, M., Parikh, D., Lee, S.: 12-in-1: multi-task vision and language representation learning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: Vqa: visual question answering. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the v in VGA matter: elevating the role of image understanding in visual question answering. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6325\u20136334 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D.: Analyzing the behavior of visual question answering models. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 1955\u20131960, Austin, Texas, Association for Computational Linguistics November 2016","DOI":"10.18653\/v1\/D16-1203"},{"key":"15_CR6","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: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., Maaten, L., Li, F.F., Girshick, R.: Clevr: a diagnostic dataset for compositional language and elementary visual reasoning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"15_CR8","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates Inc., Red Hook (2017)"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: Visual reasoning with a general conditioning layer, Courville. Film (2017)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"15_CR10","unstructured":"Hudson, D.A., Manning. C.D.: Compositional attention networks for machine reasoning. In :International Conference on Learning Representations (ICLR) (2018)"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 39\u201348 (2016)","DOI":"10.1109\/CVPR.2016.12"},{"key":"15_CR12","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: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 804\u2013813 (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Inferring and executing programs for visual reasoning. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3008\u20133017 (2017)","DOI":"10.1109\/ICCV.2017.325"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Mascharka, D., Tran, P., Soklaski, R., Majumdar, A.: Transparency by design: casing the gap between performance and interpretability in visual reasoning. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4942\u20134950 (2018)","DOI":"10.1109\/CVPR.2018.00519"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Hu, R., Andreas, J., Darrell, T., Saenko, K.: Explainable neural computation via stack neural module networks. In: European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01234-2_4"},{"key":"15_CR16","unstructured":"Yi, K., et al.: Disentangling reasoning from vision and language understanding. In: Bengio, S., et al. (eds.) Advances in Neural Information Processing Systems, vol. 31. Curran Associates Inc., Red Hook (2018)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Image retrieval using scene graphs. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3668\u20133678 (2015)","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Teney, D., Liu, L., Hengel. A.: Graph-structured representations for visual question answering. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.344"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Yin, X., Ordonez. V.: Obj2text: generating visually descriptive language from object layouts (2017)","DOI":"10.18653\/v1\/D17-1017"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C., Fei-Fei, L.: Scene graph generation by iterative message passing. In :Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.330"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi. Y.: Neural motifs: scene graph parsing with global context. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5831\u20135840 (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"15_CR22","doi-asserted-by":"publisher","unstructured":"Li, Y., Ouyang, W., Zhou, B., Cui, Y., Wang, X.: Factorizable net: an efficient subgraph-based framework for scene graph generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision\u2013 ECCV 2018. ECCV 2018. Lecture Notes in Computer Science, vol. 11205, Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_21","DOI":"10.1007\/978-3-030-01246-5_21"},{"key":"15_CR23","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 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"15_CR24","unstructured":"Battaglia, P.W.: Relational inductive biases, deep learning, and graph networks (2018)"},{"key":"15_CR25","unstructured":"Xu, K., Hu, W., Leskovec, J., Jegelka. S.: How powerful are graph neural networks? (2018)"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Liang, W., Tian, Y., Chen, C., Yu. Z.: Moss: end-to-end dialog system framework with modular supervision (2019)","DOI":"10.1609\/aaai.v34i05.6349"},{"issue":"6","key":"15_CR27","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-CON: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR28","unstructured":"Chen, W., Gan, Z., Li, L., Cheng, L., Wang, W., Liu, J.: Meta module network for compositional visual reasoning (2019)"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Hu, R., Rohrbach, A., Darrell, T., Saenko, K.: Language-conditioned graph networks for relational reasoning. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10293\u201310302 (2019)","DOI":"10.1109\/ICCV.2019.01039"}],"container-title":["Lecture Notes in Computer Science","Chinese Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-84186-7_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T21:44:29Z","timestamp":1673041469000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-84186-7_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030841850","9783030841867"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-84186-7_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"8 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China National Conference on Chinese Computational Linguistics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hohhot","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 August 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":"cncl2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cips-cl.org\/static\/CCL2021\/en\/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":"www.softconf.com","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"90","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":"31","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":"34% - 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":"3","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)"}}]}}