{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:40:36Z","timestamp":1742920836374,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030695439"},{"type":"electronic","value":"9783030695446"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/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":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69544-6_9","type":"book-chapter","created":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T11:05:00Z","timestamp":1614251100000},"page":"137-153","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Modular Graph Attention Network for Complex Visual Relational Reasoning"],"prefix":"10.1007","author":[{"given":"Yihan","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiquan","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingkui","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runhao","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,26]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: FiLM: visual reasoning with a general conditioning layer. In: AAAI Conference on Artificial Intelligence (AAAI) (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"9_CR2","unstructured":"Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"9_CR3","unstructured":"Mao, J., Gan, C., Kohli, P., Tenenbaum, J.B., Wu, J.: The neuro-symbolic concept learner: interpreting scenes, words, and sentences from natural supervision. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3674\u20133683 (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6629\u20136638 (2019)","DOI":"10.1109\/CVPR.2019.00679"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Nguyen, K., Dey, D., Brockett, C., Dolan, B.: Vision-based navigation with language-based assistance via imitation learning with indirect intervention. In: Proceedings of the of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12527\u201312537 (2019)","DOI":"10.1109\/CVPR.2019.01281"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Liu, R., Liu, C., Bai, Y., Yuille, A.L.: CLEVR-REF+: diagnosing visual reasoning with referring expressions. In: Proceedings of the of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4185\u20134194 (2019)","DOI":"10.1109\/CVPR.2019.00431"},{"key":"9_CR8","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: Proceedings of the of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.L.: ReferitGame: referring to objects in photographs of natural scenes. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: MAttNet: modular attention network for referring expression comprehension. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1307\u20131315 (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Yu, L., Tan, H., Bansal, M., Berg, T.L.: A joint speaker-listener-reinforcer model for referring expressions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3521\u20133529 (2017)","DOI":"10.1109\/CVPR.2017.375"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., Cao, J., Shen, C., Gao, L., Hengel, A.v.d.: Neighbourhood watch: referring expression comprehension via language-guided graph attention networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1960\u20131968 (2019)","DOI":"10.1109\/CVPR.2019.00206"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Bajaj, M., Wang, L., Sigal, L.: G3raphGround: graph-based language grounding. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 4281\u20134290 (2019)","DOI":"10.1109\/ICCV.2019.00438"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Hu, R., Rohrbach, A., Darrell, T., Saenko, K.: Language-conditioned graph networks for relational reasoning. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 10294\u201310303 (2019)","DOI":"10.1109\/ICCV.2019.01039"},{"key":"9_CR16","unstructured":"Li, Y., Tarlow, D., Brockschmidt, M., Zemel, R.S.: Gated graph sequence neural networks. In: International Conference on Learning Representations (ICLR) (2016)"},{"key":"9_CR17","unstructured":"Norcliffe-Brown, W., Vafeias, S., Parisot, S.: Learning conditioned graph structures for interpretable visual question answering. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 8334\u20138343 (2018)"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Chang, S., Yang, J., Park, S., Kwak, N.: Broadcasting convolutional network for visual relational reasoning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 754\u2013769 (2018)","DOI":"10.1007\/978-3-030-01267-0_46"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Huang, H., Jain, V., Mehta, H., Ku, A., Magalhaes, G., Baldridge, J., Ie, E.: Transferable representation learning in vision-and-language navigation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 7404\u20137413 (2019)","DOI":"10.1109\/ICCV.2019.00750"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Ke, L., et al.: Tactical rewind: self-correction via backtracking in vision-and-language navigation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6741\u20136749 (2019)","DOI":"10.1109\/CVPR.2019.00690"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Inferring and executing programs for visual reasoning. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2989\u20132998 (2017)","DOI":"10.1109\/ICCV.2017.325"},{"key":"9_CR22","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: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 804\u2013813 (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Cao, Q., Liang, X., Li, B., Li, G., Lin, L.: Visual question reasoning on general dependency tree. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7249\u20137257 (2018)","DOI":"10.1109\/CVPR.2018.00757"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Hu, R., Rohrbach, M., Andreas, J., Darrell, T., Saenko, K.: Modeling relationships in referential expressions with compositional modular networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1115\u20131124 (2017)","DOI":"10.1109\/CVPR.2017.470"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 39\u201348 (2016)","DOI":"10.1109\/CVPR.2016.12"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Cirik, V., Morency, L., Berg-Kirkpatrick, T.: Visual referring expression recognition: what do systems actually learn? In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), pp. 781\u2013787 (2018)","DOI":"10.18653\/v1\/N18-2123"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Gori, M., Monfardini, G., Scarselli, F.: A new model for learning in graph domains. In: Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), vol. 2, pp. 729\u2013734. IEEE (2005)","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"9_CR28","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2008","unstructured":"Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Networks 20, 61\u201380 (2008)","journal-title":"IEEE Trans. Neural Networks"},{"key":"9_CR29","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (ICLR) (2017)"},{"key":"9_CR30","unstructured":"Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Zeng, R., et al.: Graph convolutional networks for temporal action localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 7094\u20137103 (2019)","DOI":"10.1109\/ICCV.2019.00719"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Huang, D., Chen, P., Zeng, R., Du, Q., Tan, M., Gan, C.: Location-aware graph convolutional networks for video question answering. In: AAAI Conference on Artificial Intelligence (AAAI), pp. 11021\u201311028 (2020)","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"9_CR33","doi-asserted-by":"crossref","unstructured":"Li, L., Gan, Z., Cheng, Y., Liu, J.: Relation-aware graph attention network for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 10313\u201310322 (2019)","DOI":"10.1109\/ICCV.2019.01041"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Dynamic graph attention for referring expression comprehension. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 4644\u20134653 (2019)","DOI":"10.1109\/ICCV.2019.00474"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Cross-modal relationship inference for grounding referring expressions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4145\u20134154 (2019)","DOI":"10.1109\/CVPR.2019.00427"},{"key":"9_CR36","unstructured":"Zhu, M., Zhang, Y., Chen, W., Zhang, M., Zhu, J.: Fast and accurate shift-reduce constituent parsing. In: ACL, vol. 1, pp. 434\u2013443 (2013)"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"9_CR38","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45, 2673\u20132681 (1997)","journal-title":"IEEE Trans. Signal Process."},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724\u20131734 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"9_CR41","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"9_CR42","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"9_CR43","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: Proceedings of the of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1988\u20131997 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Hu, R., Andreas, J., Darrell, T., Saenko, K.: Explainable neural computation via stack neural module networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 55\u201371 (2018)","DOI":"10.1007\/978-3-030-01234-2_4"},{"key":"9_CR45","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T., Schiele, B.: Grounding of textual phrases in images by reconstruction. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 817\u2013834 (2016)","DOI":"10.1007\/978-3-319-46448-0_49"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69544-6_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T21:10:02Z","timestamp":1724533802000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69544-6_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695439","9783030695446"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69544-6_9","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":"26 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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":"768","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":"254","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":"33% - 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)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}