{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T13:56:50Z","timestamp":1743083810150,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030208752"},{"type":"electronic","value":"9783030208769"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-20876-9_42","type":"book-chapter","created":{"date-parts":[[2019,5,25]],"date-time":"2019-05-25T10:03:53Z","timestamp":1558778633000},"page":"669-685","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Dynamic Gated Graph Neural Networks for Scene Graph Generation"],"prefix":"10.1007","author":[{"given":"Mahmoud","family":"Khademi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oliver","family":"Schulte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,26]]},"reference":[{"key":"42_CR1","unstructured":"Allamanis, M., Brockschmidt, M., Khademi, M.: Learning to represent programs with graphs. arXiv preprint \n                      arXiv:1711.00740\n                      \n                     (2017)"},{"key":"42_CR2","unstructured":"Battaglia, P.W., et al.: Relational inductive biases, deep learning, and graph networks. arXiv preprint \n                      arXiv:1806.01261\n                      \n                     (2018)"},{"key":"42_CR3","unstructured":"Bojchevski, A., Shchur, O., Z\u00fcgner, D., G\u00fcnnemann, S.: NetGAN: generating graphs via random walks. arXiv preprint \n                      arXiv:1803.00816\n                      \n                     (2018)"},{"key":"42_CR4","unstructured":"De Cao, N., Kipf, T.: MolGAN: an implicit generative model for small molecular graphs. arXiv preprint \n                      arXiv:1805.11973\n                      \n                     (2018)"},{"key":"42_CR5","unstructured":"Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in Neural Information Processing Systems, pp. 3844\u20133852 (2016)"},{"key":"42_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"42_CR7","unstructured":"Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. arXiv preprint \n                      arXiv:1704.01212\n                      \n                     (2017)"},{"key":"42_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. arXiv preprint \n                      arXiv:1504.08083\n                      \n                     (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"42_CR9","unstructured":"Gori, M., Monfardini, G., Scarselli, F.: A new model for learning in graph domains. In: Proceedings of the 2005 IEEE International Joint Conference on Neural Networks, IJCNN 2005, vol. 2, pp. 729\u2013734. IEEE (2005)"},{"key":"42_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv preprint \n                      arXiv:1512.03385\n                      \n                     (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Image retrieval using scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3668\u20133678 (2015)","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"42_CR13","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. arXiv preprint \n                      arXiv:1602.07332\n                      \n                     (2016)"},{"key":"42_CR14","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"42_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Zhou, B., Wang, K., Wang, X.: Scene graph generation from objects, phrases and region captions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1261\u20131270 (2017)","DOI":"10.1109\/ICCV.2017.142"},{"key":"42_CR16","unstructured":"Li, Y., Tarlow, D., Brockschmidt, M., Zemel, R.: Gated graph sequence neural networks. arXiv preprint \n                      arXiv:1511.05493\n                      \n                     (2015)"},{"key":"42_CR17","unstructured":"Li, Y., Vinyals, O., Dyer, C., Pascanu, R., Battaglia, P.: Learning deep generative models of graphs. arXiv preprint \n                      arXiv:1803.03324\n                      \n                     (2018)"},{"key":"42_CR18","doi-asserted-by":"crossref","unstructured":"Liang, X., Lee, L., Xing, E.P.: Deep variation-structured reinforcement learning for visual relationship and attribute detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4408\u20134417. IEEE (2017)","DOI":"10.1109\/CVPR.2017.469"},{"key":"42_CR19","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"42_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1007\/978-3-319-46448-0_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"C Lu","year":"2016","unstructured":"Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 852\u2013869. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46448-0_51"},{"key":"42_CR21","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint \n                      arXiv:1312.5602\n                      \n                     (2013)"},{"issue":"7540","key":"42_CR22","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)","journal-title":"Nature"},{"key":"42_CR23","unstructured":"Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: Bilinear classifiers for visual recognition. In: Advances in Neural Information Processing Systems, pp. 1482\u20131490 (2009)"},{"key":"42_CR24","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"42_CR25","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: Advances in Neural Information Processing Systems, pp. 4967\u20134976 (2017)"},{"issue":"1","key":"42_CR26","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1109\/TNN.2008.2005141","volume":"20","author":"F Scarselli","year":"2009","unstructured":"Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: Computational capabilities of graph neural networks. IEEE Trans. Neural Netw. 20(1), 81\u2013102 (2009)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"1","key":"42_CR27","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2009","unstructured":"Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Netw. 20(1), 61\u201380 (2009)","journal-title":"IEEE Trans. Neural Netw."},{"key":"42_CR28","doi-asserted-by":"crossref","unstructured":"Schuster, S., Krishna, R., Chang, A., Fei-Fei, L., Manning, C.D.: Generating semantically precise scene graphs from textual descriptions for improved image retrieval. In: Proceedings of the Fourth Workshop on Vision and Language, pp. 70\u201380 (2015)","DOI":"10.18653\/v1\/W15-2812"},{"key":"42_CR29","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint \n                      arXiv:1409.1556\n                      \n                     (2014)"},{"key":"42_CR30","doi-asserted-by":"crossref","unstructured":"Teney, D., Liu, L., van den Hengel, A.: Graph-structured representations for visual question answering. CoRR, abs\/1609.05600 3 (2016)","DOI":"10.1109\/CVPR.2017.344"},{"key":"42_CR31","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. CoRR abs\/1411.4555 (2014). \n                      http:\/\/arxiv.org\/abs\/1411.4555"},{"key":"42_CR32","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., Fei-Fei, L.: Scene graph generation by iterative message passing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 2 (2017)","DOI":"10.1109\/CVPR.2017.330"},{"key":"42_CR33","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. arXiv preprint \n                      arXiv:1502.03044\n                      \n                     (2015)"},{"key":"42_CR34","unstructured":"You, J., Ying, R., Ren, X., Hamilton, W., Leskovec, J.: GraphRNN: generating realistic graphs with deep auto-regressive models. In: International Conference on Machine Learning, pp. 5694\u20135703 (2018)"},{"key":"42_CR35","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. CoRR abs\/1603.03925 (2016). \n                      http:\/\/arxiv.org\/abs\/1603.03925"},{"key":"42_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1007\/978-3-319-10605-2_27","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Y Zhu","year":"2014","unstructured":"Zhu, Y., Fathi, A., Fei-Fei, L.: Reasoning about object affordances in a knowledge base representation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 408\u2013424. Springer, Cham (2014). \n                      https:\/\/doi.org\/10.1007\/978-3-319-10605-2_27"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20876-9_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,25]],"date-time":"2019-05-25T19:07:09Z","timestamp":1558811229000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20876-9_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208752","9783030208769"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20876-9_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"26 May 2019","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":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","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"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"979","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"28% - 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"}},{"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"}},{"value":"2.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}