{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:20:34Z","timestamp":1775326834936,"version":"3.50.1"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012458","type":"print"},{"value":"9783030012465","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01246-5_41","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T20:14:56Z","timestamp":1538770496000},"page":"690-706","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":521,"title":["Graph R-CNN for Scene Graph\u00a0Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2167-2880","authenticated-orcid":false,"given":"Jianwei","family":"Yang","sequence":"first","affiliation":[]},{"given":"Jiasen","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Dhruv","family":"Batra","sequence":"additional","affiliation":[]},{"given":"Devi","family":"Parikh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"41_CR1","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":"41_CR2","doi-asserted-by":"crossref","unstructured":"Dai, B., Zhang, Y., Lin, D.: Detecting visual relationships with deep relational networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.352"},{"key":"41_CR3","doi-asserted-by":"crossref","unstructured":"Das, A., et al.: Visual dialog. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.121"},{"key":"41_CR4","unstructured":"Everingham, M., Van Gool, L., Williams, C., Winn, J., Zisserman, A.: The Pascal visual object classes challenge 2012 results, vol. 5 (2012). http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html"},{"issue":"1","key":"41_CR5","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s10044-008-0141-y","volume":"13","author":"X Gao","year":"2010","unstructured":"Gao, X., Xiao, B., Tao, D., Li, X.: A survey of graph edit distance. Pattern Anal. Appl. 13(1), 113\u2013129 (2010)","journal-title":"Pattern Anal. Appl."},{"key":"41_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: CVPR (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"41_CR10","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"41_CR11","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"41_CR12","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Image retrieval using scene graphs. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"41_CR13","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)"},{"issue":"1","key":"41_CR14","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"Ranjay Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: Connecting language and vision using crowdsourced dense image annotations. IJCV 123(1), 32\u201373 (2017)","journal-title":"International Journal of Computer Vision"},{"key":"41_CR15","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"41_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1007\/978-3-642-15555-0_18","volume-title":"Computer Vision \u2013 ECCV 2010","author":"L Ladicky","year":"2010","unstructured":"Ladicky, L., Russell, C., Kohli, P., Torr, P.H.S.: Graph cut based inference with co-occurrence statistics. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6315, pp. 239\u2013253. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15555-0_18"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Wang, X.: ViP-CNN: a visual phrase reasoning convolutional neural network for visual relationship detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.766"},{"key":"41_CR18","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: ICCV (2017)","DOI":"10.1109\/ICCV.2017.142"},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Liang, X., Lee, L., Xing, E.P.: Deep variation-structured reinforcement learning for visual relationship and attribute detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.469"},{"key":"41_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/3-540-58325-4_168","volume-title":"Algorithms and Computation","author":"C-L Lin","year":"1994","unstructured":"Lin, C.-L.: Hardness of approximating graph transformation problem. In: Du, D.-Z., Zhang, X.-S. (eds.) ISAAC 1994. LNCS, vol. 834, pp. 74\u201382. Springer, Heidelberg (1994). https:\/\/doi.org\/10.1007\/3-540-58325-4_168"},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"41_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"41_CR23","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). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_51"},{"key":"41_CR24","doi-asserted-by":"crossref","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Neural baby talk. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00754"},{"key":"41_CR25","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML (2010)"},{"key":"41_CR26","unstructured":"Newell, A., Deng, J.: Pixels to graphs by associative embedding. In: NIPS (2017)"},{"issue":"12","key":"41_CR27","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.tics.2007.09.009","volume":"11","author":"A Oliva","year":"2007","unstructured":"Oliva, A., Torralba, A.: The role of context in object recognition. Trends Cogn. Sci. 11(12), 520\u2013527 (2007)","journal-title":"Trends Cogn. Sci."},{"key":"41_CR28","doi-asserted-by":"crossref","unstructured":"Parikh, D., Zitnick, C.L., Chen, T.: From appearance to context-based recognition: Dense labeling in small images. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587595"},{"key":"41_CR29","doi-asserted-by":"crossref","unstructured":"Peyre, J., Laptev, I., Schmid, C., Sivic, J.: Weakly-supervised learning of visual relations. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.554"},{"key":"41_CR30","doi-asserted-by":"crossref","unstructured":"Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., Belongie, S.: Objects in context. In: ICCV (2007)","DOI":"10.1109\/ICCV.2007.4408986"},{"key":"41_CR31","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"41_CR32","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"41_CR33","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"41_CR34","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"41_CR35","doi-asserted-by":"crossref","unstructured":"Teney, D., Liu, L., Hengel, A.V.d.: Graph-structured representations for visual question answering. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.344"},{"key":"41_CR36","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: Graph attention networks. In: ICLR (2018)"},{"key":"41_CR37","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., Shen, C., Dick, A., van den Hengel, A.: FVQA: fact-based visual question answering. In: PAMI (2017)","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"41_CR38","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., Shen, C., van den Hengel, A.: The VQA-machine: learning how to use existing vision algorithms to answer new questions. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.416"},{"key":"41_CR39","doi-asserted-by":"crossref","unstructured":"Wu, Q., Shen, C., Wang, P., Dick, A., van den Hengel, A.: Image captioning and visual question answering based on attributes and external knowledge. In: PAMI (2017)","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"41_CR40","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., Fei-Fei, L.: Scene graph generation by iterative message passing. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.330"},{"key":"41_CR41","unstructured":"Yang, J., Lu, J., Batra, D., Parikh, D.: A faster Pytorch implementation of faster R-CNN (2017). https:\/\/github.com\/jwyang\/faster-rcnn.pytorch"},{"key":"41_CR42","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural motifs: Scene graph parsing with global context. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"41_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Chang, S.F., Chua, T.S.: Visual translation embedding network for visual relation detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.331"},{"key":"41_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Yu, J., Chang, S.F.: Ppr-fcn: weakly supervised visual relation detection via parallel pairwise r-fcn (2017)","DOI":"10.1109\/ICCV.2017.454"},{"key":"41_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, J., Elhoseiny, M., Cohen, S., Chang, W., Elgammal, A.: Relationship proposal networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.555"},{"key":"41_CR46","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Liu, L., Shen, C., Reid, I.: Towards context-aware interaction recognition for visual relationship detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.71"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01246-5_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T00:26:26Z","timestamp":1664929586000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01246-5_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012458","9783030012465"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01246-5_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","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":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}