{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:38:06Z","timestamp":1777657086695,"version":"3.51.4"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319682877","type":"print"},{"value":"9783319682884","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-3-319-68288-4_4","type":"book-chapter","created":{"date-parts":[[2017,10,4]],"date-time":"2017-10-04T08:59:43Z","timestamp":1507107583000},"page":"53-68","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Improving Visual Relationship Detection Using Semantic Modeling of Scene Descriptions"],"prefix":"10.1007","author":[{"given":"Stephan","family":"Baier","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunpu","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volker","family":"Tresp","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,10,4]]},"reference":[{"key":"4_CR1","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, pp. 39\u201348 (2016)","DOI":"10.1109\/CVPR.2016.12"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Bagdanov, A.D., Bertini, M., Del Bimbo, A., Serra, G., Torniai, C.: Semantic annotation and retrieval of video events using multimedia ontologies. In: International Conference on Semantic Computing, ICSC 2007, pp. 713\u2013720. IEEE (2007)","DOI":"10.1109\/ICSC.2007.30"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Bannour, H., Hudelot, C.: Towards ontologies for image interpretation and annotation. In: 2011 9th International Workshop on Content-Based Multimedia Indexing (CBMI), pp. 211\u2013216. IEEE (2011)","DOI":"10.1109\/CBMI.2011.5972547"},{"key":"4_CR4","doi-asserted-by":"publisher","unstructured":"Bloehdorn, S., et al.: Semantic annotation of images and videos for multimedia analysis. In: G\u00f3mez-P\u00e9rez, A., Euzenat, J. (eds.) ESWC 2005. LNCS, vol. 3532, pp. 592\u2013607. Springer, Heidelberg (2005). doi:10.1007\/11431053_40","DOI":"10.1007\/11431053_40"},{"key":"4_CR5","unstructured":"Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Advances in Neural Information Processing Systems, pp. 2787\u20132795 (2013)"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Chen, N., Zhou, Q.Y., Prasanna, V.: Understanding web images by object relation network. In: Proceedings of the 21st International Conference on World Wide Web, pp. 291\u2013300. ACM (2012)","DOI":"10.1145\/2187836.2187876"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Choi, W., Chao, Y.W., Pantofaru, C., Savarese, S.: Understanding indoor scenes using 3d geometric phrases. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 33\u201340 (2013)","DOI":"10.1109\/CVPR.2013.12"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Dong, X., Gabrilovich, E., Heitz, G., Horn, W., Lao, N., Murphy, K., Strohmann, T., Sun, S., Zhang, W.: Knowledge vault: a web-scale approach to probabilistic knowledge fusion. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 601\u2013610. ACM (2014)","DOI":"10.1145\/2623330.2623623"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Galleguillos, C., Rabinovich, A., Belongie, S.: Object categorization using co-occurrence, location and appearance. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587799"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"3","key":"4_CR12","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/s11263-008-0140-x","volume":"80","author":"S Gould","year":"2008","unstructured":"Gould, S., Rodgers, J., Cohen, D., Elidan, G., Koller, D.: Multi-class segmentation with relative location prior. Int. J. Comput. Vis. 80(3), 300\u2013316 (2008)","journal-title":"Int. J. Comput. Vis."},{"issue":"10","key":"4_CR13","doi-asserted-by":"publisher","first-page":"1775","DOI":"10.1109\/TPAMI.2009.83","volume":"31","author":"A Gupta","year":"2009","unstructured":"Gupta, A., Kembhavi, A., Davis, L.S.: Observing human-object interactions: using spatial and functional compatibility for recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(10), 1775\u20131789 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR14","unstructured":"Kingma, D., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"1","key":"4_CR15","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.J., Shamma, D.A., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"issue":"12","key":"4_CR16","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni, G., Premraj, V., Ordonez, V., Dhar, S., Li, S., Choi, Y., Berg, A.C., Berg, T.L.: Babytalk: understanding and generating simple image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2891\u20132903 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7553","key":"4_CR17","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"4_CR18","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\u2014ECCV 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). doi:10.1007\/978-3-319-46448-0_51"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Maji, S., Bourdev, L., Malik, J.: Action recognition from a distributed representation of pose and appearance. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3177\u20133184. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995631"},{"issue":"1","key":"4_CR20","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/JPROC.2015.2483592","volume":"104","author":"M Nickel","year":"2016","unstructured":"Nickel, M., Murphy, K., Tresp, V., Gabrilovich, E.: A review of relational machine learning for knowledge graphs. Proc. IEEE 104(1), 11\u201333 (2016)","journal-title":"Proc. IEEE"},{"key":"4_CR21","unstructured":"Nickel, M., Tresp, V., Kriegel, H.P.: A three-way model for collective learning on multi-relational data. In: Proceedings of the 28th International Conference on Machine Learning (ICML 2011), pp. 809\u2013816 (2011)"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., Li, C., Deng, J., Han, W., Li, Z., Gu, K., Song, Y., Bengio, S., Rosenberg, C., Fei-Fei, L.: Learning semantic relationships for better action retrieval in images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1100\u20131109 (2015)","DOI":"10.1109\/CVPR.2015.7298713"},{"key":"4_CR23","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":"4_CR24","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Qiu, W., Titov, I., Thater, S., Pinkal, M., Schiele, B.: Translating video content to natural language descriptions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 433\u2013440 (2013)","DOI":"10.1109\/ICCV.2013.61"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Sadeghi, M.A., Farhadi, A.: Recognition using visual phrases. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1745\u20131752. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"4_CR26","unstructured":"Santoro, A., Raposo, D., Barrett, D.G., Malinowski, M., Pascanu, R., Battaglia, P., Lillicrap, T.: A simple neural network module for relational reasoning. arXiv preprint arXiv:1706.01427 (2017)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Serafini, L., Donadello, I., Garcez, A.d.: Learning and reasoning in logic tensor networks: theory and application to semantic image interpretation. In: Proceedings of the Symposium on Applied Computing, pp. 125\u2013130. ACM (2017)","DOI":"10.1145\/3019612.3019642"},{"key":"4_CR28","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"4_CR29","unstructured":"Tresp, V., Esteban, C., Yang, Y., Baier, S., Krompa\u00df, D.: Learning with memory embeddings. arXiv preprint arXiv:1511.07972 (2015)"},{"key":"4_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1007\/978-3-319-58068-5_13","volume-title":"The Semantic Web","author":"V Tresp","year":"2017","unstructured":"Tresp, V., Ma, Y., Baier, S., Yang, Y.: Embedding learning for declarative memories. In: Blomqvist, E., Maynard, D., Gangemi, A., Hoekstra, R., Hitzler, P., Hartig, O. (eds.) ESWC 2017. LNCS, vol. 10249, pp. 202\u2013216. Springer, Cham (2017). doi:10.1007\/978-3-319-58068-5_13"},{"issue":"2","key":"4_CR31","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104(2), 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vis."},{"issue":"1","key":"4_CR32","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.websem.2005.10.002","volume":"4","author":"V Uren","year":"2006","unstructured":"Uren, V., Cimiano, P., Iria, J., Handschuh, S., Vargas-Vera, M., Motta, E., Ciravegna, F.: Semantic annotation for knowledge management: sequirements and a survey of the state of the art. J. Web Semant. Sci. Serv. Agent World Wide Web 4(1), 14\u201328 (2006)","journal-title":"J. Web Semant. Sci. Serv. Agent World Wide Web"},{"key":"4_CR33","unstructured":"Welbl, J., Riedel, S., Gaussier, E., Bouchard, G.: Complex embeddings for simple link prediction. In: Proceedings of the 33rd International Conference on Machine Learning (2016)"},{"key":"4_CR34","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"4_CR35","unstructured":"Yang, B., Yih, W.t., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. arXiv preprint arXiv:1412.6575 (2014)"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: Grouplet: A structured image representation for recognizing human and object interactions. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9\u201316. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540234"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: Modeling mutual context of object and human pose in human-object interaction activities. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17\u201324. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"4_CR38","unstructured":"Yilmaz, \u00d6., Garcez, A.S.d., Silver, D.L.: A proposal for common dataset in neural-symbolic reasoning studies. In: NeSy@ HLAI (2016)"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Lim, J.J., Fei-Fei, L.: Knowledge acquisition for visual question answering via iterative querying (2017)","DOI":"10.1109\/CVPR.2017.651"}],"container-title":["Lecture Notes in Computer Science","The Semantic Web \u2013 ISWC 2017"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-68288-4_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,11]],"date-time":"2022-10-11T00:07:30Z","timestamp":1665446850000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-68288-4_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319682877","9783319682884"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-68288-4_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"4 October 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISWC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Semantic Web Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vienna","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Austria","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 October 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 October 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"semweb2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}