{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T05:40:10Z","timestamp":1751694010719,"version":"3.41.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319930336"},{"type":"electronic","value":"9783319930343"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-319-93034-3_43","type":"book-chapter","created":{"date-parts":[[2018,6,18]],"date-time":"2018-06-18T11:30:29Z","timestamp":1529321429000},"page":"538-548","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual Relation Extraction via Multi-modal Translation Embedding Based Model"],"prefix":"10.1007","author":[{"given":"Zhichao","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuping","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yajing","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,19]]},"reference":[{"key":"43_CR1","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Chang, S.F., Chua, T.S.: Visual translation embedding network for visual relation detection. arXiv preprint arXiv:1702.08319 (2017)","DOI":"10.1109\/CVPR.2017.331"},{"key":"43_CR2","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":"43_CR3","doi-asserted-by":"crossref","unstructured":"Sadeghi, M.A., Farhadi, A.: Recognition using visual phrases. In: Computer Vision and Pattern Recognition, pp. 1745\u20131752 (2011)","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"43_CR4","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":"43_CR5","doi-asserted-by":"crossref","unstructured":"Lin, Y., Liu, Z., Sun, M., Liu, Y., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: AAAI, pp. 2181\u20132187 (2015)","DOI":"10.1609\/aaai.v29i1.9491"},{"key":"43_CR6","first-page":"55","volume":"27","author":"J Andreas","year":"2015","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Dan, K.: Deep compositional question answering with neural module networks. Comput. Sci. 27, 55\u201356 (2015)","journal-title":"Comput. Sci."},{"key":"43_CR7","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Li, F.F.: Deep visual-semantic alignments for generating image descriptions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2014)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"43_CR8","doi-asserted-by":"crossref","unstructured":"Johnson, J., Krishna, R., Stark, M., Li, L.J., Shamma, D.A., Bernstein, M.S., Li, F.F.: Image retrieval using scene graphs. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3668\u20133678 (2015)","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"43_CR9","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":"43_CR10","doi-asserted-by":"crossref","unstructured":"Guadarrama, S., Krishnamoorthy, N., Malkarnenkar, G., Venugopalan, S., Mooney, R., Darrell, T., Saenko, K.: YouTube2Text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2712\u20132719 (2013)","DOI":"10.1109\/ICCV.2013.337"},{"key":"43_CR11","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1162\/tacl_a_00207","volume":"1","author":"M Regneri","year":"2013","unstructured":"Regneri, M., Rohrbach, M., Wetzel, D., Thater, S., Schiele, B., Pinkal, M.: Grounding action descriptions in videos. Trans. Assoc. Comput. Linguist. 1, 25\u201336 (2013)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"43_CR12","unstructured":"Thomason, J., Venugopalan, S., Guadarrama, S., Saenko, K., Mooney, R.J.: Integrating language and vision to generate natural language descriptions of videos in the wild. In: Coling, vol. 2, p. 9 (2014)"},{"key":"43_CR13","doi-asserted-by":"crossref","unstructured":"Yao, J., Fidler, S., Urtasun, R.: Describing the scene as a whole: joint object detection, scene classification and semantic segmentation. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 702\u2013709. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247739"},{"issue":"12","key":"43_CR14","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."},{"key":"43_CR15","doi-asserted-by":"crossref","unstructured":"Zitnick, C.L., Parikh, D., Vanderwende, L.: Learning the visual interpretation of sentences. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1681\u20131688 (2013)","DOI":"10.1109\/ICCV.2013.211"},{"key":"43_CR16","unstructured":"Atzmon, Y., Berant, J., Kezami, V., Globerson, A., Chechik, G.: Learning to generalize to new compositions in image understanding. arXiv preprint arXiv:1608.07639 (2016)"},{"key":"43_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-15561-1_2","volume-title":"Computer Vision \u2013 ECCV 2010","author":"A Farhadi","year":"2010","unstructured":"Farhadi, A., Hejrati, M., Sadeghi, M.A., Young, P., Rashtchian, C., Hockenmaier, J., Forsyth, D.: Every picture tells a story: generating sentences from images. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 15\u201329. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_2"},{"issue":"1","key":"43_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-011-0439-x","volume":"95","author":"C Desai","year":"2011","unstructured":"Desai, C., Ramanan, D., Fowlkes, C.C.: Discriminative models for multi-class object layout. Int. J. Comput. Vis. 95(1), 1\u201312 (2011)","journal-title":"Int. J. Comput. Vis."},{"key":"43_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/978-3-540-88682-2_3","volume-title":"Computer Vision \u2013 ECCV 2008","author":"A Gupta","year":"2008","unstructured":"Gupta, A., Davis, L.S.: Beyond nouns: exploiting prepositions and comparative adjectives for learning visual classifiers. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 16\u201329. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88682-2_3"},{"key":"43_CR20","doi-asserted-by":"crossref","unstructured":"Sadeghi, F., Kumar Divvala, S.K., Farhadi, A.: VisKE: visual knowledge extraction and question answering by visual verification of relation phrases. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1456\u20131464 (2015)","DOI":"10.1109\/CVPR.2015.7298752"},{"key":"43_CR21","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Computer Vision and Pattern Recognition, pp. 580\u2013587 (2013)","DOI":"10.1109\/CVPR.2014.81"},{"key":"43_CR22","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":"43_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":"43_CR24","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"43_CR25","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, Y., Mao, J., Huang, Z., Huang, C., Xu, W.: CNN-RNN: a unified framework for multi-label image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2285\u20132294 (2016)","DOI":"10.1109\/CVPR.2016.251"},{"key":"43_CR26","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-93034-3_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T04:58:27Z","timestamp":1751691507000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-93034-3_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319930336","9783319930343"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-93034-3_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"19 June 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Melbourne, VIC","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":"3 June 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 June 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/prada-research.net\/pakdd18\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}