{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T06:57:39Z","timestamp":1763535459833,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1109\/icme.2017.8019448","type":"proceedings-article","created":{"date-parts":[[2017,9,7]],"date-time":"2017-09-07T01:03:50Z","timestamp":1504746230000},"page":"379-384","source":"Crossref","is-referenced-by-count":19,"title":["Visual relationship detection with object spatial distribution"],"prefix":"10.1109","author":[{"given":"Yaohui","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuqiang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"3485","article-title":"Sun database: Large-scale scene recognition from abbey to zoo","author":"jianxiong","year":"2010","journal-title":"CVPR IEEE"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref12","first-page":"852","article-title":"Visual relationship detection with language priors","author":"lu","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref14","first-page":"1292","article-title":"Image description using visual dependency representations","volume":"13","author":"elliott","year":"2013","journal-title":"EMNLP"},{"key":"ref15","first-page":"1745","article-title":"Recognition using visual phrases","author":"amin sadeghi","year":"2011","journal-title":"CVPR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587799"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540234"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.83"},{"key":"ref4","first-page":"1097","article-title":"lmagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"journal-title":"Deep residual learning for image recognition","year":"2015","author":"he","key":"ref3"},{"journal-title":"Ssd Single shot multibox detector","year":"2015","author":"liu","key":"ref6"},{"key":"ref5","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"CVPR IEEE"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition","year":"2014","author":"simonyan","key":"ref1"},{"journal-title":"Visual genome Connecting language and vision using crowdsourced dense image annotations","year":"2016","author":"krishna","key":"ref9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref22","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"tomas","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"ECCV"},{"journal-title":"Phrase localization and visual relationship detection with comprehensive linguistic cues","year":"2016","author":"bryan","key":"ref24"},{"journal-title":"Efficient Estimation of Word Representations in Vector Space","year":"2013","author":"mikolov","key":"ref23"}],"event":{"name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2017,7,10]]},"location":"Hong Kong, Hong Kong","end":{"date-parts":[[2017,7,14]]}},"container-title":["2017 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8014303\/8019290\/08019448.pdf?arnumber=8019448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,10,3]],"date-time":"2017-10-03T03:04:53Z","timestamp":1506999893000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8019448\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icme.2017.8019448","relation":{},"subject":[],"published":{"date-parts":[[2017,7]]}}}