{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T19:06:01Z","timestamp":1792868761035,"version":"4.5.0"},"reference-count":72,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,6]]},"DOI":"10.1109\/cvpr.2015.7298990","type":"proceedings-article","created":{"date-parts":[[2015,10,15]],"date-time":"2015-10-15T18:42:06Z","timestamp":1444934526000},"page":"3668-3678","source":"Crossref","is-referenced-by-count":828,"title":["Image retrieval using scene graphs"],"prefix":"10.1109","author":[{"given":"Justin","family":"Johnson","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ranjay","family":"Krishna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Stark","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li-Jia","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David A.","family":"Shamma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael S.","family":"Bernstein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Fei-Fei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.211"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.387"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.401"},{"key":"ref39","first-page":"28","article-title":"Stanford's multi-pass sieve coreference resolution system at the conll-2011 shared task","author":"lee","year":"2011","journal-title":"Proceedings of the Fifteenth Conference on Computational Natural Language Learning Shared Task"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459359"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1162\/tacl_a_00220","article-title":"Jointly learning to parse and perceive: Connecting natural language to the physical world","volume":"1","author":"krishnamurthy","year":"2013","journal-title":"TACL"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1007\/978-3-319-10602-1_47","article-title":"Geodesic object proposals","author":"krahenbuhl","year":"2014","journal-title":"Computer Vision-ECCV 2014"},{"key":"ref31","article-title":"Deep fragment em-beddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"CoRR abs\/1406 5679"},{"key":"ref30","author":"jurafsky","year":"2000","journal-title":"Speech & language processing"},{"key":"ref37","article-title":"Attribute-based classification for zero-shot learning of object categories","author":"lampert","year":"2013","journal-title":"PAMI"},{"key":"ref36","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"2001","journal-title":"Proceedings of the Eighteenth International Conference on Machine Learning ICML'01"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"1601","DOI":"10.1109\/CVPR.2011.5995466","article-title":"Baby talk: Understanding and generating simple image descriptions","author":"kulkarni","year":"2011","journal-title":"Computer Vision and Pattern Recognition (CVPR) 2011 IEEE Conference on"},{"key":"ref34","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref60","article-title":"Crowdsourcing annotations for visual object detection","author":"su","year":"2012","journal-title":"AAAI Technical Report 4th Human Computation Workshop"},{"key":"ref62","first-page":"776","article-title":"Efficient object category recognition using classemes","author":"torresani","year":"2010","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref61","article-title":"The new data and new challenges in multimedia research","author":"thomee","year":"2015","journal-title":"ar Xiv preprint arXiv 1503 01817"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.415"},{"key":"ref66","article-title":"Classifying actions and measuring action similarity by modeling the mutual context of objects and human poses","author":"yao","year":"2011","journal-title":"a) A 1(D2) D3"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref67","article-title":"Introduction to a large scale general purpose groundtruth dataset: methodology, annotation tool, and benchmarks","author":"yao","year":"2007","journal-title":"EMMCVPR"},{"key":"ref68","doi-asserted-by":"crossref","DOI":"10.1162\/tacl_a_00166","article-title":"From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions","author":"young","year":"2014","journal-title":"Transactions of the Association for Computational Linguistics 2 67–"},{"key":"ref69","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2009.5459354","article-title":"Efficient indexing for large scale visual search","author":"zhang","year":"2009","journal-title":"Computer Vision 2009 IEEE 12th International Conference On"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.28"},{"key":"ref1","year":"0","journal-title":"OpenSceneGraph"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1964921.1964929"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.260"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1964921.1964929"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1613\/jair.3994","article-title":"Framing image description as a ranking task: Data, models and evaluation metrics","volume":"47","author":"hodosh","year":"2013","journal-title":"J Artif Intell Res (JAIR)"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1007\/978-3-540-88682-2_3","article-title":"Beyond nouns: Exploiting prepositions and comparative adjectives for learning visual classifiers","author":"gupta","year":"2008","journal-title":"Computer Vision-ECCV 2008"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"ref51","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","author":"platt","year":"1999","journal-title":"Advances in Large Margin Classifiers"},{"key":"ref59","article-title":"Size matters: Exhaustive geometric verification for image retrieval","author":"stewenius","year":"0","journal-title":"ECCV"},{"key":"ref58","article-title":"Grounded compositional semantics for finding and describing images with sentences","author":"socher","year":"2013","journal-title":"NIPS Deep Learning Workshop"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0090-8"},{"key":"ref54","article-title":"Imagenet large scale visual recognition challenge","author":"russakovsky","year":"2014"},{"key":"ref53","first-page":"492","article-title":"A multi-pass sieve for coreference resolution","author":"raghunathan","year":"2010","journal-title":"Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.211"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.12"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408891"},{"key":"ref40","article-title":"Towards total scene understanding: Classification, annotation and segmentation in an automatic framework","author":"li","year":"2009","journal-title":"CVPR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0439-x"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.412"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539924"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref19","article-title":"Learning visual attributes","author":"ferrari","year":"2007","journal-title":"NIPS"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1007\/978-3-642-15549-9_48","article-title":"Automatic attribute discovery and characterization from noisy web data","author":"berg","year":"2010","journal-title":"Computer Vision-ECCV 2010"},{"key":"ref3","article-title":"OpenGM: A C++ library for discrete graphical models","author":"andres","year":"2012","journal-title":"ar Xiv preprint arXiv 1206 0111"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540021"},{"key":"ref5","first-page":"2088","article-title":"Learning a compact code for novel-category recognition","author":"bergamo","year":"2011","journal-title":"Advances in Neural Information Processing Systems 24"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.178"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1217"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540221"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref45","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"2012","journal-title":"Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"ref47","first-page":"25","article-title":"Deepdive: Web-scale knowledge-base construction using statistical learning and inference","author":"niu","year":"2012","journal-title":"VLDS"},{"key":"ref42","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"arXiv preprint arXiv 1405 0312"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.340"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.313"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"}],"event":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Boston, MA, USA","start":{"date-parts":[[2015,6,7]]},"end":{"date-parts":[[2015,6,12]]}},"container-title":["2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7293313\/7298593\/07298990.pdf?arnumber=7298990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,9]],"date-time":"2020-09-09T17:11:17Z","timestamp":1599671477000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7298990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2015.7298990","relation":{},"subject":[],"published":{"date-parts":[[2015,6]]}}}