{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T03:26:30Z","timestamp":1773545190736,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/dicta.2018.8615789","type":"proceedings-article","created":{"date-parts":[[2019,1,18]],"date-time":"2019-01-18T00:57:07Z","timestamp":1547773027000},"page":"1-7","source":"Crossref","is-referenced-by-count":38,"title":["Image and Encoded Text Fusion for Multi-Modal Classification"],"prefix":"10.1109","author":[{"given":"I.","family":"Gallo","sequence":"first","affiliation":[]},{"given":"A.","family":"Calefati","sequence":"additional","affiliation":[]},{"given":"S.","family":"Nawaz","sequence":"additional","affiliation":[]},{"given":"M. K.","family":"Janjua","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Multimodal machine learning: A survey and taxonomy","author":"baltrusaitis","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref12","first-page":"22","article-title":"Distributional semantics from text and images","author":"bruni","year":"2011","journal-title":"Proceedings of the GEMS 2011 Workshop on GEometrical Models of Natural Language Semantics ser GEMS '11"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1303"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2267205"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.323"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"ref18","first-page":"2222","article-title":"Multimodallearning with deep boltzmann machines","author":"srivastava","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502112"},{"key":"ref4","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref3","article-title":"Efficient large-scale multi-modal classification","author":"kiela","year":"2018","journal-title":"Proceedings of AAAI-2018"},{"key":"ref6","first-page":"1403","article-title":"Going beyond text: A hybrid image-text approach for measuring word relatedness.","author":"leong","year":"2011","journal-title":"IJCNLP"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540120"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref7","first-page":"91","article-title":"Visual information in semantic representation","author":"feng","year":"2010","journal-title":"Annual Conference of the North American Chapter of the Association for Computational Linguistics"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1005"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.326"},{"key":"ref9","article-title":"Efficient estimation of word representations in vector space","volume":"absi1301 3781","author":"mikolov","year":"2013","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref22","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":"ref21","first-page":"1","article-title":"Recipe recognition with large multimodal food dataset","author":"wang","year":"2015","journal-title":"Multimedia and Expo Workshops (ICMEW)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-009-9124-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"}],"event":{"name":"2018 Digital Image Computing: Techniques and Applications (DICTA)","location":"Canberra, Australia","start":{"date-parts":[[2018,12,10]]},"end":{"date-parts":[[2018,12,13]]}},"container-title":["2018 Digital Image Computing: Techniques and Applications (DICTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8615628\/8615748\/08615789.pdf?arnumber=8615789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T21:44:39Z","timestamp":1643233479000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8615789\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/dicta.2018.8615789","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}