{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T02:53:52Z","timestamp":1790823232389,"version":"4.1.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1109\/icmew.2017.8026277","type":"proceedings-article","created":{"date-parts":[[2017,9,7]],"date-time":"2017-09-07T16:34:59Z","timestamp":1504802099000},"page":"309-314","source":"Crossref","is-referenced-by-count":20,"title":["Visual saliency for image captioning in new multimedia services"],"prefix":"10.1109","author":[{"given":"Marcella","family":"Cornia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Baraldi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Serra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rita","family":"Cucchiara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref11","article-title":"Hierarchical Boundary-Aware Neural Encoder for Video Captioning","author":"baraldi","year":"0","journal-title":"CVPR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref13","article-title":"Graph-based visual saliency","author":"harel","year":"0","journal-title":"ANIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.272"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.26"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900174"},{"key":"ref18","article-title":"Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model","author":"cornia","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.623"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2644872"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/135062800394667"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref6","article-title":"DeepGaze I: Boosting saliency prediction with feature maps trained on ImageNet","author":"k\u00fcmmerer","year":"0","journal-title":"ICLR Workshop"},{"key":"ref5","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.620"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"ref1","article-title":"Microsoft COCO: Common Objects in Context","author":"lin","year":"0","journal-title":"ECCV"},{"key":"ref20","article-title":"Seeing with humans: Gaze-assisted neural image captioning","author":"sugano","year":"2016"},{"key":"ref22","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"0","journal-title":"Text Summarization Branches Out Proceedings of the ACL-04 Workshop"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref23","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","author":"banerjee","year":"0","journal-title":"ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation And\/or Summarization"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"simonyan","year":"2014"}],"event":{"name":"2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","location":"Hong Kong, Hong Kong","start":{"date-parts":[[2017,7,10]]},"end":{"date-parts":[[2017,7,14]]}},"container-title":["2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8014334\/8026209\/08026277.pdf?arnumber=8026277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,10,2]],"date-time":"2017-10-02T22:08:26Z","timestamp":1506982106000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8026277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icmew.2017.8026277","relation":{},"subject":[],"published":{"date-parts":[[2017,7]]}}}