{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T11:17:22Z","timestamp":1730200642355,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/bigmm.2018.8499066","type":"proceedings-article","created":{"date-parts":[[2018,10,22]],"date-time":"2018-10-22T20:35:25Z","timestamp":1540240525000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Image Captioning Based on Adaptive Balancing Loss"],"prefix":"10.1109","author":[{"given":"Linghui","family":"Li","sequence":"first","affiliation":[]},{"given":"Sheng","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Junbo","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Lyu","sequence":"additional","affiliation":[]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/TKDE.2014.2312336"},{"key":"ref38","first-page":"4041","article-title":"Towards class-imbalance aware multi-label learning","author":"zhang","year":"2015","journal-title":"IJCAI"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref32","first-page":"2361","article-title":"Review networks for caption generation","author":"yang","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Multi-level policy and reward reinforcement learning for image captioning","author":"xu","year":"2018","journal-title":"IJCAI"},{"key":"ref30","first-page":"5","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"2","author":"xu","year":"2015","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/TPAMI.2016.2567393"},{"key":"ref36","first-page":"53","article-title":"Exploiting local features from deep networks for image retrieval","author":"yue-","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1109\/CVPR.2016.503"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/TIP.2017.2694222"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/CVPR.2014.81"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/TIP.2017.2766445"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/MSP.2017.2749125"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/CVPR.2016.90"},{"year":"2015","author":"jia","journal-title":"Guiding long-short term memory for image caption generation","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref16","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":"ref17","first-page":"4133","article-title":"Image caption with global-local attention","author":"li","year":"2017","journal-title":"AAAI"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/TMM.2017.2751140"},{"key":"ref19","first-page":"210","article-title":"Category aggregation among region proposals for object detection","author":"li","year":"2016","journal-title":"Pacific Rim Conference on Multimedia"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/CVPR.2015.7298935"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/TGRS.2017.2783902"},{"key":"ref27","first-page":"12","article-title":"lnception-v4, inception-resnet and the impact of residual connections on learning","volume":"4","author":"szegedy","year":"2017","journal-title":"AAAI"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref6","first-page":"1826","article-title":"Addressing imbalance in multi-label classification using structured hellinger forests","author":"daniels","year":"2017","journal-title":"AAAI"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/CVPR.2017.780"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.3115\/v1\/D14-1179"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/CVPR.2017.108"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR.2015.7298878"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1016\/j.neucom.2014.08.091"},{"year":"2017","author":"gan","journal-title":"Semantic compositional networks for visual captioning","key":"ref9"},{"key":"ref1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"ICLRE"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1007\/s00138-017-0843-5"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPR.2017.345"},{"year":"2017","author":"lin","journal-title":"Focal loss for dense object detection","key":"ref21"},{"key":"ref24","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":"ref23","article-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","author":"mao","year":"2015","journal-title":"ICLRE"},{"key":"ref26","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs 1409 1556","author":"simonyan","year":"2014","journal-title":"CoRR"}],"event":{"name":"2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM)","start":{"date-parts":[[2018,9,13]]},"location":"Xi'an","end":{"date-parts":[[2018,9,16]]}},"container-title":["2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8482104\/8499056\/08499066.pdf?arnumber=8499066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T12:59:52Z","timestamp":1643201992000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8499066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/bigmm.2018.8499066","relation":{},"subject":[],"published":{"date-parts":[[2018,9]]}}}