{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T16:17:05Z","timestamp":1789575425208,"version":"build-2803163510"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"UM Frontier Research","award":["FG002-17AFR"],"award-info":[{"award-number":["FG002-17AFR"]}]},{"DOI":"10.13039\/501100004386","name":"University of Malaya","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004386","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1109\/tmm.2019.2904878","type":"journal-article","created":{"date-parts":[[2019,3,13]],"date-time":"2019-03-13T19:00:28Z","timestamp":1552503628000},"page":"2686-2696","source":"Crossref","is-referenced-by-count":46,"title":["COMIC: Toward A Compact Image Captioning Model With Attention"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7743-848X","authenticated-orcid":false,"given":"Jia Huei","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7677-2865","authenticated-orcid":false,"given":"Chee Seng","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joon Huang","family":"Chuah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref38","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1249"},{"key":"ref32","article-title":"Which encoding is the best for text classification in Chinese, English, Japanese and Korean","author":"zhang","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220422"},{"key":"ref30","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref37","first-page":"4385","article-title":"LightRNN: Memory and computation-efficient recurrent neural networks","volume":"29","author":"li","year":"2016","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref36","article-title":"Radical-level ideograph encoder for RNN-based sentiment analysis of Chinese and Japanese","author":"ke","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1155"},{"key":"ref34","article-title":"Neural machine translation of rare words with subword units","author":"sennrich","year":"2015"},{"key":"ref28","first-page":"898","article-title":"Contrastive learning for image captioning","author":"dai","year":"0","journal-title":"Proc 31st Conf Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3115432"},{"key":"ref29","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $< $ 0.5 mb model size","author":"iandola","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0"},{"key":"ref20","first-page":"2361","article-title":"Review networks for caption generation","author":"yang","year":"2016","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.12.026"},{"key":"ref21","first-page":"101","article-title":"phi-LSTM: A phrase-based hierarchical LSTM model for image captioning","author":"tan","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964299"},{"key":"ref25","article-title":"Boosting image captioning with attributes","author":"yao","year":"2016"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.128"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref10","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.681"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref13","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume":"29","author":"banerjee","year":"0","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref14","first-page":"1","article-title":"ROUGE: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"0","journal-title":"Proc of Workshop on Text Summarization Branches Out at ACL"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref17","first-page":"595","article-title":"Multimodal neural language models","author":"kiros","year":"0","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref4","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"sutskever","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref5","article-title":"Using the output embedding to improve language models","author":"press","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2642953"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref46","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref48","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref47","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0"},{"key":"ref42","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1151"},{"key":"ref44","article-title":"One model to learn them all","author":"kaiser","year":"2017"},{"key":"ref43","article-title":"Attention is all you need","author":"vaswani","year":"2017"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8846791\/08666805.pdf?arnumber=8666805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:47:06Z","timestamp":1657745226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8666805\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":52,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2904878","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10]]}}}