{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T20:32:37Z","timestamp":1730233957022,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,6]],"date-time":"2021-07-06T00:00:00Z","timestamp":1625529600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,6]],"date-time":"2021-07-06T00:00:00Z","timestamp":1625529600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,6]]},"DOI":"10.1109\/icccnt51525.2021.9579512","type":"proceedings-article","created":{"date-parts":[[2021,11,3]],"date-time":"2021-11-03T19:29:48Z","timestamp":1635967788000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Attention based Image Captioning using Depth-wise Separable Convolution"],"prefix":"10.1109","author":[{"given":"Vikash Raja","family":"Mallick","sequence":"first","affiliation":[{"name":"National Institue of Technology,Dept. of Information Technology,Karnataka,India"}]},{"given":"Dinesh","family":"Naik","sequence":"additional","affiliation":[{"name":"National Institue of Technology,Dept. of Information Technology,Karnataka,India"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.152"},{"key":"ref38","article-title":"Understanding the exploding gradient problem","author":"pascanu","year":"0","journal-title":"CoRR"},{"key":"ref33","article-title":"Rethinking the Inception Architecture for Computer Vision","author":"szegedy","year":"2015","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2831447"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"hochreiter","year":"1997","journal-title":"Long Short-term Memory Neural Computation"},{"key":"ref36","article-title":"Microsoft COCO: Common Objects in Context","volume":"8693","author":"lin","year":"2014","journal-title":"Computer Vision-ECCV 2014 ECCV 2014 Lecture Notes in Computer Science"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1142\/S0218488598000094"},{"key":"ref34","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annu Meeting Assoc Comput Linguist"},{"journal-title":"Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift","year":"2015","author":"ioffe","key":"ref10"},{"key":"ref40","article-title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","author":"junyoung chung","year":"2014","journal-title":"CoRR"},{"key":"ref11","first-page":"595","article-title":"Multimodal neural language models","author":"kiros","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref12","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"0","journal-title":"Trans Assoc"},{"key":"ref13","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref14","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learning Representations (ICLR)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCMC51019.2021.9418414"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCMC51019.2021.9418234"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCMC51019.2021.9418036"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.140"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSP.2019.8698097"},{"journal-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","year":"2014","author":"mao","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","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"},{"journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition","year":"2014","author":"zisserman","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114528"},{"journal-title":"Show and Tell A Neural Image Caption Generator","year":"2014","author":"vinyals","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"journal-title":"Yann LeCun","article-title":"THE MNIST DATABASE of handwritten digits","year":"0","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/I2CT51068.2021.9418171"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2019.2892755"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/PARC49193.2020.236619"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICIIECS.2017.8276124"},{"key":"ref24","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2004.1394652"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref25","first-page":"1724","article-title":"Learning phrase representations using RNN en-coder-decoder for statistical machine translation","author":"cho","year":"2014","journal-title":"Proc Conf Empirical Methods Natural Lang Process"}],"event":{"name":"2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT)","start":{"date-parts":[[2021,7,6]]},"location":"Kharagpur, India","end":{"date-parts":[[2021,7,8]]}},"container-title":["2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9579467\/9579470\/09579512.pdf?arnumber=9579512","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:43:21Z","timestamp":1659483801000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9579512\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icccnt51525.2021.9579512","relation":{},"subject":[],"published":{"date-parts":[[2021,7,6]]}}}