{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T20:34:10Z","timestamp":1730234050425,"version":"3.28.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,6]],"date-time":"2021-07-06T00:00:00Z","timestamp":1625529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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\/icccnt51525.2021.9579925","type":"proceedings-article","created":{"date-parts":[[2021,11,3]],"date-time":"2021-11-03T15:29:48Z","timestamp":1635953388000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Loss Optimised Video Captioning using Deep-Lstm,Attention Mechanism and Weighted Loss Metrices"],"prefix":"10.1109","author":[{"given":"Naveen","family":"Yadav","sequence":"first","affiliation":[]},{"given":"Dinesh","family":"Naik","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Generating Short Video Description using Deep-Lstm and Attention Mechanism","author":"yadav","year":"0","journal-title":"International Conference for Convergence of Technology (I2CT) 2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref30","article-title":"On Loss Functions for Deep Neural Networks","volume":"25","author":"janocha","year":"2016","journal-title":"accepted in Schedae Informaticae"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref35","first-page":"1782","article-title":"Deliberation networks: Sequence generation beyond one-pass decoding","author":"xia","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306"},{"key":"ref40","article-title":"En-De-Cap: An Encoder Decoder model for Image Captioning","author":"patwari","year":"0","journal-title":"5th International Conference on Computing Methodologies and Communication (ICCMC)"},{"key":"ref11","first-page":"541","article-title":"Generating natural-language video descriptions using text-mined knowledge","author":"krishnamoorthy","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref12","first-page":"1218","article-title":"Integrating language and vision to generate natural language descriptions of videos in the wild","author":"thomason","year":"0","journal-title":"Proc Int Conf Comput Linguist"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-8289-9_57"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1154"},{"key":"ref19","first-page":"1218","article-title":"Integrating language and vision to generate natural language descriptions of videos in the wild","author":"thomason","year":"0","journal-title":"Proc Int Conf Comput Linguist"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2831447"},{"key":"ref4","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"0","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2520959"},{"key":"ref3","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref6","article-title":"Attention-Based Models for Speech Recognition","author":"chorowski","year":"0","journal-title":"Advances in Neural Information Processing Systems 28 (NIPS 2015)"},{"key":"ref29","article-title":"Hierarchical LSTMs with Adaptive Attention for Visual Captioning","volume":"14","author":"gao","year":"2015","journal-title":"Journal of latex class files"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/GRC.2008.4664680"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPEIC.2016.7557203"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2814344"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430144"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601260"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref42","article-title":"Effect of Batch Normalization and Stacked LSTMs on Video Captioning","author":"sarathi","year":"0","journal-title":"5th International Conference on Computing Methodologies and Communication (ICCMC)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref41","article-title":"Comparison of Image Encoder Architectures for Image Captioning","author":"maru","year":"0","journal-title":"5th International Conference on Computing Methodologies and Communication (ICCMC)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref26","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref25","article-title":"Recurrent Neural Network for Text Classification with Multi-Task Learning","author":"liu","year":"0","journal-title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16)"}],"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\/09579925.pdf?arnumber=9579925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T12:56:01Z","timestamp":1652187361000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9579925\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icccnt51525.2021.9579925","relation":{},"subject":[],"published":{"date-parts":[[2021,7,6]]}}}