{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:31:10Z","timestamp":1730266270538,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"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":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533970","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-8","source":"Crossref","is-referenced-by-count":19,"title":["Attentive Contextual Network for Image Captioning"],"prefix":"10.1109","author":[{"given":"Jeripothula","family":"Prudviraj","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Hyderabad,Department of Computer Science and Engineering,Sangareddy, Hyderabad"}]},{"given":"Chalavadi","family":"Vishnu","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Hyderabad,Department of Computer Science and Engineering,Sangareddy, Hyderabad"}]},{"given":"C. Krishna","family":"Mohan","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Hyderabad,Department of Computer Science and Engineering,Sangareddy, Hyderabad"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref38","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_17"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref30","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206932"},{"key":"ref36","article-title":"Real-Time Semantic Segmentation via Multiply Spatial Fusion Network","author":"si","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref35","first-page":"267","article-title":"Psanet: Point-wise spatial attention network for scene parsing","author":"zhao","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref34","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.592"},{"key":"ref11","article-title":"C-DLinkNet: considering multi-level semantic features for human parsing","author":"lu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref12","article-title":"Stack-captioning: Coarse-to-fine learning for image captioning","volume":"32","author":"gu","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref13","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"0","journal-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851832"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref17","first-page":"269","article-title":"Exfuse: Enhancing feature fusion for semantic segmentation","author":"zhang","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852118"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206815"},{"key":"ref4","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref27","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref29","article-title":"Robust visual tracking via hierarchical convolutional features","author":"ma","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.592"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref46","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"ref45","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref22","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/1118162.1118168"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref41","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"journal-title":"Automatic differentiation in pytorch","year":"2017","author":"paszke","key":"ref23"},{"key":"ref44","article-title":"DeST-Net: Densely fused spatial transformer networks","author":"annunziata","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852118"},{"key":"ref25","first-page":"219","article-title":"Texture synthesis and the controlled generation of natural stimuli using convolutional neural networks","author":"gatys","year":"0","journal-title":"Bernstein Conference 2015"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533970.pdf?arnumber=9533970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:32:17Z","timestamp":1659483137000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533970","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}