{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:19:03Z","timestamp":1740169143216,"version":"3.37.3"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61601230"],"award-info":[{"award-number":["61601230"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2982571","type":"journal-article","created":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T02:25:49Z","timestamp":1585016749000},"page":"56695-56710","source":"Crossref","is-referenced-by-count":0,"title":["Conditionally Learn to Pay Attention for Sequential Visual Task"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1671-2283","authenticated-orcid":false,"given":"Jun","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan-Jie","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref32","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc 40th Ann Meeting Assoc for Computational Linguistics (ACL 02)"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref30","first-page":"1","article-title":"Segmentation of multiple, partially occluded objects by grouping, merging, assigning part detection responses","author":"wu","year":"2008","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref35","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2014","journal-title":"arXiv 1412 6632"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref10","first-page":"451","article-title":"Ask, attend and answer: Exploring question-guided spatial attention for visual question answering","author":"xu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref11","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","first-page":"1","article-title":"Learn to pay attention","author":"jetley","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref13","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref14","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"2013","journal-title":"arXiv 1312 6034"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICCV.2015.338"},{"key":"ref16","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.18653\/v1\/P17-1098"},{"key":"ref18","article-title":"A unified query-based generative model for question generation and question answering","author":"song","year":"2017","journal-title":"arXiv 1709 01058"},{"key":"ref19","article-title":"Progressive attention networks for visual attribute prediction","author":"hongsuck seo","year":"2016","journal-title":"arXiv 1606 02393"},{"key":"ref28","first-page":"1","article-title":"Multi-digit number recognition from street view imagery using deep convolutional neural networks","author":"goodfellow","year":"2014","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref4","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref6","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"1","article-title":"Multiple object recognition with visual attention","author":"ba","year":"2015","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/CVPR.2017.667"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR.2016.503"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICASSP.2013.6638947"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref20","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPR.2019.00856"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CVPR.2018.00754"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1162\/neco.1997.9.8.1735"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/CVPR.2019.00850"},{"key":"ref26","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref25","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09044202.pdf?arnumber=9044202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T20:14:40Z","timestamp":1643314480000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9044202\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2982571","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}