{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T12:49:44Z","timestamp":1761396584777,"version":"3.28.0"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191548","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T13:30:03Z","timestamp":1690983003000},"page":"01-09","source":"Crossref","is-referenced-by-count":4,"title":["Variational Disentangled Attention and Regularization for Visual Dialog"],"prefix":"10.1109","author":[{"given":"Jen-Tzung","family":"Chien","sequence":"first","affiliation":[{"name":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan"}]},{"given":"Hsiu-Wei","family":"Tien","sequence":"additional","affiliation":[{"name":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3068187"},{"key":"ref35","first-page":"1761","article-title":"Bayesian transformer using disentangled mask attention","author":"tzung chien","year":"0","journal-title":"Proc of Annual Conference of the International Speech Communication Association"},{"key":"ref12","article-title":"Probabilistic binary neural networks","author":"peters","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref34","article-title":"Bayesian attention modules","volume":"33","author":"fan","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688234"},{"key":"ref37","first-page":"1","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"0","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref14","first-page":"1541","article-title":"Over-coming language priors in visual question answering with adversarial regularization","volume":"31","author":"ramakrishnan","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref36","article-title":"Disentangling factors of variation via generative entangling","author":"desjardins","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref31","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref30","article-title":"Learning deep representations by mutual information estimation and maximization","author":"devon hjelm","year":"0","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref11","article-title":"Learning discrete weights using the local reparameterization trick","author":"shayer","year":"0","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref33","first-page":"9712","article-title":"Latent alignment and variational attention","volume":"31","author":"deng","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"841","article-title":"Rubi: Reducing Unimodal Biases for visual question answering","volume":"32","author":"cadene","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref32","first-page":"1672","article-title":"Variational attention for sequence-to-sequence models","author":"bahuleyan","year":"0","journal-title":"Proc of International Conference on Computational Linguistics"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1209"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.02.099"},{"key":"ref39","article-title":"Stochastic variational inference","volume":"14","author":"hoffman","year":"2013","journal-title":"Journal of Machine Learning Research"},{"key":"ref16","first-page":"1713","article-title":"Supportive and self attentions for image caption","author":"chien","year":"0","journal-title":"Proc of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206667"},{"key":"ref19","first-page":"4402","article-title":"Disentangling disentanglement in variational autoencoders","author":"mathieu","year":"0","journal-title":"Proc of International Conference on Machine Learning"},{"key":"ref18","article-title":"Dialog without dialog data: Learning visual dialog agents from VQA data","volume":"33","author":"cogswell","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.673"},{"key":"ref46","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref23","first-page":"2180","article-title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets","author":"chen","year":"0","journal-title":"Proc of International Conference on Neural Information Processing"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref26","first-page":"201","article-title":"The IM algorithm: a variational approach to information maximization","volume":"16","author":"barber felix agakov","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Variational interaction information maximization for crossdomain disentanglement","volume":"33","author":"hwang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00684"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01028"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109463"},{"key":"ref22","article-title":"Deep variational information bottleneck","author":"alemi","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3235202"},{"key":"ref21","first-page":"1","article-title":"Learning flow-based disentanglement","author":"chien","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref43","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"0","journal-title":"Proc of European Conference on Computer Vision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160280102"},{"key":"ref27","article-title":"Club: A Contrastive log-ratio upper bound of mutual information","author":"cheng","year":"0","journal-title":"Proc of International Conference on Machine Learning"},{"key":"ref29","first-page":"531","article-title":"Mutual information neural estimation","author":"ishmael belghazi","year":"0","journal-title":"Proc of International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3162711"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.728"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_20"},{"key":"ref6","first-page":"424","article-title":"AVAST: Attentive variational state tracker in a reinforced navigator","author":"jang","year":"0","journal-title":"Proc of International Joint Conference on Natural Language Processing"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/app11073009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000037"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191548.pdf?arnumber=10191548","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T13:44:15Z","timestamp":1692625455000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191548\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191548","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}