{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T16:06:24Z","timestamp":1782662784712,"version":"3.54.5"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"National Science and Technology Council, Taiwan","award":["NSTC 112-2634-F-A49-006"],"award-info":[{"award-number":["NSTC 112-2634-F-A49-006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3432631","type":"journal-article","created":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T19:24:14Z","timestamp":1721762654000},"page":"10047-10059","source":"Crossref","is-referenced-by-count":16,"title":["Latent Semantic and Disentangled Attention"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3466-8941","authenticated-orcid":false,"given":"Jen-Tzung","family":"Chien","sequence":"first","affiliation":[{"name":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Han","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3162711"},{"key":"ref3","article-title":"Reformer: The efficient transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kitaev"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"ref5","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1223"},{"key":"ref7","first-page":"17105","article-title":"Adversarial sparse transformer for time series forecasting","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1146"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016489"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.72"},{"key":"ref13","first-page":"3543","article-title":"Attention is not explanation","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Jain"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746154"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10457"},{"key":"ref16","first-page":"1672","article-title":"Variational attention for sequence-to-sequence models","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Bahuleyan"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107295360"},{"key":"ref18","article-title":"Calibrating transformers via sparse Gaussian processes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref19","first-page":"4114","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Locatello"},{"key":"ref20","first-page":"5670","article-title":"Disentangled sequential autoencoder","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yingzhen"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1652"},{"key":"ref22","first-page":"2615","article-title":"Isolating sources of disentanglement in VAEs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1041"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.673"},{"key":"ref25","article-title":"Improving zero-shot voice style transfer via disentangled representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yuan"},{"key":"ref26","article-title":"On mutual information maximization for representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tschannen"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3190068"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/273"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2677439"},{"key":"ref30","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3068187"},{"key":"ref32","first-page":"21665","article-title":"Fast transformers with clustered attention","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vyas"},{"key":"ref33","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos"},{"key":"ref34","first-page":"5243","article-title":"Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref35","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zaheer"},{"key":"ref36","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref37","first-page":"5171","article-title":"On variational bounds of mutual information","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Poole"},{"key":"ref38","article-title":"A structured self-attentive sentence embedding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-545"},{"key":"ref43","article-title":"Pay less attention with lightweight and dynamic convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref44","article-title":"DeLighT: Deep and light-weight transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mehta"},{"issue":"11","key":"ref45","first-page":"2579","article-title":"Visualizing data using $t$t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"ref47","article-title":"Incorporating BERT into neural machine translation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref48","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054260"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10607968.pdf?arnumber=10607968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T23:59:03Z","timestamp":1732665543000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10607968\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":50,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3432631","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}