{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T12:04:42Z","timestamp":1775217882515,"version":"3.50.1"},"reference-count":48,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T00:00:00Z","timestamp":1748476800000},"content-version":"vor","delay-in-days":148,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12301656"],"award-info":[{"award-number":["12301656"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12326607"],"award-info":[{"award-number":["12326607"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12471469"],"award-info":[{"award-number":["12471469"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["xzy012023047"],"award-info":[{"award-number":["xzy012023047"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515010919"],"award-info":[{"award-number":["2024A1515010919"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Disentangled representation learning demonstrates great success in enhancing the explainability, robustness and generalization capability of models across computer vision domains. While adopting the variational auto\u2010encoders (VAEs) to learn disentangled representations holds great promise, these models are prone to suffer from the poor disentanglement capability in complicated datasets, for example, colourful portrait images. These datasets often contain strong correlation among attributes, making it difficult to disentangle them. To alleviate this issue, a novel approach named group and individual priors\u2010based VAE (GAIP\u2010VAE) is proposed, which constrains the semantic attributes by customizing prior information to improve the disentanglement capability of the VAE. Specifically, we start from modelling the joint distribution of the observed data, and then derive three compatible loss terms in the objective function. The first one is the reconstruction term, utilizing the Laplace distribution to improve the image quality. The second one is the individual prior regularizer, encouraging the model to learn more interpretable factors via dimensional\u2010level regularizer. The third one is the group prior regularizer, constraining the approximate posterior distribution through multivariate normal distribution with the tailored correlation. Both quantitative and qualitative experimental results demonstrate that GAIP\u2010VAE can achieve a great balance between image quality and disentanglement\u00a0capability.<\/jats:p>","DOI":"10.1049\/ipr2.70113","type":"journal-article","created":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T23:06:47Z","timestamp":1748560007000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GAIP\u2010VAE: Balancing Reconstruction and Disentanglement in VAE With Group and Individual Priors"],"prefix":"10.1049","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1396-1177","authenticated-orcid":false,"given":"Yi","family":"Tian","sequence":"first","affiliation":[{"name":"School of Management Xi'an Jiaotong University Shaanxi China"}]},{"given":"Zengjie","family":"Song","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics Xi'an Jiaotong University Shaanxi China"}]}],"member":"265","published-online":{"date-parts":[[2025,5,29]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3420937"},{"key":"e_1_2_10_4_1","unstructured":"D. P.KingmaandM.Welling \u201cAuto\u2010Encoding Variational Bayes \u201dpreprint arXiv:1312.6114 December 20 2013 https:\/\/doi.org\/10.48550\/arXiv.1312.6114."},{"key":"e_1_2_10_5_1","unstructured":"I.Higgins L.Matthey A.Pal et\u00a0al. \u201cBeta\u2010VAE: Learning Basic Visual Concepts With a Constrained Variational Framework \u201dpaper presented at the International Conference on Learning Representations San Juan Puerto Rico May 2\u20134 2016."},{"key":"e_1_2_10_6_1","unstructured":"R. T.Chen X.Li R. B.Grosse andD. K.Duvenaud \u201cIsolating Sources of Disentanglement in Variational Autoencoders \u201d inProceedings of the Advances in Neural Information Processing Systems(Curran Associates Inc. 2018) 2610\u20132620."},{"key":"e_1_2_10_7_1","doi-asserted-by":"crossref","unstructured":"H. Y.Lee H. Y.Tseng J. B.Huang M.Singh andM. H.Yang \u201cDiverse Image\u2010to\u2010Image Translation via Disentangled Representations \u201d inProceedings of the European Conference on Computer Vision (ECCV)(Springer 2018) 35\u201351.","DOI":"10.1007\/978-3-030-01246-5_3"},{"key":"e_1_2_10_8_1","first-page":"1294","volume-title":"Advances in Neural Information Processing Systems","author":"Gonzalez\u2010Garcia A.","year":"2018"},{"key":"e_1_2_10_9_1","doi-asserted-by":"crossref","unstructured":"S.Lee S.Cho andS.Im \u201cDranet: Disentangling Representation and Adaptation Networks for Unsupervised Cross\u2010Domain Adaptation \u201d inProceedings of the IEEE\/CVF Conference on Computer Cision and Pattern Recognition(IEEE 2021) 15252\u201315261.","DOI":"10.1109\/CVPR46437.2021.01500"},{"key":"e_1_2_10_10_1","doi-asserted-by":"crossref","unstructured":"R.Hamaguchi K.Sakurada andR.Nakamura \u201cRare Event Detection Using Disentangled Representation Learning \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2019) 9327\u20139335.","DOI":"10.1109\/CVPR.2019.00955"},{"key":"e_1_2_10_11_1","doi-asserted-by":"crossref","unstructured":"Z.Feng C.Xu andD.Tao \u201cSelf\u2010Supervised Representation Learning by Rotation Feature Decoupling \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2019) 10364\u201310374.","DOI":"10.1109\/CVPR.2019.01061"},{"key":"e_1_2_10_12_1","doi-asserted-by":"crossref","unstructured":"E. H.Sanchez M.Serrurier andM.Ortner \u201cLearning Disentangled Representations via Mutual Information Estimation \u201d inProceedings of the European Conference on Computer Vision (ECCV)(Springer 2020) 205\u2013221.","DOI":"10.1007\/978-3-030-58542-6_13"},{"key":"e_1_2_10_13_1","unstructured":"A.Kumar P.Sattigeri andA.Balakrishnan \u201cVariational Inference of Disentangled Latent Concepts From Unlabeled Observations \u201dpaper presented at the International Conference on Learning Representations Vancouver Canada April 30\u2013May 3 2018."},{"key":"e_1_2_10_14_1","first-page":"2180","volume-title":"Advances in Neural Information Processing Systems","author":"Chen X.","year":"2016"},{"key":"e_1_2_10_15_1","unstructured":"A.B. L.Larsen S. K.S\u00f8nderby H.Larochelle andO.Winther \u201cAutoencoding Beyond Pixels Using a Learned Similarity Metric \u201d inInternational Conference on Machine Learning(Curran Associates Inc. 2016) 1558\u20131566."},{"key":"e_1_2_10_16_1","unstructured":"Z.Song O.Koyejo andJ.Zhang \u201cLearning Controllable Disentangled Representations With Decorrelation Regularization \u201dpreprint arXiv:1912.11675 December 25 2019 https:\/\/doi.org\/10.48550\/arXiv.1912.11675."},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3000480"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369757"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3510793"},{"key":"e_1_2_10_20_1","doi-asserted-by":"crossref","unstructured":"G.Wang C.Chen D. P.Fan A.Hao andH.Qin \u201cFrom Semantic Categories to Fixations: A Novel Weakly\u2010Supervised Visual\u2010Auditory Saliency Detection Approach \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2021) 15119\u201315128.","DOI":"10.1109\/CVPR46437.2021.01487"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068644"},{"key":"e_1_2_10_22_1","first-page":"19618","article-title":"A Geometric Perspective on Variational Autoencoders","volume":"35","author":"Chadebec C.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_23_1","unstructured":"I.Tolstikhin O.Bousquet S.Gelly andB.Schoelkopf \u201cWasserstein Auto\u2010Encoders \u201dpaper presented at the International Conference on Learning Representations Vancouver Canada April 30\u2013May 3 2018."},{"key":"e_1_2_10_24_1","unstructured":"A.Brock T.Lim J. M.Ritchie andN. J.Weston \u201cNeural Photo Editing With Introspective Adversarial Networks \u201dpaper presented at the International Conference on Learning Representations Toulon France April 24\u201326 2017."},{"key":"e_1_2_10_25_1","unstructured":"H.KimandA.Mnih \u201cDisentangling by Factorising \u201d inInternational Conference on Machine Learning(Microtome Publishing 2018) 2649\u20132658."},{"key":"e_1_2_10_26_1","first-page":"708","volume-title":"Advances in Neural Information Processing Systems","author":"Dupont E.","year":"2018"},{"key":"e_1_2_10_27_1","unstructured":"F.Locatello S.Bauer M.Lucic et\u00a0al. \u201cChallenging Common Assumptions in the Unsupervised Learning of Disentangled Representations \u201d inInternational Conference on Machine Learning(Microtome Publishing 2019) 4114\u20134124."},{"key":"e_1_2_10_28_1","unstructured":"Z.Hu Z.Yang X.Liang R.Salakhutdinov andE. P.Xing \u201cToward Controlled Generation of Text \u201d inInternational Conference on Machine Learning(Microtome Publishing 2017) 1587\u20131596."},{"key":"e_1_2_10_29_1","doi-asserted-by":"crossref","unstructured":"Y.Bao H.Zhou S.Huang et\u00a0al. \u201cGenerating Sentences From Disentangled Syntactic and Semantic Spaces \u201dpreprint arXiv:1907.05789 July 6 2019 https:\/\/doi.org\/10.48550\/arXiv.1907.05789.","DOI":"10.18653\/v1\/P19-1602"},{"key":"e_1_2_10_30_1","doi-asserted-by":"crossref","unstructured":"P.Cheng M. R.Min D.Shen et\u00a0al. \u201cImproving Disentangled Text Representation Learning With Information\u2010Theoretic Guidance \u201dpreprint arXiv:2006.00693 June 1 2020 https:\/\/doi.org\/10.48550\/arXiv.2006.00693.","DOI":"10.18653\/v1\/2020.acl-main.673"},{"key":"e_1_2_10_31_1","first-page":"5711","volume-title":"Advances in Neural Information Processing Systems","author":"Ma J.","year":"2019"},{"key":"e_1_2_10_32_1","doi-asserted-by":"crossref","unstructured":"X.Wang H.Jin A.Zhang X.He T.Xu andT. S.Chua \u201cDisentangled Graph Collaborative Filtering \u201d inProceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval(Association for Computing Machinery 2020) 1001\u20131010.","DOI":"10.1145\/3397271.3401137"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3153112"},{"key":"e_1_2_10_34_1","first-page":"139","volume-title":"Advances in Neural Information Processing Systems","author":"Goodfellow I.","year":"2014"},{"key":"e_1_2_10_35_1","first-page":"2234","volume-title":"Advances in Neural Information Processing Systems","author":"Salimans T.","year":"2016"},{"key":"e_1_2_10_36_1","unstructured":"C. P.Burgess I.Higgins A.Pal et\u00a0al. \u201cUnderstanding Disentangling in Beta\u2010VAE \u201dpreprint arXiv:1804.03599 April 10 2018 https:\/\/doi.org\/10.48550\/arXiv.1804.0359."},{"key":"e_1_2_10_37_1","first-page":"3483","volume-title":"Advances in Neural Information Processing Systems","author":"Sohn K.","year":"2015"},{"key":"e_1_2_10_38_1","doi-asserted-by":"crossref","unstructured":"G.PandeyandA.Dukkipati \u201cVariational Methods for Conditional Multimodal Deep Learning \u201d in2017 International Joint Conference on Neural Networks (IJCNN)(IEEE 2017) 308\u2013315.","DOI":"10.1109\/IJCNN.2017.7965870"},{"key":"e_1_2_10_39_1","unstructured":"M.Suzuki K.Nakayama andY.Matsuo \u201cJoint Multimodal Learning With Deep Generative Models \u201dpreprint arXiv:1611.01891. November 7 2016 https:\/\/doi.org\/10.48550\/arXiv.1611.01891."},{"key":"e_1_2_10_40_1","first-page":"5580","volume-title":"Advances in Neural Information Processing Systems","author":"Wu M.","year":"2018"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2016.2644865"},{"key":"e_1_2_10_42_1","doi-asserted-by":"crossref","unstructured":"Z.Liu P.Luo X.Wang andX.Tang \u201cDeep Learning Face Attributes in the Wild \u201d inProceedings of International Conference on Computer Vision (ICCV)(IEEE 2015) 3730\u20133738.","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_2_10_43_1","doi-asserted-by":"crossref","unstructured":"J.Snell K.Ridgeway R.Liao B. D.Roads M. C.Mozer andR. S.Zemel \u201cLearning to Generate Images With Perceptual Similarity Metrics \u201d in2017 IEEE International Conference on Image Processing (ICIP)(IEEE 2017) 4277\u20134281.","DOI":"10.1109\/ICIP.2017.8297089"},{"key":"e_1_2_10_44_1","unstructured":"A.Subramanian PyTorch\u2010VAE (GitHub 2020) https:\/\/github.com\/AntixK\/PyTorch\u2010VAE."},{"key":"e_1_2_10_45_1","unstructured":"I.Loshchilov \u201cDecoupled Weight Decay Regularization \u201dpreprint arXiv:1711.05101 November 14 2017 https:\/\/doi.org\/10.48550\/arXiv.1711.05101."},{"key":"e_1_2_10_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_2_10_47_1","unstructured":"K.DoandT.Tran \u201cTheory and Evaluation Metrics for Learning Disentangled Representations \u201dpaper presented at the International Conference on Learning Representations Addis Ababa Ethiopia April 302020."},{"key":"e_1_2_10_48_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"e_1_2_10_49_1","unstructured":"G.Bredell K.Flouris K.Chaitanya E.Erdil andE.Konukoglu \u201cExplicitly Minimizing the Blur Error of Variational Autoencoders \u201dpaper presented at the Eleventh International Conference on Learning Representations Kigali Riwanda May 1\u20135 2023."}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70113","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70113","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70113","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T11:28:01Z","timestamp":1775215681000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70113"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1049\/ipr2.70113"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70113","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-02-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70113"}}