{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:26:07Z","timestamp":1772907967638,"version":"3.50.1"},"publisher-location":"Cham","reference-count":94,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729942","type":"print"},{"value":"9783031729959","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72995-9_16","type":"book-chapter","created":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T19:17:14Z","timestamp":1732389434000},"page":"270-289","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Closed-Loop Unsupervised Representation Disentanglement with\u00a0$$\\beta $$-VAE Distillation and\u00a0Diffusion Probabilistic Feedback"],"prefix":"10.1007","author":[{"given":"Xin","family":"Jin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bohan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baao","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenyao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, S., Hu, S.X., Damianou, A., Lawrence, N.D., Dai, Z.: Variational information distillation for knowledge transfer. In: CVPR, pp. 9163\u20139171 (2019)","DOI":"10.1109\/CVPR.2019.00938"},{"key":"16_CR2","unstructured":"Bao, Z., Hebert, M., Wang, Y.X.: Generative modeling for multi-task visual learning. In: ICML, pp. 1537\u20131554. PMLR (2022)"},{"issue":"8","key":"16_CR3","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. TPAMI 35(8), 1798\u20131828 (2013)","journal-title":"TPAMI"},{"key":"16_CR4","unstructured":"Burgess, C.P., et al.: Understanding disentangling in $$\\beta $$-vae. In: NeurIPS Workshop on Learning Disentangled Representations (2017)"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Cao, Q., Shen, L., Xie, W., Parkhi, O.M., Zisserman, A.: VGGFace2: a dataset for recognising faces across pose and age. In: International Conference on Automatic Face and Gesture Recognition (2018)","DOI":"10.1109\/FG.2018.00020"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Chan, E.R., Monteiro, M., Kellnhofer, P., Wu, J., Wetzstein, G.: pi-GAN: periodic implicit generative adversarial networks for 3D-aware image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"16_CR7","unstructured":"Chen, H., Zhang, Y., Wang, X., Duan, X., Zhou, Y., Zhu, W.: DisenBooth: disentangled parameter-efficient tuning for subject-driven text-to-image generation. arXiv preprint arXiv:2305.03374 (2023)"},{"key":"16_CR8","unstructured":"Chen, R.T., Li, X., Grosse, R.B., Duvenaud, D.K.: Isolating sources of disentanglement in variational autoencoders. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"16_CR9","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"16_CR10","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-031-20050-2_7","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Z Chen","year":"2022","unstructured":"Chen, Z., Jiang, R., Duke, B., Zhao, H., Aarabi, P.: Exploring gradient-based multi-directional controls in\u00a0GANs. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, pp. 104\u2013119. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20050-2_7"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, P., et al.: Improving disentangled text representation learning with information-theoretic guidance. arXiv preprint arXiv:2006.00693 (2020)","DOI":"10.18653\/v1\/2020.acl-main.673"},{"key":"16_CR12","unstructured":"Cheng, Y., Wang, D., Zhou, P., Zhang, T.: A survey of model compression and acceleration for deep neural networks. arXiv preprint arXiv:1710.09282 (2017)"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Cherepkov, A., Voynov, A., Babenko, A.: Navigating the GAN parameter space for semantic image editing. In: CVPR, pp. 3671\u20133680 (2021)","DOI":"10.1109\/CVPR46437.2021.00367"},{"key":"16_CR14","unstructured":"Dai, J., et al.: Safe RLHF: safe reinforcement learning from human feedback. arXiv preprint arXiv:2310.12773 (2023)"},{"key":"16_CR15","unstructured":"Dasgupta, S., Dey, A., Roberts, N., Sabato, S.: Learning from discriminative feature feedback. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"16_CR16","unstructured":"Dasgupta, S., Sabato, S.: Robust learning from discriminative feature feedback. In: International Conference on Artificial Intelligence and Statistics, pp. 973\u2013982. PMLR (2020)"},{"key":"16_CR17","unstructured":"Denton, E.L., et\u00a0al.: Unsupervised learning of disentangled representations from video. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"16_CR18","unstructured":"Driess, D., et\u00a0al.: PaLM-E: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"key":"16_CR19","unstructured":"Eastwood, C., Williams, C.K.: A framework for the quantitative evaluation of disentangled representations. In: International conference on learning representations (2018)"},{"issue":"6","key":"16_CR20","first-page":"455","volume":"70","author":"K Egan","year":"1989","unstructured":"Egan, K.: Memory, imagination, and learning: connected by the story. Phi Delta Kappan 70(6), 455\u2013459 (1989)","journal-title":"Phi Delta Kappan"},{"key":"16_CR21","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.visres.2013.11.004","volume":"94","author":"RW Fleming","year":"2014","unstructured":"Fleming, R.W.: Visual perception of materials and their properties. Vis. Res. 94, 62\u201375 (2014)","journal-title":"Vis. Res."},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Goetschalckx, L., Andonian, A., Oliva, A., Isola, P.: GANalyze: toward visual definitions of cognitive image properties. In: ICCV, pp. 5744\u20135753 (2019)","DOI":"10.1109\/ICCV.2019.00584"},{"key":"16_CR23","unstructured":"Gonzalez-Garcia, A., Van De\u00a0Weijer, J., Bengio, Y.: Image-to-image translation for cross-domain disentanglement. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"16_CR24","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"16_CR25","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou, J., Yu, B., Maybank, S.J., Tao, D.: Knowledge distillation: a survey. IJCV 129, 1789\u20131819 (2021)","journal-title":"IJCV"},{"key":"16_CR26","first-page":"9841","volume":"33","author":"E H\u00e4rk\u00f6nen","year":"2020","unstructured":"H\u00e4rk\u00f6nen, E., Hertzmann, A., Lehtinen, J., Paris, S.: GANSpace: discovering interpretable GAN controls. Adv. Neural Inf. Process. Syst. 33, 9841\u20139850 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"He, R., Lee, W.S., Ng, H.T., Dahlmeier, D.: An unsupervised neural attention model for aspect extraction. In: ACL, pp. 388\u2013397 (2017)","DOI":"10.18653\/v1\/P17-1036"},{"key":"16_CR28","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"16_CR29","unstructured":"Higgins, I., et al.: Towards a definition of disentangled representations. arXiv preprint arXiv:1812.02230 (2018)"},{"key":"16_CR30","unstructured":"Higgins, I., et al.: beta-VAE: learning basic visual concepts with a constrained variational framework. In: ICLR (2016)"},{"key":"16_CR31","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Adv. Neural Inf. Process. Syst. Denoising diffusion probabilistic models 33, 6840\u20136851 (2020)","journal-title":"Denoising diffusion probabilistic models"},{"key":"16_CR32","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"16_CR33","unstructured":"Hsu, W.N., Glass, J.: Disentangling by partitioning: a representation learning framework for multimodal sensory data. arXiv preprint arXiv:1805.11264 (2018)"},{"key":"16_CR34","unstructured":"Huang, G.B., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. In: Workshop on faces in Real-Life Images: Detection, Alignment, and Recognition (2008)"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Ji, M., Heo, B., Park, S.: Show, attend and distill: knowledge distillation via attention-based feature matching. In: AAAI, pp. 7945\u20137952 (2021)","DOI":"10.1609\/aaai.v35i9.16969"},{"key":"16_CR36","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Katakkar, A., Yoo, C.H., Wang, W., Lipton, Z.C., Kaushik, D.: Practical benefits of feature feedback under distribution shift. arXiv preprint arXiv:2110.07566 (2021)","DOI":"10.18653\/v1\/2022.blackboxnlp-1.29"},{"key":"16_CR39","unstructured":"Kim, H., Mnih, A.: Disentangling by factorising. In: ICML, pp. 2649\u20132658. PMLR (2018)"},{"key":"16_CR40","unstructured":"Kim, M., Wang, Y., Sahu, P., Pavlovic, V.: Relevance factor VAE: learning and identifying disentangled factors. arXiv preprint arXiv:1902.01568 (2019)"},{"key":"16_CR41","unstructured":"Kim, Y., Kim, D., Lee, H., Moon, I.c.: Unsupervised controllable generation with score-based diffusion models: disentangled latent code guidance. In: NeurIPS 2022 Workshop on Score-Based Methods (2022)"},{"key":"16_CR42","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"16_CR43","unstructured":"Knox, W.B., Stone, P.: Augmenting reinforcement learning with human feedback. In: ICML 2011 Workshop on New Developments in Imitation Learning, vol.\u00a0855, p.\u00a03 (2011)"},{"key":"16_CR44","unstructured":"Kumar, A., Sattigeri, P., Balakrishnan, A.: Variational inference of disentangled latent concepts from unlabeled observations. In: ICLR (2018)"},{"key":"16_CR45","unstructured":"Kwon, M., Jeong, J., Uh, Y.: Diffusion models already have a semantic latent space. arXiv preprint arXiv:2210.10960 (2022)"},{"key":"16_CR46","doi-asserted-by":"publisher","first-page":"e253","DOI":"10.1017\/S0140525X16001837","volume":"40","author":"BM Lake","year":"2017","unstructured":"Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. Brain Sci. 40, e253 (2017)","journal-title":"Behav. Brain Sci."},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Lee, H.Y., Tseng, H.Y., Huang, J.B., Singh, M., Yang, M.H.: Diverse image-to-image translation via disentangled representations. In: ECCV, pp. 35\u201351 (2018)","DOI":"10.1007\/978-3-030-01246-5_3"},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Lee, P.S., Sewell, D.K.: A revised diffusion model for conflict tasks. Psychon. Bull. Rev. 31, 1\u201331 (2023)","DOI":"10.3758\/s13423-023-02288-0"},{"key":"16_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/978-3-030-58574-7_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"W Lee","year":"2020","unstructured":"Lee, W., Kim, D., Hong, S., Lee, H.: High-fidelity synthesis with disentangled representation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 157\u2013174. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58574-7_10"},{"key":"16_CR50","doi-asserted-by":"crossref","unstructured":"Li, M., Jin, Y., Zhu, H.: Surrogate gradient field for latent space manipulation. In: CVPR, pp. 6529\u20136538 (2021)","DOI":"10.1109\/CVPR46437.2021.00646"},{"key":"16_CR51","unstructured":"Lin, Z., Thekumparampil, K.K., Fanti, G., Oh, S.: InfoGAN-CR: disentangling generative adversarial networks with contrastive regularizers. arXiv preprint arXiv:1906.06034 (2019)"},{"key":"16_CR52","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, J., Niu, L., Xu, R., Zhang, L.: Activity image-to-video retrieval by disentangling appearance and motion. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i3.16312"},{"key":"16_CR53","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Smoothing the disentangled latent style space for unsupervised image-to-image translation. In: CVPR, pp. 10785\u201310794 (2021)","DOI":"10.1109\/CVPR46437.2021.01064"},{"key":"16_CR54","unstructured":"Locatello, F., et al.: Challenging common assumptions in the unsupervised learning of disentangled representations. In: International Conference on Machine Learning, pp. 4114\u20134124. PMLR (2019)"},{"key":"16_CR55","doi-asserted-by":"crossref","unstructured":"Luo, Z., He, Y., Xue, Y., Wang, H., Hauskrecht, M., Li, T.: Hierarchical active learning with qualitative feedback on regions. IEEE Trans. Hum. Mach. Syst. 53(3), 581\u2013589 (2023)","DOI":"10.1109\/THMS.2023.3252815"},{"key":"16_CR56","doi-asserted-by":"crossref","unstructured":"Materzy\u0144ska, J., Torralba, A., Bau, D.: Disentangling visual and written concepts in clip. In: CVPR, pp. 16410\u201316419 (2022)","DOI":"10.1109\/CVPR52688.2022.01592"},{"key":"16_CR57","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Geiger, A.: GIRAFFE: representing scenes as compositional generative neural feature fields. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01129"},{"issue":"10","key":"16_CR58","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1038\/s41583-019-0202-9","volume":"20","author":"J Pearson","year":"2019","unstructured":"Pearson, J.: The human imagination: the cognitive neuroscience of visual mental imagery. Nat. Rev. Neurosci. 20(10), 624\u2013634 (2019)","journal-title":"Nat. Rev. Neurosci."},{"issue":"2","key":"16_CR59","doi-asserted-by":"publisher","first-page":"942","DOI":"10.1109\/TIT.2012.2219496","volume":"59","author":"M Pierobon","year":"2012","unstructured":"Pierobon, M., Akyildiz, I.F.: Capacity of a diffusion-based molecular communication system with channel memory and molecular noise. IEEE Trans. Inf. Theory 59(2), 942\u2013954 (2012)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"16_CR60","unstructured":"Plumerault, A., Borgne, H.L., Hudelot, C.: Controlling generative models with continuous factors of variations. In: ICLR (2020)"},{"key":"16_CR61","unstructured":"Poulis, S., Dasgupta, S.: Learning with feature feedback: from theory to practice. In: Artificial Intelligence and Statistics, pp. 1104\u20131113. PMLR (2017)"},{"key":"16_CR62","doi-asserted-by":"crossref","unstructured":"Preechakul, K., Chatthee, N., Wizadwongsa, S., Suwajanakorn, S.: Diffusion autoencoders: toward a meaningful and decodable representation. In: CVPR, pp. 10619\u201310629 (2022)","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"16_CR63","unstructured":"Ren, X., Yang, T., Wang, Y., Zeng, W.: Learning disentangled representation by exploiting pretrained generative models: a contrastive learning view. In: ICLR (2021)"},{"key":"16_CR64","unstructured":"Savva, M., et\u00a0al.: Habitat: a platform for embodied AI research. In: ICCV, pp. 9339\u20139347 (2019)"},{"key":"16_CR65","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"16_CR66","unstructured":"Shao, H., et al.: ControlVAE: controllable variational autoencoder. In: International Conference on Machine Learning, pp. 8655\u20138664. PMLR (2020)"},{"key":"16_CR67","doi-asserted-by":"crossref","unstructured":"Shen, Y., Gu, J., Tang, X., Zhou, B.: Interpreting the latent space of GANs for semantic face editing. In: CVPR, pp. 9243\u20139252 (2020)","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"16_CR68","doi-asserted-by":"crossref","unstructured":"Shen, Y., Zhou, B.: Closed-form factorization of latent semantics in GANs. In: CVPR, pp. 1532\u20131540 (2021)","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"16_CR69","doi-asserted-by":"crossref","unstructured":"Shi, Y., Yang, X., Wan, Y., Shen, X.: SemanticStyleGAN: learning compositional generative priors for controllable image synthesis and editing. In: CVPR, pp. 11254\u201311264 (2022)","DOI":"10.1109\/CVPR52688.2022.01097"},{"key":"16_CR70","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2020)"},{"key":"16_CR71","unstructured":"Song, Y., Keller, A., Sebe, N., Welling, M.: Latent traversals in generative models as potential flows. In: ICML (2023)"},{"key":"16_CR72","doi-asserted-by":"crossref","unstructured":"Song, Y., Zhang, J., Sebe, N., Wang, W.: Householder projector for unsupervised latent semantics discovery. In: ICCV, pp. 7712\u20137722 (2023)","DOI":"10.1109\/ICCV51070.2023.00709"},{"key":"16_CR73","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Teed","year":"2020","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"key":"16_CR74","doi-asserted-by":"crossref","unstructured":"Tran, L., Yin, X., Liu, X.: Disentangled representation learning GAN for pose-invariant face recognition. In: CVPR, pp. 1415\u20131424 (2017)","DOI":"10.1109\/CVPR.2017.141"},{"key":"16_CR75","unstructured":"Tsai, Y.H.H., Liang, P.P., Zadeh, A., Morency, L.P., Salakhutdinov, R.: Learning factorized multimodal representations. In: ICLR (2018)"},{"key":"16_CR76","unstructured":"Voynov, A., Babenko, A.: Unsupervised discovery of interpretable directions in the GAN latent space. In: ICML, pp. 9786\u20139796. PMLR (2020)"},{"key":"16_CR77","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhao, H., Li, X., Tan, X.: Progressive blockwise knowledge distillation for neural network acceleration. In: IJCAI, pp. 2769\u20132775 (2018)","DOI":"10.24963\/ijcai.2018\/384"},{"key":"16_CR78","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhang, Y., Fan, Y., Wang, J., Chen, Q.: High-fidelity GAN inversion for image attribute editing. In: CVPR, pp. 11379\u201311388 (2022)","DOI":"10.1109\/CVPR52688.2022.01109"},{"key":"16_CR79","unstructured":"Wang, X., Chen, H., Tang, S., Wu, Z., Zhu, W.: Disentangled representation learning. arXiv preprint arXiv:2211.11695 (2022)"},{"key":"16_CR80","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhao, L., Xing, W.: StyleDiffusion: controllable disentangled style transfer via diffusion models. In: ICCV, pp. 7677\u20137689 (2023)","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"16_CR81","unstructured":"Wu, J., Li, X., Ao, X., Meng, Y., Wu, F., Li, J.: Improving robustness and generality of NLP models using disentangled representations. arXiv preprint arXiv:2009.09587 (2020)"},{"key":"16_CR82","doi-asserted-by":"crossref","unstructured":"Wu, Q., et al.: Uncovering the disentanglement capability in text-to-image diffusion models. In: CVPR, pp. 1900\u20131910 (2023)","DOI":"10.1109\/CVPR52729.2023.00189"},{"key":"16_CR83","doi-asserted-by":"crossref","unstructured":"Wu, Y., Nakashima, Y., Garcia, N.: Not only generative art: stable diffusion for content-style disentanglement in art analysis. In: Proceedings of the 2023 ACM International Conference on Multimedia Retrieval, pp. 199\u2013208 (2023)","DOI":"10.1145\/3591106.3592262"},{"key":"16_CR84","doi-asserted-by":"crossref","unstructured":"Wu, Z., Lischinski, D., Shechtman, E.: StyleSpace analysis: disentangled controls for StyleGAN image generation. In: CVPR, pp. 12863\u201312872 (2021)","DOI":"10.1109\/CVPR46437.2021.01267"},{"key":"16_CR85","doi-asserted-by":"crossref","unstructured":"Xie, B., et al.: NaviNeRF: NeRF-based 3D representation disentanglement by latent semantic navigation. arXiv preprint arXiv:2304.11342 (2023)","DOI":"10.1109\/ICCV51070.2023.01649"},{"key":"16_CR86","doi-asserted-by":"crossref","unstructured":"Xu, X., Wang, Z., Zhang, G., Wang, K., Shi, H.: Versatile diffusion: text, images and variations all in one diffusion model. In: ICCV, pp. 7754\u20137765 (2023)","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"16_CR87","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Predict, prevent, and evaluate: disentangled text-driven image manipulation empowered by pre-trained vision-language model. In: CVPR, pp. 18229\u201318238 (2022)","DOI":"10.1109\/CVPR52688.2022.01769"},{"key":"16_CR88","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-319-46493-0_47","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Yan","year":"2016","unstructured":"Yan, X., Yang, J., Sohn, K., Lee, H.: Attribute2Image: conditional image generation from visual attributes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 776\u2013791. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_47"},{"key":"16_CR89","unstructured":"Yang, T., Wang, Y., Lan, C., Lu, Y., Zheng, N.: Vector-based representation is the key: a study on disentanglement and compositional generalization. arXiv preprint arXiv:2305.18063 (2023)"},{"key":"16_CR90","unstructured":"Yang, T., Wang, Y., Lv, Y., Zh, N.: DisDiff: unsupervised disentanglement of diffusion probabilistic models. arXiv preprint arXiv:2301.13721 (2023)"},{"key":"16_CR91","unstructured":"Yi, D., Lei, Z., Liao, S., Li, S.Z.: Learning face representation from scratch. arXiv preprint arXiv:1411.7923 (2014)"},{"key":"16_CR92","unstructured":"Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., Xiao, J.: LSUN: construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365 (2015)"},{"key":"16_CR93","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, Y., Guo, W., Cai, X., Yuan, X.: Learning disentangled representation for multimodal cross-domain sentiment analysis. TNNLS 34(10) (2022)","DOI":"10.1109\/TNNLS.2022.3147546"},{"key":"16_CR94","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xu, C., Tao, D.: Where and what? Examining interpretable disentangled representations. In: CVPR, pp. 5861\u20135870 (2021)","DOI":"10.1109\/CVPR46437.2021.00580"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72995-9_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T20:04:36Z","timestamp":1732392276000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72995-9_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"ISBN":["9783031729942","9783031729959"],"references-count":94,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72995-9_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,24]]},"assertion":[{"value":"24 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}