{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:49:48Z","timestamp":1743040188594,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031730238"},{"type":"electronic","value":"9783031730245"}],"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\/978-3-031-73024-5_6","type":"book-chapter","created":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T16:42:09Z","timestamp":1732552929000},"page":"86-100","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Multimodal Latent Generative Models with\u00a0Energy-Based Prior"],"prefix":"10.1007","author":[{"given":"Shiyu","family":"Yuan","sequence":"first","affiliation":[]},{"given":"Jiali","family":"Cui","sequence":"additional","affiliation":[]},{"given":"Hanao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Tian","family":"Han","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"issue":"2","key":"6_CR1","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2018","unstructured":"Baltru\u0161aitis, T., Ahuja, C., Morency, L.P.: Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 423\u2013443 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR2","unstructured":"Cui, J., Han, T.: Learning energy-based model via dual-MCMC teaching. In: 37th Conference on Neural Information Processing Systems (2023)"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Cui, J., Wu, Y.N., Han, T.: Learning hierarchical features with joint latent space energy-based prior. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2218\u20132227 (2023)","DOI":"10.1109\/ICCV51070.2023.00211"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Cui, J., Wu, Y.N., Han, T.: Learning joint latent space EBM prior model for multi-layer generator. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3603\u20133612 (2023)","DOI":"10.1109\/CVPR52729.2023.00351"},{"key":"6_CR5","unstructured":"Du, Y., Li, S., Tenenbaum, J., Mordatch, I.: Improved contrastive divergence training of energy based models. arXiv preprint arXiv:2012.01316 (2020)"},{"key":"6_CR6","unstructured":"Gao, R., Song, Y., Poole, B., Wu, Y.N., Kingma, D.P.: Learning energy-based models by diffusion recovery likelihood. arXiv preprint arXiv:2012.08125 (2020)"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10696\u201310706 (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Guo, J., Lu, S., Cai, H., Zhang, W., Yu, Y., Wang, J.: Long text generation via adversarial training with leaked information. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11957"},{"key":"6_CR9","unstructured":"Gupta, A., et al.: Photorealistic video generation with diffusion models. arXiv preprint arXiv:2312.06662 (2023)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Han, T., Lu, Y., Zhu, S.C., Wu, Y.N.: Alternating back-propagation for generator network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a031 (2017)","DOI":"10.1609\/aaai.v31i1.10902"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Han, T., Nijkamp, E., Zhou, L., Pang, B., Zhu, S.C., Wu, Y.N.: Joint training of variational auto-encoder and latent energy-based model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7978\u20137987 (2020)","DOI":"10.1109\/CVPR42600.2020.00800"},{"key":"6_CR12","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR13","first-page":"12194","volume":"34","author":"H Hwang","year":"2021","unstructured":"Hwang, H., Kim, G.H., Hong, S., Kim, K.E.: Multi-view representation learning via total correlation objective. Adv. Neural. Inf. Process. Syst. 34, 12194\u201312207 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Jiang, Q., et al.: Understanding and constructing latent modality structures in multi-modal representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7661\u20137671 (2023)","DOI":"10.1109\/CVPR52729.2023.00740"},{"key":"6_CR15","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"6_CR16","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.: Controllable text-to-image generation. Adv. Neural. Inf. Process. Syst. 32 (2019)"},{"key":"6_CR17","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: Vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR18","unstructured":"Lin, K., Li, D., He, X., Zhang, Z., Sun, M.T.: Adversarial ranking for language generation. Adv. Neural. Inf. Process. Syst. 30 (2017)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Lin, X., Bertasius, G., Wang, J., Chang, S.F., Parikh, D., Torresani, L.: VX2Text: end-to-end learning of video-based text generation from multimodal inputs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7005\u20137015 (2021)","DOI":"10.1109\/CVPR46437.2021.00693"},{"issue":"11","key":"6_CR20","first-page":"2","volume":"2","author":"RM Neal","year":"2011","unstructured":"Neal, R.M., et al.: MCMC using Hamiltonian dynamics. Handb. Markov Chain Monte Carlo 2(11), 2 (2011)","journal-title":"Handb. Markov Chain Monte Carlo"},{"key":"6_CR21","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Nijkamp, E., Hill, M., Han, T., Zhu, S.C., Wu, Y.N.: On the anatomy of MCMC-based maximum likelihood learning of energy-based models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 5272\u20135280 (2020)","DOI":"10.1609\/aaai.v34i04.5973"},{"key":"6_CR23","unstructured":"Nijkamp, E., Hill, M., Zhu, S.C., Wu, Y.N.: Learning non-convergent non-persistent short-run MCMC toward energy-based model. Adv. Neural. Inf. Process. Syst. 32 (2019)"},{"key":"6_CR24","unstructured":"Palumbo, E., Daunhawer, I., Vogt, J.E.: MMVAE+: enhancing the generative quality of multimodal VAEs without compromises. In: The Eleventh International Conference on Learning Representations. OpenReview (2023)"},{"key":"6_CR25","first-page":"21994","volume":"33","author":"B Pang","year":"2020","unstructured":"Pang, B., Han, T., Nijkamp, E., Zhu, S.C., Wu, Y.N.: Learning latent space energy-based prior model. Adv. Neural. Inf. Process. Syst. 33, 21994\u201322008 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR26","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"6_CR27","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR28","unstructured":"Shi, Y., Paige, B., Torr, P., et\u00a0al.: Variational mixture-of-experts autoencoders for multi-modal deep generative models. Adv. Neural. Inf. Process. Syst. 32 (2019)"},{"key":"6_CR29","unstructured":"S\u00f8\u00a0nderby, C.K., Raiko, T., Maal\u00f8\u00a0e, L., S\u00f8\u00a0nderby, S.R.K., Winther, O.: Ladder variational autoencoders. In: Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a029. Curran Associates, Inc. (2016). https:\/\/proceedings.neurips.cc\/paper\/2016\/file\/6ae07dcb33ec3b7c814df797cbda0f87-Paper.pdf"},{"key":"6_CR30","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: International Conference on Learning Representations (2020)"},{"key":"6_CR31","first-page":"6100","volume":"33","author":"T Sutter","year":"2020","unstructured":"Sutter, T., Daunhawer, I., Vogt, J.: Multimodal generative learning utilizing Jensen-Shannon-divergence. Adv. Neural. Inf. Process. Syst. 33, 6100\u20136110 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR32","unstructured":"Sutter, T.M., Daunhawer, I., Vogt, J.E.: Generalized multimodal ELBO. In: International Conference on Learning Representations (2021)"},{"key":"6_CR33","first-page":"19667","volume":"33","author":"A Vahdat","year":"2020","unstructured":"Vahdat, A., Kautz, J.: NVAE: a deep hierarchical variational autoencoder. Adv. Neural. Inf. Process. Syst. 33, 19667\u201319679 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR34","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-UCSD birds-200-2011 dataset (2011). authors.library.caltech.edu"},{"key":"6_CR35","unstructured":"Wu, M., Goodman, N.: Multimodal generative models for scalable weakly-supervised learning. Adv. Neural. Inf. Process. Syst. 31 (2018)"},{"key":"6_CR36","unstructured":"Xiao, Z., Han, T.: Adaptive multi-stage density ratio estimation for learning latent space energy-based model. In: NeurIPS (2022). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/874a4d89f2d04b4bcf9a2c19545cf040-Abstract-Conference.html"},{"key":"6_CR37","unstructured":"Xiao, Z., Kreis, K., Kautz, J., Vahdat, A.: VAEBM: a symbiosis between variational autoencoders and energy-based models. arXiv preprint arXiv:2010.00654 (2020)"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, H., Koh, J.Y., Baldridge, J., Lee, H., Yang, Y.: Cross-modal contrastive learning for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 833\u2013842 (2021)","DOI":"10.1109\/CVPR46437.2021.00089"}],"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\/978-3-031-73024-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T17:03:53Z","timestamp":1732554233000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73024-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"ISBN":["9783031730238","9783031730245"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73024-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}