{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T12:46:14Z","timestamp":1770813974097,"version":"3.50.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["Grant No. 61802053"],"award-info":[{"award-number":["Grant No. 61802053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"crossref","award":["Grant No. 2024NSFSC0508"],"award-info":[{"award-number":["Grant No. 2024NSFSC0508"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Fund of National Laboratory on Adaptive Optics, China","award":["Grant No. FNLAO-24-ZD-O02"],"award-info":[{"award-number":["Grant No. FNLAO-24-ZD-O02"]}]},{"name":"Key Lab. For Civil Aviation Data Governance and Decision Optimization"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s00530-025-02064-1","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T07:00:12Z","timestamp":1764831612000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Energy-based causal disentanglement for compositional zero-shot learning"],"prefix":"10.1007","volume":"32","author":[{"given":"Yuankang","family":"Pan","sequence":"first","affiliation":[]},{"given":"Zining","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zhaoquan","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"key":"2064_CR1","doi-asserted-by":"publisher","unstructured":"Anwaar, M.U., Pan, Z., Kleinsteuber, M.: On leveraging variational graph embeddings for open world compositional zero-shot learning. In: MM \u201922: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10\u201314, 2022. ACM, pp 4645\u20134654, (2022). https:\/\/doi.org\/10.1145\/3503161.3547798","DOI":"10.1145\/3503161.3547798"},{"key":"2064_CR2","unstructured":"Atzmon, Y., Kreuk, F., Shalit, U., et\u00a0al.: A causal view of compositional zero-shot recognition. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6\u201312, 2020, virtual (2020)"},{"key":"2064_CR3","unstructured":"Chen, H., Du, Y., Chen, Y., et\u00a0al.: Planning with sequence models through iterative energy minimization. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1\u20135, 2023 (2023)"},{"key":"2064_CR4","doi-asserted-by":"crossref","unstructured":"Chytas, S.P., Kim, H.J., Singh, V.: Understanding multi-compositional learning in vision and language models via category theory. In: European Conference on Computer Vision, Springer, pp 324\u2013341 (2024)","DOI":"10.1007\/978-3-031-73195-2_19"},{"key":"2064_CR5","unstructured":"Du, Y., Li, S., Mordatch, I.: Compositional visual generation with energy based models. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6\u201312, 2020, virtual (2020)"},{"key":"2064_CR6","unstructured":"Du, Y., Li, S., Sharma, Y., et\u00a0al.: Unsupervised learning of compositional energy concepts. In: Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6\u201314, 2021, virtual, pp 15608\u201315620 (2021)"},{"key":"2064_CR7","unstructured":"Du, Y., Li, S., Tenenbaum, J.B., et\u00a0al.: Improved contrastive divergence training of energy-based models. In: Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, Proceedings of Machine Learning Research, vol 139. PMLR, pp 2837\u20132848 (2021)"},{"key":"2064_CR8","doi-asserted-by":"crossref","unstructured":"Hao, S., Han, K., Wong, K.Y.K.: Learning attention as disentangler for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 15315\u201315324(2023)","DOI":"10.1109\/CVPR52729.2023.01470"},{"key":"2064_CR9","doi-asserted-by":"crossref","unstructured":"Huo, F., Xu, W., Guo, S., et\u00a0al.: Procc: Progressive cross-primitive compatibility for open-world compositional zero-shot learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 12689\u201312697 (2024)","DOI":"10.1609\/aaai.v38i11.29164"},{"key":"2064_CR10","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1613\/jair.1.11674","volume":"67","author":"D Hupkes","year":"2020","unstructured":"Hupkes, D., Dankers, V., Mul, M., et al.: Compositionality decomposed: How do neural networks generalise? J. Artif. Intell. Res. 67, 757\u2013795 (2020)","journal-title":"J. Artif. Intell. Res."},{"key":"2064_CR11","doi-asserted-by":"publisher","unstructured":"Isola, P., Lim, J.J., Adelson, E.H.: Discovering states and transformations in image collections. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7\u201312, 2015. IEEE Computer Society, pp 1383\u20131391, (2015) https:\/\/doi.org\/10.1109\/CVPR.2015.7298744","DOI":"10.1109\/CVPR.2015.7298744"},{"key":"2064_CR12","doi-asserted-by":"publisher","unstructured":"Khan, M.G.Z.A., Naeem, M.F., Gool, L.V., et\u00a0al.: Learning attention propagation for compositional zero-shot learning. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV 2023, Waikoloa, HI, USA, January 2\u20137, 2023. IEEE, pp 3817\u20133826, (2023). https:\/\/doi.org\/10.1109\/WACV56688.2023.00382","DOI":"10.1109\/WACV56688.2023.00382"},{"key":"2064_CR13","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837","volume":"40","author":"BM Lake","year":"2017","unstructured":"Lake, B.M., Ullman, T.D., Tenenbaum, J.B., et al.: Building machines that learn and think like people. Behav. Brain Sci. 40, e253 (2017)","journal-title":"Behav. Brain Sci."},{"key":"2064_CR14","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Chopra, S., Hadsell, R., et al.: A tutorial on energy-based learning. Predict. Struct. Data (2006)","DOI":"10.7551\/mitpress\/7443.003.0014"},{"key":"2064_CR15","unstructured":"Li, S., Du, Y., Tenenbaum, J.B., et al.: Composing ensembles of pre-trained models via iterative consensus. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1\u20135 (2023)"},{"key":"2064_CR16","doi-asserted-by":"crossref","unstructured":"Li, X., Yang, X., Wei, K., et al.: Siamese contrastive embedding network for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 9326\u20139335 (2022)","DOI":"10.1109\/CVPR52688.2022.00911"},{"issue":"12","key":"2064_CR17","doi-asserted-by":"publisher","first-page":"9043","DOI":"10.1109\/TPAMI.2021.3119406","volume":"44","author":"Y Li","year":"2022","unstructured":"Li, Y., Xu, Y., Xu, X., et al.: Learning single\/multi-attribute of object with symmetry and group. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9043\u20139055 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3119406","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2064_CR18","doi-asserted-by":"publisher","unstructured":"Li, Y., Liu, Z., Jha, S., et al.: Distilled reverse attention network for open-world compositional zero-shot learning. In: IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1\u20136, 2023. IEEE, pp 1782\u20131791 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00171","DOI":"10.1109\/ICCV51070.2023.00171"},{"key":"2064_CR19","unstructured":"Liu, H., Abbeel, P.: Hybrid discriminative-generative training via contrastive learning. CoRR abs\/2007.09070 (2020) https:\/\/arxiv.org\/abs\/2007.09070,"},{"key":"2064_CR20","unstructured":"Liu, N., Li, S., Du, Y., et al.: Learning to compose visual relations. In: Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6\u201314, 2021, virtual, pp 23166\u201323178 (2021)"},{"key":"2064_CR21","doi-asserted-by":"publisher","unstructured":"Liu, N., Li, S., Du, Y., et al.: Compositional visual generation with composable diffusion models. In: Computer Vision-ECCV 2022-17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XVII, Lecture Notes in Computer Science, vol 13677. Springer, pp 423\u2013439 (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_26","DOI":"10.1007\/978-3-031-19790-1_26"},{"issue":"1","key":"2064_CR22","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1109\/TPAMI.2023.3323012","volume":"46","author":"Z Liu","year":"2024","unstructured":"Liu, Z., Li, Y., Yao, L., et al.: Simple primitives with feasibility- and contextuality-dependence for open-world compositional zero-shot learning. IEEE Trans. Pattern Anal. Mach. Intell. 46(1), 543\u2013560 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2023.3323012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2064_CR23","doi-asserted-by":"crossref","unstructured":"Ma, X., Yang, J., Lin, J., et al.: Lvar-czsl: Learning visual attributes representation for compositional zero-shot learning. IEEE Trans. Circ. Syst. Video Technol. (2024)","DOI":"10.1109\/TCSVT.2024.3444782"},{"key":"2064_CR24","doi-asserted-by":"crossref","unstructured":"Mancini, M., Naeem, M.F., Xian, Y., et al.: Open world compositional zero-shot learning. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp 5222\u20135230 (2021)","DOI":"10.1109\/CVPR46437.2021.00518"},{"issue":"3","key":"2064_CR25","doi-asserted-by":"publisher","first-page":"1545","DOI":"10.1109\/TPAMI.2022.3163667","volume":"46","author":"M Mancini","year":"2022","unstructured":"Mancini, M., Naeem, M.F., Xian, Y., et al.: Learning graph embeddings for open world compositional zero-shot learning. IEEE Trans. Pattern Anal. Mach. Intell. 46(3), 1545\u20131560 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2064_CR26","unstructured":"Marcus, G.F.: The algebraic mind: Integrating connectionism and cognitive science. MIT Press"},{"key":"2064_CR27","doi-asserted-by":"crossref","unstructured":"Misra, I., Gupta, A., Hebert, M.: From red wine to red tomato: Composition with context. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition pp 1792\u20131801 (2017)","DOI":"10.1109\/CVPR.2017.129"},{"key":"2064_CR28","doi-asserted-by":"crossref","unstructured":"Naeem, M.F., Xian, Y., Tombari, F., et al.: Learning graph embeddings for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 953\u2013962 (2021)","DOI":"10.1109\/CVPR46437.2021.00101"},{"key":"2064_CR29","doi-asserted-by":"crossref","unstructured":"Nagarajan, T., Grauman, K.: Attributes as operators: factorizing unseen attribute-object compositions. In: Proceedings of the European Conference on Computer Vision (ECCV) pp 169\u2013185 (2018)","DOI":"10.1007\/978-3-030-01246-5_11"},{"key":"2064_CR30","unstructured":"Nayak, N.V., Yu, P., Bach, S.H.: Learning to compose soft prompts for compositional zero-shot learning. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1\u20135, (2023)"},{"key":"2064_CR31","doi-asserted-by":"publisher","unstructured":"Nijkamp, E., Hill, M., Han, T., et al.: On the anatomy of mcmc-based maximum likelihood learning of energy-based models. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020. AAAI Press, pp 5272\u20135280 (2020). https:\/\/doi.org\/10.1609\/AAAI.V34I04.5973","DOI":"10.1609\/AAAI.V34I04.5973"},{"key":"2064_CR32","doi-asserted-by":"crossref","unstructured":"Purushwalkam, S., Nickel, M., Gupta, A., et\u00a0al.: Task-driven modular networks for zero-shot compositional learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 3593\u20133602 (2019)","DOI":"10.1109\/ICCV.2019.00369"},{"key":"2064_CR33","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, PMLR, pp 8748\u20138763 (2021)"},{"key":"2064_CR34","doi-asserted-by":"publisher","unstructured":"Reddy, A.G., L, B.G., Balasubramanian VN.: On causally disentangled representations. In: Thirty-Sixth AAAI Conference on Artificial Intelligence AAAI 2022. AAAI Press, pp 8089\u20138097 (2022). https:\/\/doi.org\/10.1609\/AAAI.V36I7.20781","DOI":"10.1609\/AAAI.V36I7.20781"},{"key":"2064_CR35","first-page":"10641","volume":"34","author":"F Ruis","year":"2021","unstructured":"Ruis, F., Burghouts, G., Bucur, D.: Independent prototype propagation for zero-shot compositionality. Adv. Neural. Inf. Process. Syst. 34, 10641\u201310653 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2064_CR36","doi-asserted-by":"crossref","unstructured":"Saini, N., Pham, K., Shrivastava, A.: Disentangling visual embeddings for attributes and objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 13658\u201313667 (2022)","DOI":"10.1109\/CVPR52688.2022.01329"},{"key":"2064_CR37","unstructured":"Suter, R., Miladinovic, D., Sch\u00f6lkopf, B., et al.: Robustly disentangled causal mechanisms: Validating deep representations for interventional robustness. In: Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9\u201315 June 2019, Long Beach, California, USA, Proceedings of Machine Learning Research, vol\u00a097. PMLR, pp 6056\u20136065 (2019)"},{"key":"2064_CR38","doi-asserted-by":"publisher","unstructured":"Wang, Q., Liu, L., Jing, C., et al.: Learning conditional attributes for compositional zero-shot learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17\u201324, 2023. IEEE, pp 11197\u201311206 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01077","DOI":"10.1109\/CVPR52729.2023.01077"},{"key":"2064_CR39","unstructured":"Wu, C.H., Motamed, S., Srivastava, S., et al.: Generative visual prompt: Unifying distributional control of pre-trained generative models. In: Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28\u2013December 9, 2022 (2022)"},{"key":"2064_CR40","unstructured":"Xiao, Z., Kreis, K., Kautz, J., et al.: VAEBM: A symbiosis between variational autoencoders and energy-based models. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021 (2021)"},{"key":"2064_CR41","doi-asserted-by":"publisher","first-page":"5892","DOI":"10.1109\/TMM.2022.3200578","volume":"25","author":"M Yang","year":"2023","unstructured":"Yang, M., Xu, C., Wu, A., et al.: A decomposable causal view of compositional zero-shot learning. IEEE Trans. Multimedia 25, 5892\u20135902 (2023). https:\/\/doi.org\/10.1109\/TMM.2022.3200578","journal-title":"IEEE Trans. Multimedia"},{"key":"2064_CR42","doi-asserted-by":"publisher","unstructured":"Yu, A., Grauman, K.: Fine-grained visual comparisons with local learning. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, OH, USA, June 23\u201328, 2014. IEEE Computer Society, pp 192\u2013199 (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.32","DOI":"10.1109\/CVPR.2014.32"},{"key":"2064_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, T., Liang, K., Zhang, K., et al.: Learning conditional prompt for compositional zero-shot learning. In: 2024 IEEE International Conference on Multimedia and Expo (ICME), IEEE (2024)","DOI":"10.1109\/ICME57554.2024.10688263"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02064-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02064-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02064-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T04:21:01Z","timestamp":1770783661000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02064-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2064"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02064-1","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]},"assertion":[{"value":"3 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"6"}}