{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T12:06:26Z","timestamp":1789041986561,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370198","type":"print"},{"value":"9783032370204","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37020-4_20","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:08:13Z","timestamp":1789038493000},"page":"362-379","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Synesthesia via\u00a0Direct Latent Augmentation: Bypassing the\u00a0Decode-Encode Loop for\u00a0Cross-Modal Distillation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6873-1967","authenticated-orcid":false,"given":"Cristian","family":"Sbrolli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6265-6748","authenticated-orcid":false,"given":"Nicolas","family":"Michel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8306-6739","authenticated-orcid":false,"given":"Matteo","family":"Matteucci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1784-2314","authenticated-orcid":false,"given":"Toshihiko","family":"Yamasaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 35, pp. 23716\u201323736 (2022)","DOI":"10.52202\/068431-1723"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Assran, M., et al.: Self-supervised learning from images with a joint-embedding predictive architecture. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15619\u201315629 (2023)","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"20_CR3","unstructured":"Azizi, S., Kornblith, S., Saharia, C., Norouzi, M., Fleet, D.J.: Synthetic data from diffusion models improves imagenet classification. Trans. Mach. Learn. Res. (2023)"},{"key":"20_CR4","unstructured":"Baevski, A., Babu, A., Hsu, W.N., Auli, M.: Efficient self-supervised learning with contextualized target representations for vision, speech and language. In: International Conference on Machine Learning, pp. 1416\u20131429 (2023)"},{"key":"20_CR5","unstructured":"Baevski, A., Hsu, W.N., Xu, Q., Babu, A., Gu, J., Auli, M.: Data2vec: a general framework for self-supervised learning in speech, vision and language. In: International Conference on Machine Learning, pp. 1298\u20131312 (2022)"},{"key":"20_CR6","unstructured":"Brusini, L., Sbrolli, C., Lomurno, E., Yamasaki, T., Matteucci, M.: Polygen: fully synthetic vision-language training via multi-generator ensembles. arXiv preprint arXiv:2602.01370 (2026)"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Copet, J., et al.: Simple and controllable music generation. In: Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-2066"},{"key":"20_CR8","volume-title":"Elements of Information Theory","author":"TM Cover","year":"1999","unstructured":"Cover, T.M.: Elements of Information Theory. Wiley, Hoboken (1999)"},{"issue":"4","key":"20_CR9","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S Davis","year":"1980","unstructured":"Davis, S., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28(4), 357\u2013366 (1980)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"20_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"El Banani, M., Desai, K., Johnson, J.: Learning visual representations via language-guided sampling. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19208\u201319220 (2023)","DOI":"10.1109\/CVPR52729.2023.01841"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Elizalde, B., Deshmukh, S., Al\u00a0Ismail, M., Wang, H.: Clap: learning audio concepts from natural language supervision. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp.\u00a01\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Garcia, N.C., Morerio, P., Murino, V.: Modality distillation with multiple stream networks for action recognition. In: European Conference on Computer Vision, pp. 103\u2013118 (2018)","DOI":"10.1007\/978-3-030-01237-3_7"},{"key":"20_CR15","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, S., Hoffman, J., Malik, J.: Cross-modal distillation for supervision transfer. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2827\u20132836 (2016)","DOI":"10.1109\/CVPR.2016.309"},{"key":"20_CR17","unstructured":"Hammoud, H.A.A.K., Itani, H., Pizzati, F., Torr, P., Bibi, A., Ghanem, B.: Synthclip: are we ready for a fully synthetic clip training? arXiv preprint arXiv:2402.01832 (2024)"},{"key":"20_CR18","unstructured":"He, R., et al.: Is synthetic data from generative models ready for image recognition? In: International Conference on Learning Representations (2023)"},{"key":"20_CR19","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv:1503.02531 (2015)"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Hoffman, J., Gupta, S., Leong, J., Guadarrama, S., Darrell, T.: Cross-modal adaptation for RGB-D detection. In: IEEE International Conference on Robotics and Automation, pp. 5032\u20135039 (2016)","DOI":"10.1109\/ICRA.2016.7487708"},{"key":"20_CR21","unstructured":"Howard, J.: Imagenette: a smaller subset of 10 easily classified classes from imagenet (2019). https:\/\/github.com\/fastai\/imagenette. Accessed 30 June 2026"},{"key":"20_CR22","unstructured":"Hu, N., Cheng, H., Xie, Y., Li, S., Zhu, J.: 3D-jepa: a joint embedding predictive architecture for 3D self-supervised representation learning. arXiv preprint arXiv:2409.15803 (2024)"},{"key":"20_CR23","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., Carreira, J.: Perceiver: general perception with iterative attention. In: International Conference on Machine Learning, pp. 4651\u20134664 (2021)"},{"key":"20_CR24","unstructured":"Kiela, D., Bhooshan, S., Firooz, H., Perez, E., Testuggine, D.: Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950 (2019)"},{"key":"20_CR25","unstructured":"Kreuk, F., et al.: Audiogen: textually guided audio generation. In: International Conference on Learning Representations (2023)"},{"issue":"4","key":"20_CR26","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1109\/TPAMI.2006.79","volume":"28","author":"FF Li","year":"2006","unstructured":"Li, F.F., Fergus, R., Perona, P.: One-shot learning of object categories. IEEE Trans. Pattern Anal. Mach. Intell. 28(4), 594\u2013611 (2006)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Lian, J., Baevski, A., Hsu, W.N., Auli, M.: AV-data2vec: self-supervised learning of audio-visual speech representations with contextualized target representations. In: IEEE Automatic Speech Recognition and Understanding Workshop, pp. 1\u20138 (2023)","DOI":"10.1109\/ASRU57964.2023.10389642"},{"key":"20_CR28","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: International Conference on Learning Representations (2023)"},{"key":"20_CR29","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Menadil, R.E., Georgescu, M.I., Ionescu, R.T.: Learning using generated privileged information by text-to-image diffusion models. In: International Conference on Pattern Recognition, pp. 423\u2013438 (2024)","DOI":"10.1007\/978-3-031-78183-4_27"},{"key":"20_CR31","unstructured":"Nagrani, A., Yang, S., Arnab, A., Jansen, A., Schmid, C., Sun, C.: Attention bottlenecks for multimodal fusion. In: Advances in Neural Information Processing Systems, vol. 34, pp. 14200\u201314213 (2021)"},{"key":"20_CR32","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: icarl: incremental classifier and representation learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2001\u20132010 (2017)","DOI":"10.1109\/CVPR.2017.587"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"20_CR35","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: hints for thin deep nets. In: International Conference on Learning Representations (2015)"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Sandru, A., Georgescu, M.I., Ionescu, R.T.: Feature-level augmentation to improve robustness of deep neural networks to affine transformations. In: European Conference on Computer Vision, pp. 332\u2013341 (2022)","DOI":"10.1007\/978-3-031-25056-9_22"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Sun, S., Cheng, Y., Gan, Z., Liu, J.: Patient knowledge distillation for BERT model compression. In: Conference on Empirical Methods in Natural Language Processing and the International Joint Conference on Natural Language Processing, pp. 4323\u20134332 (2019)","DOI":"10.18653\/v1\/D19-1441"},{"key":"20_CR38","unstructured":"Team, G., et al.: Gemma 3 technical report (2025)"},{"key":"20_CR39","unstructured":"Team, T.H.: Hunyuan3D 2.0: scaling diffusion models for high resolution textured 3D assets generation. arXiv preprint arXiv:2501.12202 (2025)"},{"key":"20_CR40","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive representation distillation. In: International Conference on Learning Representations (2020)"},{"key":"20_CR41","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357 (2021)"},{"issue":"5\u20136","key":"20_CR42","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1016\/j.neunet.2009.06.042","volume":"22","author":"V Vapnik","year":"2009","unstructured":"Vapnik, V., Vashist, A.: A new learning paradigm: learning using privileged information. Neural Netw. 22(5\u20136), 544\u2013557 (2009)","journal-title":"Neural Netw."},{"key":"20_CR43","doi-asserted-by":"publisher","first-page":"51284","DOI":"10.52202\/079017-1623","volume":"37","author":"M Wang","year":"2024","unstructured":"Wang, M., Michel, N., Mao, J., Yamasaki, T.: Dealing with synthetic data contamination in online continual learning. Adv. Neural. Inf. Process. Syst. 37, 51284\u201351311 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR44","doi-asserted-by":"crossref","unstructured":"Wang, W., Tran, D., Feiszli, M.: What makes training multi-modal classification networks hard? In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12695\u201312705 (2020)","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"20_CR45","unstructured":"Xiao, F., Lee, Y.J., Grauman, K., Malik, J., Feichtenhofer, C.: Audiovisual slowfast networks for video recognition. arXiv preprint arXiv:2001.08740 (2020)"},{"key":"20_CR46","doi-asserted-by":"crossref","unstructured":"Yuan, S., Stenger, B., Kim, T.K.: RGB-based 3D hand pose estimation via privileged learning with depth images (2018). arXiv:1811.07376","DOI":"10.1109\/ICCVW.2019.00348"},{"issue":"12","key":"20_CR47","doi-asserted-by":"publisher","first-page":"15098","DOI":"10.1109\/TPAMI.2023.3305243","volume":"45","author":"F Zhan","year":"2023","unstructured":"Zhan, F., et al.: Multimodal image synthesis and editing: the generative AI era. IEEE Trans. Pattern Anal. Mach. Intell. 45(12), 15098\u201315119 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR48","unstructured":"Zhao, C., Jin, Y., Song, Z., Chen, H., Miao, D., Hu, G.: Cross-modal distillation for widely differing modalities. arXiv preprint arXiv:2507.16296 (2025)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37020-4_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:08:29Z","timestamp":1789038509000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37020-4_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370198","9783032370204"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37020-4_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"11 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}