{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T23:05:05Z","timestamp":1789254305153,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032369680","type":"print"},{"value":"9783032369697","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\/978-3-032-36969-7_6","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:20:59Z","timestamp":1789251659000},"page":"97-114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MJEPA: A Simple and\u00a0Scalable Joint-Embedding Predictive Architecture for\u00a0Audio-Visual Learning"],"prefix":"10.1007","author":[{"given":"Revant","family":"Teotia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adrien","family":"Bardes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Rabbat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sumit","family":"Chopra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Muckley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Ballas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"6_CR1","unstructured":"Akbari, H., et al.: VATT: transformers for multimodal self-supervised learning from raw video, audio and text. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol.\u00a034, pp. 24206\u201324221. Curran Associates, Inc. (2021). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/cb3213ada48302953cb0f166464ab356-Paper.pdf"},{"key":"6_CR2","unstructured":"Alex, T., Atito, S., Mustafa, A., Awais, M., Jackson, P.J.B.: SSLAM: enhancing self-supervised models with audio mixtures for polyphonic soundscapes. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=odU59TxdiB"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Araujo, E., et al.: CAV-MAE sync: improving contrastive audio-visual mask autoencoders via fine-grained alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2025)","DOI":"10.1109\/CVPR52734.2025.01751"},{"key":"6_CR5","unstructured":"Assran, M., et al.: V-JEPA\u00a02: self-supervised video models enable understanding, prediction and planning. arXiv preprint arXiv:2506.09985 (2025)"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Assran, M., et al.: Self-supervised learning from images with a joint-embedding predictive architecture. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15619\u201315629 (2023)","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"6_CR7","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 (2022). https:\/\/arxiv.org\/abs\/2202.03555"},{"key":"6_CR8","unstructured":"Bardes, A., et al.: Revisiting feature prediction for learning visual representations from video (2024). arXiv:2404.08471"},{"issue":"6","key":"6_CR9","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","volume":"16","author":"S Chen","year":"2022","unstructured":"Chen, S., et al.: WavLM: large-scale self-supervised pre-training for full stack speech processing. IEEE J. Sel. Top. Signal Process. 16(6), 1505\u20131518 (2022)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"6_CR10","unstructured":"Chen, S., et al.: BEATs: audio pre-training with acoustic tokenizers. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) Proceedings of the 40th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 5178\u20135193. PMLR, 23\u201329 July 2023. https:\/\/proceedings.mlr.press\/v202\/chen23ag.html"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Dinkel, H., Yan, Z., Wang, Y., Zhang, J., Wang, Y., Wang, B.: Scaling up masked audio encoder learning for general audio classification. In: Interspeech 2024 (2024)","DOI":"10.21437\/Interspeech.2024-246"},{"key":"6_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"6_CR13","unstructured":"Fei, Z., Fan, M., Huang, J.: A-JEPA: joint-embedding predictive architecture can listen (2024). https:\/\/arxiv.org\/abs\/2311.15830"},{"key":"6_CR14","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1109\/TASLP.2021.3133208","volume":"30","author":"E Fonseca","year":"2022","unstructured":"Fonseca, E., Favory, X., Pons, J., Font, F., Serra, X.: FSD50K: an open dataset of human-labeled sound events. IEEE\/ACM Trans. Audio Speech Lang. Process. 30, 829\u2013852 (2022)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"6_CR15","doi-asserted-by":"publisher","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780 (2017). https:\/\/doi.org\/10.1109\/ICASSP.2017.7952261","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Georgescu, M.I., Fonseca, E., Ionescu, R.T., Lucic, M., Schmid, C., Arnab, A.: Audio-visual masked autoencoders. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01479"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: ImageBind: one embedding space to bind them all. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"6_CR18","doi-asserted-by":"publisher","unstructured":"Gong, Y., Chung, Y.A., Glass, J.: AST: audio spectrogram transformer. In: Proceedings of Interspeech 2021, pp. 571\u2013575 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-698","DOI":"10.21437\/Interspeech.2021-698"},{"key":"6_CR19","unstructured":"Gong, Y., et al.: Contrastive audio-visual masked autoencoder. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=QPtMRyk5rb"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense (2017). https:\/\/arxiv.org\/abs\/1706.04261","DOI":"10.1109\/ICCV.2017.622"},{"key":"6_CR21","unstructured":"Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21271\u201321284 (2020)"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377 (2021)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Huang, P.Y., et al.: MAVil: masked audio-video learners. In: Thirty-Seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=OmTMaTbjac","DOI":"10.52202\/075280-0894"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Huang, P.Y., et al.: Masked autoencoders that listen. In: NeurIPS (2022)","DOI":"10.52202\/068431-2081"},{"key":"6_CR25","unstructured":"Huh, M., Cheung, B., Wang, T., Isola, P.: Position: the platonic representation hypothesis. In: Salakhutdinov, R., et al. (eds.) Proceedings of the 41st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0235, pp. 20617\u201320642. PMLR, 21\u201327 July 2024. https:\/\/proceedings.mlr.press\/v235\/huh24a.html"},{"key":"6_CR26","unstructured":"Kay, W., et al.: The kinetics human action video dataset (2017). https:\/\/arxiv.org\/abs\/1705.06950"},{"key":"6_CR27","unstructured":"Kim, J., Lee, H., Rho, K., Kim, J., Chung, J.S.: EquiAV: leveraging equivariance for audio-visual contrastive learning. In: Salakhutdinov, R., et al. (eds.) Proceedings of the 41st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0235, pp. 24327\u201324341. PMLR, 21\u201327 July 2024. https:\/\/proceedings.mlr.press\/v235\/kim24v.html"},{"key":"6_CR28","unstructured":"LeCun, Y., et\u00a0al.: A path towards autonomous machine intelligence version 0.9.2, 2022-06-27. Open Rev. 62(1), 1\u201362 (2022)"},{"key":"6_CR29","unstructured":"Lee, J.J., Yoon, S.W.: Can one modality model synergize training of other modality models? In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=5BXWhVbHAK"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Lin, Y.B., Bertasius, G.: Siamese vision transformers are scalable audio-visual learners. arXiv preprint arXiv:2403.19638 (2024)","DOI":"10.1007\/978-3-031-72630-9_18"},{"key":"6_CR31","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2019). https:\/\/arxiv.org\/abs\/1711.05101"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: HowTo100M: learning a text-video embedding by watching hundred million narrated video clips. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"6_CR33","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. Trans. Mach. Learn. Res. (2024). https:\/\/openreview.net\/forum?id=a68SUt6zFt. Featured Certification"},{"key":"6_CR34","doi-asserted-by":"publisher","unstructured":"Piczak, K.J.: ESC: dataset for environmental sound classification. In: Proceedings of the 23rd Annual ACM Conference on Multimedia, pp. 1015\u20131018. ACM Press (2015). https:\/\/doi.org\/10.1145\/2733373.2806390. http:\/\/dl.acm.org\/citation.cfm?doid=2733373.2806390","DOI":"10.1145\/2733373.2806390"},{"key":"6_CR35","unstructured":"Rauch, L., Heinrich, R., Ghaffari, H., Miklautz, L., Moummad, I., Sick, B., Scholz, C.: Unmute the patch tokens: rethinking probing in multi-label audio classification. In: The Fourteenth International Conference on Learning Representations (2026). https:\/\/openreview.net\/forum?id=FbY5Co2NWk"},{"key":"6_CR36","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge (2015). https:\/\/arxiv.org\/abs\/1409.0575"},{"key":"6_CR37","unstructured":"Sarkar, P., Etemad, A.: XKD: cross-modal knowledge distillation with domain alignment for video representation learning (2022)"},{"key":"6_CR38","unstructured":"Sim\u00e9oni, O., et al.: Dinov3 (2025). https:\/\/arxiv.org\/abs\/2508.10104"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: NeurIPS (2022)","DOI":"10.52202\/068431-0732"},{"key":"6_CR40","unstructured":"Yang, X., et al.: Spear: a unified SSL framework for learning speech and audio representations (2026). https:\/\/arxiv.org\/abs\/2510.25955"},{"key":"6_CR41","unstructured":"Yu, S., et al.: Representation alignment for generation: training diffusion transformers is easier than you think. In: International Conference on Learning Representations (2025)"},{"key":"6_CR42","unstructured":"Zhu, B., et al.: LanguageBind: extending video-language pretraining to n-modality by language-based semantic alignment. In: Kim, B., Yue, Y., Chaudhuri, S., Fragkiadaki, K., Khan, M., Sun, Y. (eds.) International Conference on Learning Representations, vol.\u00a02024, pp. 9588\u20139608 (2024). https:\/\/proceedings.iclr.cc\/paper_files\/paper\/2024\/file\/2862ccf01e3843c81623b246895bcc45-Paper-Conference.pdf"}],"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\/978-3-032-36969-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:21:06Z","timestamp":1789251666000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36969-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032369680","9783032369697"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36969-7_6","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":"13 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"}}]}}