{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:35:18Z","timestamp":1763202918335,"version":"3.40.3"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031723407"},{"type":"electronic","value":"9783031723414"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72341-4_2","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T13:02:55Z","timestamp":1726491775000},"page":"17-31","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Masked Image Modeling as\u00a0a\u00a0Framework for\u00a0Self-Supervised Learning Across Eye Movements"],"prefix":"10.1007","author":[{"given":"Robin","family":"Weiler","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Brucklacher","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cyriel M. A.","family":"Pennartz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sander M.","family":"Boht\u00e9","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"2_CR1","unstructured":"LeCun, Y.: A path towards autonomous machine intelligence version 0.9.2, 2022-06-27. Open Rev. 62(1) (2022)"},{"key":"2_CR2","unstructured":"van\u00a0den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. Preprint arXiv:1807.03748 (2018)"},{"key":"2_CR3","unstructured":"Bardes, A., Ponce, J., LeCun,Y.: Vicreg: variance-invariance-covariance regularization for self-supervised learning. Preprint arXiv:2105.04906 (2021)"},{"key":"2_CR4","unstructured":"Grill, J.-B., et\u00a0al.: Bootstrap your own latent-a new approach to self-supervised learning. In: NeurIPS, vol. 33, 21271\u201321284 (2020)"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: CVPR, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Assran, M., et al.: Self-supervised learning from images with a joint-embedding predictive architecture. In: CVPR, pp. 15619\u201315629 (2023)","DOI":"10.1109\/CVPR52729.2023.01499"},{"issue":"11","key":"2_CR8","doi-asserted-by":"publisher","first-page":"1906","DOI":"10.1038\/s41593-023-01460-y","volume":"26","author":"Manu Srinath Halvagal and Friedemann Zenke","year":"2023","unstructured":"Manu Srinath Halvagal and Friedemann Zenke: The combination of Hebbian and predictive plasticity learns invariant object representations in deep sensory networks. Nat. Neurosci. 26(11), 1906\u20131915 (2023)","journal-title":"Nat. Neurosci."},{"key":"2_CR9","unstructured":"Illing, B., Ventura, J., Bellec, G., Gerstner, W.: Local plasticity rules can learn deep representations using self-supervised contrastive predictions. In: NeurIPS, vol. 34, pp. 30365\u201330379 (2021)"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Simons, D.J., Chabris, C.F.: Gorillas in our midst: sustained inattentional blindness for dynamic events. Perception 28(9), 1059\u20131074 (1999)","DOI":"10.1068\/p281059"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Crapse, T.B., Sommer, M.A.: The frontal eye field as a prediction map. Progress Brain Res. 171, 383\u2013390 (2008)","DOI":"10.1016\/S0079-6123(08)00656-0"},{"issue":"20","key":"2_CR12","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1007\/BF00622503","volume":"37","author":"E Von Holst","year":"1950","unstructured":"Von Holst, E., Mittelstaedt, H.: Das reafferenzprinzip: Wechselwirkungen zwischen zentralnervensystem und peripherie. Naturwissenschaften 37(20), 464\u2013476 (1950)","journal-title":"Naturwissenschaften"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Woo, S., et al.: ConvNeXt v2: co-designing and scaling convnets with masked autoencoders. In: CVPR, pp. 16133\u201316142 (2023)","DOI":"10.1109\/CVPR52729.2023.01548"},{"issue":"5","key":"2_CR14","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1162\/neco.1995.7.5.889","volume":"7","author":"P Dayan","year":"1995","unstructured":"Dayan, P., Hinton, G.E., Neal, R.M., Zemel, R.S.: The helmholtz machine. Neural Comput. 7(5), 889\u2013904 (1995)","journal-title":"Neural Comput."},{"issue":"1","key":"2_CR15","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1038\/4580","volume":"2","author":"RPN Rao","year":"1999","unstructured":"Rao, R.P.N., Ballard, D.H.: Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. Nature Neurosci. 2(1), 79\u201387 (1999)","journal-title":"Nature Neurosci."},{"issue":"1456","key":"2_CR16","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1098\/rstb.2005.1622","volume":"360","author":"K Friston","year":"2005","unstructured":"Friston, K.: A theory of cortical responses. Philosoph. Trans. Royal Soc. B: Biol. Sci. 360(1456), 815\u2013836 (2005)","journal-title":"Philosoph. Trans. Royal Soc. B: Biol. Sci."},{"key":"2_CR17","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262029315.001.0001","volume-title":"The Brain\u2019s Representational Power: On Consciousness and the Integration of Modalities","author":"CMA Pennartz","year":"2015","unstructured":"Pennartz, C.M.A.: The Brain\u2019s Representational Power: On Consciousness and the Integration of Modalities. MIT Press, Cambridge (2015)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Kong, L., et al.: Understanding masked autoencoders via hierarchical latent variable models. In: CVPR, pp. 7918\u20137928 (2023)","DOI":"10.1109\/CVPR52729.2023.00765"},{"issue":"19","key":"2_CR19","doi-asserted-by":"publisher","first-page":"7403","DOI":"10.1523\/JNEUROSCI.5114-14.2015","volume":"35","author":"BV Ehinger","year":"2015","unstructured":"Ehinger, B.V., K\u00f6nig, P., Ossand\u00f3n, J.P.: Predictions of visual content across eye movements and their modulation by inferred information. J. Neurosci. 35(19), 7403\u20137413 (2015)","journal-title":"J. Neurosci."},{"issue":"41","key":"2_CR20","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2204248119","volume":"119","author":"T Tsao","year":"2022","unstructured":"Tsao, T., Tsao, D.Y.: A topological solution to object segmentation and tracking. PNAS 119(41), e2204248119 (2022)","journal-title":"PNAS"},{"key":"2_CR21","doi-asserted-by":"publisher","unstructured":"Brucklacher, M., Pezzulo, G., Mannella, F., Galati, G., Pennartz, C.M.A.: Learning to segment self-generated from externally caused optic flow through sensorimotor mismatch circuits. bioRxiv preprint, pp. 2023\u201311 (2023). https:\/\/doi.org\/10.1101\/2023.11.15.567170v2","DOI":"10.1101\/2023.11.15.567170v2"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"H\u00e9naff, O.J., Koppula, S., Alayrac, J.-B., Van\u00a0den Oord, A., Vinyals, O., Carreira, J.: Efficient visual pretraining with contrastive detection. In: CVPR, pp. 10086\u201310096 (2021)","DOI":"10.1109\/ICCV48922.2021.00993"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: SimMIM: a simple framework for masked image modeling. In: CVPR, pp. 9653\u20139663 (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"issue":"6","key":"2_CR24","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1038\/s41583-020-0277-3","volume":"21","author":"TP Lillicrap","year":"2020","unstructured":"Lillicrap, T.P., Santoro, A., Marris, L., Akerman, C.J., Hinton, G.: Backpropagation and the brain. Nature Rev. Neurosci. 21(6), 335\u2013346 (2020)","journal-title":"Nature Rev. Neurosci."},{"issue":"5","key":"2_CR25","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1162\/NECO_a_00949","volume":"29","author":"JCR Whittington","year":"2017","unstructured":"Whittington, J.C.R., Bogacz, R.: An approximation of the error backpropagation algorithm in a predictive coding network with local Hebbian synaptic plasticity. Neural Comput. 29(5), 1229\u20131262 (2017)","journal-title":"Neural Comput."},{"key":"2_CR26","unstructured":"Renninger, L., Coughlan, J., Verghese, P., Malik, J.: An information maximization model of eye movements. In: NeurIPS, 17 (2004)"},{"key":"2_CR27","doi-asserted-by":"publisher","first-page":"151","DOI":"10.3389\/fpsyg.2012.00151","volume":"3","author":"K Friston","year":"2012","unstructured":"Friston, K., Adams, R.A., Perrinet, L., Breakspear, M.: Perceptions as hypotheses: saccades as experiments. Front. Psychol. 3, 151 (2012)","journal-title":"Front. Psychol."},{"key":"2_CR28","unstructured":"Larochelle, H., Hinton, G.E.: Learning to combine foveal glimpses with a thirdorder Boltzmann machine. In: NeurIPS, vol. 23 (2010)"},{"key":"2_CR29","unstructured":"Thompson, J.A.F., Sheahan, H., Summerfield, C.: Learning to count visual objects by combining \u201cwhat\u201d and \u201cwhere\u201d in recurrent memory. In: NeuRIPS 2022 Workshop on Gaze Meets ML, pp. 199\u2013218 (2022)"},{"issue":"12","key":"2_CR30","doi-asserted-by":"publisher","first-page":"1182","DOI":"10.1093\/cercor\/11.12.1182","volume":"11","author":"AT Smith","year":"2001","unstructured":"Smith, A.T., Singh, K.D., Williams, A.L., Greenlee, M.W.: Estimating receptive field size from fMRI data in human striate and extrastriate visual cortex. Cerebral Cortex 11(12), 1182\u20131190 (2001)","journal-title":"Cerebral Cortex"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR32","unstructured":"Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 215\u2013223. JMLR Workshop and Conference Proceedings (2011)"},{"key":"2_CR33","unstructured":"Purves, D., et al.: Neuroscience, 3rd ed. Sinauer Associates (2004)"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Perry, J.S., Geisler, W.S.: Gaze-contingent real-time simulation of arbitrary visual fields. In: Human Vision and Electronic Imaging VII, vol. 4662, pp. 57\u201369. SPIE (2002)","DOI":"10.1117\/12.469554"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Jiang, M., Huang, S., Duan, J., Zhao, Q.: Salicon: saliency in context. In: CVPR, pp. 1072\u20131080 (2015)","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"2_CR36","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"2_CR37","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"issue":"01","key":"2_CR38","first-page":"217","volume":"1","author":"HB Barlow","year":"1961","unstructured":"Barlow, H.B., et al.: Possible principles underlying the transformation of sensory messages. Sensory Commun. 1(01), 217\u2013233 (1961)","journal-title":"Sensory Commun."},{"key":"2_CR39","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: self-supervised learning via redundancy reduction. In: ICML Proceedings, pp. 12310\u201312320. PMLR (2021)"},{"issue":"4","key":"2_CR40","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1016\/j.tics.2005.02.009","volume":"9","author":"M Hayhoe","year":"2005","unstructured":"Hayhoe, M., Ballard, D.: Eye movements in natural behavior. Trends Cogn. Sci. 9(4), 188\u2013194 (2005)","journal-title":"Trends Cogn. Sci."},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Yarbus, A.L.: Eye Movements and Vision. Plenum Press (1967)","DOI":"10.1007\/978-1-4899-5379-7"},{"issue":"6583","key":"2_CR42","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1038\/381607a0","volume":"381","author":"BA Olshausen","year":"1996","unstructured":"Olshausen, B.A., Field, D.J.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381(6583), 607\u2013609 (1996)","journal-title":"Nature"},{"key":"2_CR43","doi-asserted-by":"publisher","first-page":"1136","DOI":"10.3758\/BF03194840","volume":"65","author":"R Houtkamp","year":"2003","unstructured":"Houtkamp, R., Spekreijse, H., Roelfsema, P.R.: A gradual spread of attention. Percept. Psychophys 65, 1136\u20131144 (2003)","journal-title":"Percept. Psychophys"},{"key":"2_CR44","unstructured":"L\u00f6we, S., O\u2019Connor, P., Veeling, B.: Putting an end to end-to-end: Gradient-isolated learning of representations. In: NeurIPS, vol. 32 (2019)"},{"key":"2_CR45","unstructured":"Siddiqui, S.A. Krueger, D., LeCun, Y., Deny, S.: Blockwise self-supervised learning at scale. Preprint arXiv:2302.01647 (2023)"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Kong, X., Zhang, X.: Understanding masked image modeling via learning occlusion invariant feature. In: CVPR, pp. 6241\u20136251 (2023)","DOI":"10.1109\/CVPR52729.2023.00604"},{"key":"2_CR47","unstructured":"Jing, L., Zhu, J., LeCun, Y.: Masked siamese convnets. arXiv preprint arXiv:2206.07700 (2022)"},{"key":"2_CR48","unstructured":"Feichtenhofer, C., Li, Y., He, K., et al.: Masked autoencoders as spatiotemporal learners. In: NeurIPS, vol. 35, pp. 35946\u201335958 (2022)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72341-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T13:09:51Z","timestamp":1726492191000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72341-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723407","9783031723414"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72341-4_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}