{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T07:39:25Z","timestamp":1767944365136,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543779","type":"print"},{"value":"9789819543786","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"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\/978-981-95-4378-6_21","type":"book-chapter","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T15:52:30Z","timestamp":1762789950000},"page":"299-313","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Emergence of\u00a0Fixational and\u00a0Saccadic Movements in\u00a0a\u00a0Multi-level Recurrent Attention Model for\u00a0Vision"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2324-3590","authenticated-orcid":false,"given":"Pengcheng","family":"Pan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3223-6902","authenticated-orcid":false,"given":"Shogo","family":"Yonekura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8443-4161","authenticated-orcid":false,"given":"Yasuo","family":"Kuniyoshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,9]]},"reference":[{"key":"21_CR1","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings (2014)"},{"issue":"10","key":"21_CR2","doi-asserted-by":"publisher","first-page":"1154","DOI":"10.1016\/j.visres.2008.07.012","volume":"49","author":"DM Beck","year":"2009","unstructured":"Beck, D.M., Kastner, S.: Top-down and bottom-up mechanisms in biasing competition in the human brain. Vision. Res. 49(10), 1154\u20131165 (2009)","journal-title":"Vision. Res."},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Butko, J.R.M.N.J.: Optimal scanning for faster object detection. In: Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009 (2009)","DOI":"10.1109\/CVPRW.2009.5206540"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Caicedo, J.C., Lazebnik, S.: Active object localization with deep reinforcement learning. In: ICCV, pp. 2488\u20132496. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.286"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Cao, C., et al.: Look and think twice: capturing top-down visual attention with feedback convolutional neural networks. In: ICCV, pp. 2956\u20132964. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.338"},{"key":"21_CR6","unstructured":"Chung, J., Ahn, S., Bengio, Y.: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326 (2017)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Degtyarenko, I., et al.: Hierarchical recurrent neural network for handwritten strokes classification. In: ICASSP, pp. 2865\u20132869. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413412"},{"issue":"6","key":"21_CR8","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","volume":"29","author":"L Deng","year":"2012","unstructured":"Deng, L.: The MNIST database of handwritten digit images for machine learning research. IEEE Signal Process. Mag. 29(6), 141\u2013142 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Desimone, R., Duncan, J.: Neural mechanisms of selective visual attention. Ann. Rev. Neurosci. 18, 193\u2013222\u2013 (1995)","DOI":"10.1146\/annurev.ne.18.030195.001205"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Desimone, R.: Visual attention mediated by biased competition in extrastriate visual cortex. Philos. Trans. Roy. Soc. Lond. Ser. B, Biol. Sci. 353, 1245\u201355 (1998)","DOI":"10.1098\/rstb.1998.0280"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: CVPR, pp. 1110\u20131118. IEEE Computer Society (2015)","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Dumitru, Goodfellow, I., Cukierski, W., Bengio, Y.: Challenges in representation learning: facial expression recognition challenge. Kaggle (2013)","DOI":"10.1007\/978-3-642-42051-1_16"},{"key":"21_CR13","unstructured":"Elsayed, G.F., Kornblith, S., Le, Q.V.: Saccader: improving accuracy of hard attention models for vision. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9 Buc, F., Fox, E.B., Garnett, R. (eds.) NeurIPS, pp. 700\u2013712 (2019)"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Fu, J., Zheng, H., Mei, T.: Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition. In: CVPR, pp. 4476\u20134484. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.476"},{"key":"21_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/978-3-540-30572-9_7","volume-title":"Attention and Performance in Computational Vision","author":"DA Gajewski","year":"2005","unstructured":"Gajewski, D.A., Pearson, A.M., Mack, M.L., Bartlett, F.N., Henderson, J.M.: Human gaze control in real world search. In: Paletta, L., Tsotsos, J.K., Rome, E., Humphreys, G. (eds.) WAPCV 2004. LNCS, vol. 3368, pp. 83\u201399. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/978-3-540-30572-9_7"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol.\u00a000, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"4","key":"21_CR17","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":"21_CR18","doi-asserted-by":"crossref","unstructured":"Hayhoe, M., Ballard, D.: Modeling task control of eye movements. Curr. Biol. 24, R622\u2013R628 (2014)","DOI":"10.1016\/j.cub.2014.05.020"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Hengst, B.: Hierarchical Reinforcement Learning, pp. 495\u2013502. Springer, Boston (2010)","DOI":"10.1007\/978-0-387-30164-8_363"},{"issue":"8","key":"21_CR20","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"issue":"11","key":"21_CR21","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254\u20131259 (1998)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR22","unstructured":"Kandel, E.R., Schwarz, J.H., Jessel, T.M.: Principles of Neural Science. McGraw-Hill, 4. edn. (2000)"},{"key":"21_CR23","unstructured":"Larochelle, H., Hinton, G.E.: Learning to combine foveal glimpses with a third-order Boltzmann machine. In: Lafferty, J.D., Williams, C.K.I., Shawe-Taylor, J., Zemel, R.S., Culotta, A. (eds.) NIPS, pp. 1243\u20131251. Curran Associates, Inc. (2010)"},{"issue":"7553","key":"21_CR24","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)","journal-title":"Nature"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Li, Z., Yang, Y., Liu, X., Zhou, F., Wen, S., Xu, W.: Dynamic computational time for visual attention. In: ICCV Workshops, pp. 1199\u20131209 (2017)","DOI":"10.1109\/ICCVW.2017.145"},{"key":"21_CR26","unstructured":"Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) NIPS, pp. 2204\u20132212 (2014)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Qiao, T., Dong, J., Xu, D.: Exploring human-like attention supervision in visual question answering. In: McIlraith, S.A., Weinberger, K.Q. (eds.) AAAI, pp. 7300\u20137307. AAAI Press (2018)","DOI":"10.1609\/aaai.v32i1.12272"},{"issue":"3","key":"21_CR28","doi-asserted-by":"publisher","first-page":"p372","DOI":"10.1037\/0033-2909.124.3.372","volume":"124","author":"K Rayner","year":"1998","unstructured":"Rayner, K.: Eye movements in reading and information processing: 20 years of research. Psychol. Bull. 124(3), p372-422 (1998)","journal-title":"Psychol. Bull."},{"issue":"6","key":"21_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2024.100983","volume":"5","author":"A Sharafeldin","year":"2024","unstructured":"Sharafeldin, A., Imam, N., Choi, H.: Active sensing with predictive coding and uncertainty minimization. Patterns 5(6), 100983 (2024)","journal-title":"Patterns"},{"key":"21_CR30","unstructured":"Sutton, R.S., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Proceedings of the 12th International Conference on Neural Information Processing Systems. NIPS\u201999, Cambridge, MA, USA, pp. 1057\u20131063. MIT Press (1999)"},{"key":"21_CR31","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1023\/A:1022672621406","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"21_CR32","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms (2017)"},{"key":"21_CR33","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: Bach, F.R., Blei, D.M. (eds.) Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015. JMLR Workshop and Conference Proceedings, vol.\u00a037, pp. 2048\u20132057 (2015)"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., Hovy, E.: Hierarchical attention networks for document classification. In: Knight, K., Nenkova, A., Rambow, O. (eds.) Proceedings of the 2016 Conference of the NAACL-HLT, San Diego, California, pp. 1480\u20131489. Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/N16-1174"},{"key":"21_CR35","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-5379-7","volume-title":"Eye Movements and Vision","author":"AL Yarbus","year":"1967","unstructured":"Yarbus, A.L.: Eye Movements and Vision. Springer, US (1967)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4378-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T05:59:23Z","timestamp":1767938363000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4378-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,9]]},"ISBN":["9789819543779","9789819543786"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4378-6_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,9]]},"assertion":[{"value":"9 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have\u00a0no competing interests to declare that are relevant to the content\u00a0of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}