{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T20:50:14Z","timestamp":1743108614439,"version":"3.40.3"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726637"},{"type":"electronic","value":"9783031726644"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72664-4_7","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:02:04Z","timestamp":1729875724000},"page":"112-129","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AdaGlimpse: Active Visual Exploration with\u00a0Arbitrary Glimpse Position and\u00a0Scale"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3406-6732","authenticated-orcid":false,"given":"Adam","family":"Pardyl","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5208-9900","authenticated-orcid":false,"given":"Micha\u0142","family":"Wronka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3933-9971","authenticated-orcid":false,"given":"Maciej","family":"Wo\u0142czyk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2917-4392","authenticated-orcid":false,"given":"Kamil","family":"Adamczewski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1486-8906","authenticated-orcid":false,"given":"Tomasz","family":"Trzci\u0144ski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3063-3621","authenticated-orcid":false,"given":"Bartosz","family":"Zieli\u0144ski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Abnar, S., Zuidema, W.: Quantifying attention flow in transformers. arXiv preprint arXiv:2005.00928 (2020)","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"7_CR2","unstructured":"Alexe, B., Heess, N., Teh, Y., Ferrari, V.: Searching for objects driven by context. Adv. Neural Inf. Process. Syst. 25 (2012)"},{"key":"7_CR3","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. In: ICLR (2015)"},{"key":"7_CR4","unstructured":"Ba, J., Salakhutdinov, R.R., Grosse, R.B., Frey, B.J.: Learning wake-sleep recurrent attention models. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Beyer, L., Izmailov, P., Kolesnikov, A., et\u00a0al.: Flexivit: one model for all patch sizes. arXiv:2212.08013 (2022)","DOI":"10.1109\/CVPR52729.2023.01393"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Caicedo, J.C., Lazebnik, S.: Active object localization with deep reinforcement learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2488\u20132496 (2015)","DOI":"10.1109\/ICCV.2015.286"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Chai, Y.: Patchwork: a patch-wise attention network for efficient object detection and segmentation in video streams. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3415\u20133424 (2019)","DOI":"10.1109\/ICCV.2019.00351"},{"key":"7_CR8","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: 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":"7_CR10","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Double Robotics, Inc.: Double 3 - telepresence robot for the hybrid office (2024). https:\/\/www.doublerobotics.com\/. Accessed 24 Feb 2024","DOI":"10.1155\/2024\/9831614"},{"key":"7_CR12","unstructured":"Elsayed, G., Kornblith, S., Le, Q.V.: Saccader: improving accuracy of hard attention models for vision. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Singh, M., Ravi, N., van\u00a0der Maaten, L., Joulin, A., Misra, I.: Omnivore: a single model for many visual modalities. In: ICCV (2022)","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"7_CR14","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"7_CR15","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396 (2021)"},{"key":"7_CR16","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"issue":"4","key":"7_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":"7_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., et\u00a0al.: Masked autoencoders are scalable vision learners. In: CVPR, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"7_CR19","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"7_CR20","unstructured":"Ilse, M., Tomczak, J., Welling, M.: Attention-based deep multiple instance learning. In: International Conference on Machine Learning, pp. 2127\u20132136. PMLR (2018)"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Jha, A., Seifi, S., Tuytelaars, T.: Simglim: simplifying glimpse based active visual reconstruction. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 269\u2013278 (2023)","DOI":"10.1109\/WACV56688.2023.00035"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Krotenok, A.Y., Yu, A.S., Yu, V.A.: The change in the altitude of an unmanned aerial vehicle, depending on the height difference of the area taken. In: IOP Conference Series: Earth and Environmental Science, vol.\u00a0272, p. 022165. IOP Publishing (2019)","DOI":"10.1088\/1755-1315\/272\/2\/022165"},{"key":"7_CR23","unstructured":"K\u00fcmmerer, M., Theis, L., Bethge, M.: Deep gaze I: boosting saliency prediction with feature maps trained on imagenet. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Workshop Track Proceedings (2015)"},{"key":"7_CR24","unstructured":"Li, C., et al.: Efficient self-supervised vision transformers for representation learning. arXiv preprint arXiv:2106.09785 (2021)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Li, W., Lin, Z., Zhou, K., Qi, L., Wang, Y., Jia, J.: Mat: mask-aware transformer for large hole image inpainting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10758\u201310768 (2022)","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"7_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"7_CR27","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2018)"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Mathe, S., Pirinen, A., Sminchisescu, C.: Reinforcement learning for visual object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2894\u20132902 (2016)","DOI":"10.1109\/CVPR.2016.316"},{"key":"7_CR29","unstructured":"Mnih, V., Heess, N., Graves, A., et\u00a0al.: Recurrent models of visual attention. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"7_CR30","first-page":"14694","volume":"34","author":"A Papadopoulos","year":"2021","unstructured":"Papadopoulos, A., Korus, P., Memon, N.: Hard-attention for scalable image classification. Adv. Neural. Inf. Process. Syst. 34, 14694\u201314707 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR31","unstructured":"Pardyl, A., Kurzejamski, G., Olszewski, J., Trzci\u0144ski, T., Zieli\u0144ski, B.: Beyond grids: exploring elastic input sampling for vision transformers. arXiv preprint arXiv:2309.13353 (2023)"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Pardyl, A., Rype\u015b\u0107, G., Kurzejamski, G., Zieli\u0144ski, B., Trzci\u0144ski, T.: Active visual exploration based on attention-map entropy. In: Elkind, E. (ed.) Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23, pp. 1303\u20131311 (2023)","DOI":"10.24963\/ijcai.2023\/145"},{"key":"7_CR33","doi-asserted-by":"publisher","first-page":"1616","DOI":"10.1007\/s11263-021-01437-z","volume":"129","author":"SK Ramakrishnan","year":"2021","unstructured":"Ramakrishnan, S.K., Jayaraman, D., Grauman, K.: An exploration of embodied visual exploration. Int. J. Comput. Vision 129, 1616\u20131649 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"7_CR34","unstructured":"Rangrej, S.B., Clark, J.J.: A probabilistic hard attention model for sequentially observed scenes. arXiv preprint arXiv:2111.07534 (2021)"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Rangrej, S.B., Srinidhi, C.L., Clark, J.J.: Consistency driven sequential transformers attention model for partially observable scenes. In: CVRP, pp. 2518\u20132527 (2022)","DOI":"10.1109\/CVPR52688.2022.00255"},{"key":"7_CR36","unstructured":"Ranzato, M.: On learning where to look. arXiv preprint arXiv:1405.5488 (2014)"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Recasens, A., Kellnhofer, P., Stent, S., Matusik, W., Torralba, A.: Learning to zoom: a saliency-based sampling layer for neural networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 51\u201366 (2018)","DOI":"10.1007\/978-3-030-01240-3_4"},{"key":"7_CR38","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-7091-6025-1_18","volume-title":"Sensors and Sensing in Biology and Engineering","author":"G Sandini","year":"2003","unstructured":"Sandini, G., Metta, G.: Retina-like sensors: motivations, technology and applications. In: Barth, F.G., Humphrey, J.A.C., Secomb, T.W. (eds.) Sensors and Sensing in Biology and Engineering, pp. 251\u2013262. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/978-3-7091-6025-1_18"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Seifi, S., Jha, A., Tuytelaars, T.: Glimpse-attend-and-explore: self-attention for active visual exploration. In: ICCV, pp. 16137\u201316146 (2021)","DOI":"10.1109\/ICCV48922.2021.01583"},{"key":"7_CR40","unstructured":"Seifi, S., Tuytelaars, T.: Where to look next: unsupervised active visual exploration on 360$$^\\circ $$ input. CoRR arxiv:1909.10304 (2019)"},{"key":"7_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/978-3-030-58595-2_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Seifi","year":"2020","unstructured":"Seifi, S., Tuytelaars, T.: Attend and segment: attention guided active semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 305\u2013321. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_19"},{"key":"7_CR42","unstructured":"\u015amieja, M., Struski, \u0141., Tabor, J., Zieli\u0144ski, B., Spurek, P.: Processing of missing data by neural networks. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun rgb-d: a rgb-d scene understanding benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"7_CR44","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (2018)"},{"key":"7_CR45","doi-asserted-by":"publisher","unstructured":"Touvron, H., Cord, M., J\u00e9gou, H.: Deit iii: revenge of the vit. In: European Conference on Computer Vision, pp. 516\u2013533. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_30","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"7_CR46","doi-asserted-by":"crossref","unstructured":"Uzkent, B., Ermon, S.: Learning when and where to zoom with deep reinforcement learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12345\u201312354 (2020)","DOI":"10.1109\/CVPR42600.2020.01236"},{"key":"7_CR47","first-page":"2432","volume":"33","author":"Y Wang","year":"2020","unstructured":"Wang, Y., Lv, K., Huang, R., Song, S., Yang, L., Huang, G.: Glance and focus: a dynamic approach to reducing spatial redundancy in image classification. Adv. Neural. Inf. Process. Syst. 33, 2432\u20132444 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR48","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/978-3-030-71278-5_29","volume-title":"Pattern Recognition","author":"P Wenzel","year":"2021","unstructured":"Wenzel, P., et al.: 4seasons: a cross-season dataset for multi-weather slam in autonomous driving. In: Akata, Z., Geiger, A., Sattler, T. (eds.) Pattern Recognition, pp. 404\u2013417. Springer, Cham (2021)"},{"key":"7_CR49","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Girshick, R., He, K., Feichtenhofer, C., Krahenbuhl, P.: A multigrid method for efficiently training video models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 153\u2013162 (2020)","DOI":"10.1109\/CVPR42600.2020.00023"},{"key":"7_CR50","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"7_CR51","doi-asserted-by":"crossref","unstructured":"Yoo, D., Park, S., Lee, J.Y., Paek, A.S., So\u00a0Kweon, I.: Attentionnet: aggregating weak directions for accurate object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2659\u20132667 (2015)","DOI":"10.1109\/ICCV.2015.305"},{"key":"7_CR52","doi-asserted-by":"crossref","unstructured":"Zheng, S., et\u00a0al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"7_CR53","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72664-4_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:03:30Z","timestamp":1729875810000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72664-4_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726637","9783031726644"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72664-4_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}