{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T04:03:20Z","timestamp":1749269000805,"version":"3.41.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031915772","type":"print"},{"value":"9783031915789","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91578-9_22","type":"book-chapter","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T09:23:13Z","timestamp":1749201793000},"page":"289-298","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Variable Resolution Improves Visual Question Answering Under a\u00a0Limited Pixel Budget"],"prefix":"10.1007","author":[{"given":"Andrey","family":"Gizdov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shimon","family":"Ullman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4745-9292","authenticated-orcid":false,"given":"Daniel","family":"Harari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"22_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pcbi.1005743","volume":"13","author":"E Akbas","year":"2017","unstructured":"Akbas, E., Eckstein, M.P.: Object detection through search with a foveated visual system. PLoS Comput. Biol. 13, 1\u201328 (2017)","journal-title":"PLoS Comput. Biol."},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Bar, M.: A cortical mechanism for triggering top-down facilitation in visual object recognition. J. Cogn. Neurosci. 600\u2013609 (2003)","DOI":"10.1162\/089892903321662976"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"22_CR4","unstructured":"Deza, A., Konkle, T.: Emergent properties of foveated perceptual systems (2021)"},{"issue":"9","key":"22_CR5","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1038\/nn.2889","volume":"14","author":"J Freeman","year":"2011","unstructured":"Freeman, J., Simoncelli, E.P.: Metamers of the ventral stream. Nat. Neurosci. 14(9), 1195\u20131201 (2011)","journal-title":"Nat. Neurosci."},{"issue":"4","key":"22_CR6","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1007\/s11263-018-1116-0","volume":"127","author":"Y Goyal","year":"2019","unstructured":"Goyal, Y., Khot, T., Agrawal, A., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. Int. J. Comput. Vision 127(4), 398\u2013414 (2019)","journal-title":"Int. J. Comput. Vision"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Han, Y., Roig, G., Geiger, G., Poggio, T.: Is the Human Visual System Invariant to Translation and Scale? pp. 564\u2013568 (2017)","DOI":"10.1167\/17.10.471"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"22_CR11","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/978-3-030-24741-6_17","volume-title":"Biomimetic and Biohybrid Systems","author":"U Jaramillo-Avila","year":"2019","unstructured":"Jaramillo-Avila, U., Anderson, S.R.: Foveated image processing for faster object detection and recognition in embedded systems using deep convolutional neural networks. In: Martinez-Hernandez, U., et al. (eds.) Living Machines 2019. LNCS (LNAI), vol. 11556, pp. 193\u2013204. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-24741-6_17"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: MDETR - modulated detection for end-to-end multi-modal understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1780\u20131790 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"22_CR13","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594 (2021)"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Li, B., Wang, R., Wang, G., Ge, Y., Ge, Y., Shan, Y.: Seed-bench: benchmarking multimodal LLMs with generative comprehension. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"22_CR15","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)"},{"key":"22_CR16","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":"22_CR17","doi-asserted-by":"crossref","unstructured":"Lukanov, H., K\u00f6nig, P., Pipa, G.: Biologically inspired deep learning model for efficient foveal-peripheral vision. Front. Comput. Neurosci. 15 (2021)","DOI":"10.3389\/fncom.2021.746204"},{"issue":"7","key":"22_CR18","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1364\/JOSA.70.000868","volume":"70","author":"D Marr","year":"1980","unstructured":"Marr, D., Poggio, T., Hildreth, E.: Smallest channel in early human vision. J. Opt. Soc. Am. 70(7), 868\u2013870 (1980)","journal-title":"J. Opt. Soc. Am."},{"issue":"Suppl 2","key":"22_CR19","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1007\/s10336-007-0213-6","volume":"148","author":"GR Martin","year":"2007","unstructured":"Martin, G.R.: Visual fields and their functions in birds. J. Ornithol. 148(Suppl 2), 547\u2013562 (2007)","journal-title":"J. Ornithol."},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Nguyen, P., Quach, K.G., Duong, C.N., Le, N., Nguyen, X.B., Luu, K.: Multi-camera multiple 3D object tracking on the move for autonomous vehicles. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2569\u20132578 (2022)","DOI":"10.1109\/CVPRW56347.2022.00289"},{"issue":"12","key":"22_CR21","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.tics.2007.09.009","volume":"11","author":"A Oliva","year":"2007","unstructured":"Oliva, A., Torralba, A.: The role of context in object recognition. Trends Cogn. Sci. 11(12), 520\u2013527 (2007)","journal-title":"Trends Cogn. Sci."},{"key":"22_CR22","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1109\/TIP.2020.3034487","volume":"30","author":"Y Pang","year":"2021","unstructured":"Pang, Y., Cao, J., Li, Y., Xie, J., Sun, H., Gong, J.: TJU-DHD: a diverse high-resolution dataset for object detection. IEEE Trans. Image Process. 30, 207\u2013219 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Paula, B., Moreno, P.: Learning to search for and detect objects in foveal images using deep learning. In: Conference on Pattern Recognition and Image Analysis, pp. 223\u2013237. Springer (2023)","DOI":"10.1007\/978-3-031-36616-1_18"},{"key":"22_CR24","unstructured":"Poggio, T., Mutch, J., Isik, L.: Computational role of eccentricity dependent cortical magnification. Technical Report CBMM Memo 017 (2014)"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Pramod, R.T., Katti, H., Arun, S.P.: Human peripheral blur is optimal for object recognition. Vis. Res. 200 (2022)","DOI":"10.1016\/j.visres.2022.108083"},{"key":"22_CR26","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1146\/annurev-vision-093019-113212","volume":"7","author":"JC Read","year":"2021","unstructured":"Read, J.C.: Binocular vision and stereopsis across the animal kingdom. Annu. Rev. Vis. Sci. 7, 389\u2013415 (2021)","journal-title":"Annu. Rev. Vis. Sci."},{"issue":"16","key":"22_CR27","doi-asserted-by":"publisher","first-page":"25241","DOI":"10.1007\/s11042-021-10918-9","volume":"80","author":"Y Said","year":"2021","unstructured":"Said, Y., Barr, M.: Human emotion recognition based on facial expressions via deep learning on high-resolution images. Multimedia Tools Appl. 80(16), 25241\u201325253 (2021). https:\/\/doi.org\/10.1007\/s11042-021-10918-9","journal-title":"Multimedia Tools Appl."},{"key":"22_CR28","doi-asserted-by":"publisher","first-page":"1958","DOI":"10.1109\/TPAMI.2008.128","volume":"30","author":"A Torralba","year":"2008","unstructured":"Torralba, A., Fergus, R., Freeman, W.T.: 80 million tiny images: a large data set for nonparametric object and scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 30, 1958\u201370 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR29","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/BF00422717","volume":"31","author":"CB Trevarthen","year":"1968","unstructured":"Trevarthen, C.B.: Two mechanisms of vision in primates. Psychol. Forsch. 31, 299\u2013337 (1968)","journal-title":"Psychol. Forsch."},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Wang, P., Cottrell, G.W.: Central and peripheral vision for scene recognition: a neurocomputational modeling exploration. J. Vis. 17(4), 9 (2017)","DOI":"10.1167\/17.4.9"},{"issue":"1","key":"22_CR31","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/0042-6989(79)90117-2","volume":"19","author":"HR Wilson","year":"1979","unstructured":"Wilson, H.R., Bergen, J.R.: A four mechanism model for spatial vision. Vision. Res. 19(1), 19\u201332 (1979)","journal-title":"Vision. Res."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91578-9_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T09:23:20Z","timestamp":1749201800000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91578-9_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915772","9783031915789"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91578-9_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}