{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:14:09Z","timestamp":1789038849621,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372703","type":"print"},{"value":"9783032372710","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\/978-3-032-37271-0_14","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:00:44Z","timestamp":1789038044000},"page":"242-269","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DeepGaze3.5-VL: Modeling Scanpaths via\u00a0Autoregressive Token Prediction"],"prefix":"10.1007","author":[{"given":"Susmit","family":"Agrawal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Bethge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"K\u00fcmmerer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Aydemir, B., Hoffstetter, L., Zhang, T., Salzmann, M., S\"usstrunk, S.: Tempsal - Uncovering temporal information for deep saliency prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00625"},{"issue":"9","key":"14_CR2","doi-asserted-by":"publisher","first-page":"967","DOI":"10.1016\/0042-6989(79)90222-0","volume":"19","author":"W Becker","year":"1979","unstructured":"Becker, W., J\u00fcrgens, R.: An analysis of the saccadic system by means of double step stimuli. Vision. Res. 19(9), 967\u2013983 (1979)","journal-title":"Vision. Res."},{"issue":"1\u20132","key":"14_CR3","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.physa.2003.09.011","volume":"331","author":"G Boccignone","year":"2004","unstructured":"Boccignone, G., Ferraro, M.: Modelling gaze shift as a constrained random walk. Physica A Stat. Mech. Appl. 331(1\u20132), 207\u2013218 (2004)","journal-title":"Physica A Stat. Mech. Appl."},{"key":"14_CR4","unstructured":"Borji, A., Itti, L.: Cat 2000: a large scale fixation dataset for boosting saliency research. arXiv preprint arXiv:1505.03581 (2015)"},{"key":"14_CR5","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/j.visres.2015.03.005","volume":"116","author":"Z Bylinskii","year":"2015","unstructured":"Bylinskii, Z., Isola, P., Bainbridge, C., Torralba, A., Oliva, A.: Intrinsic and extrinsic effects on image memorability. Vision. Res. 116, 165\u2013178 (2015)","journal-title":"Vision. Res."},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Cartella, G., et al.: Modeling human gaze behavior with diffusion models for unified scanpath prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.01504"},{"key":"14_CR7","unstructured":"Chen, K., et al.: Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic. arXiv preprint arXiv:2306.15195 (2023)"},{"key":"14_CR8","unstructured":"Chen, T., Saxena, S., Li, L., Fleet, D.J., Hinton, G.: Pix2seq: a language modeling framework for object detection. arXiv preprint arXiv:2109.10852 (2021)"},{"issue":"1","key":"14_CR9","doi-asserted-by":"publisher","first-page":"8776","DOI":"10.1038\/s41598-021-87715-9","volume":"11","author":"Y Chen","year":"2021","unstructured":"Chen, Y., et al.: Coco-search18: a dataset for predicting goal-directed attention control. Sci. Rep. 11(1), 8776 (2021)","journal-title":"Sci. Rep."},{"key":"14_CR10","unstructured":"D\u2019Agostino, F., Schwetlick, L., Bethge, M., K\u00fcmmerer, M.: What moves the eyes: doubling mechanistic model performance using deep networks to discover and test cognitive hypotheses. In: NeurIPS Workshop on Gaze Meets ML (2022)"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"David, E.V.D.H.: Potsdam data set of eye movement on natural scenes (DAEMONS). Front. Psychol. 15 (2024)","DOI":"10.3389\/fpsyg.2024.1389609"},{"issue":"4","key":"14_CR12","doi-asserted-by":"publisher","first-page":"455","DOI":"10.3758\/BF03195475","volume":"34","author":"AT Duchowski","year":"2002","unstructured":"Duchowski, A.T.: A breadth-first survey of eye-tracking applications. Behav. Res. Methods Instrum. Comput. 34(4), 455\u2013470 (2002)","journal-title":"Behav. Res. Methods Instrum. Comput."},{"issue":"4","key":"14_CR13","first-page":"1","volume":"15","author":"R Engbert","year":"2015","unstructured":"Engbert, R., Rothkegel, L.O., Metzner, P., Nuthmann, A.: Scenewalk: a cognitive model for eye movements during natural scene viewing. J. Vis. 15(4), 1\u20131 (2015)","journal-title":"J. Vis."},{"issue":"24","key":"14_CR14","doi-asserted-by":"publisher","first-page":"11687","DOI":"10.1073\/pnas.1820553116","volume":"116","author":"B de Haas","year":"2019","unstructured":"de Haas, B., Iakovidis, A.L., Schwarzkopf, D.S., Gegenfurtner, K.R.: Individual differences in visual salience vary along a single semantic dimension. Proc. Natl. Acad. Sci. 116(24), 11687\u201311692 (2019)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"14_CR15","doi-asserted-by":"publisher","unstructured":"de Haas, B., Iakovidis, A.L., Schwarzkopf, D.S., Gegenfurtner, K.R.: Individual differences in visual salience vary along semantic dimensions. Proc. Natl. Acad. Sci. 116(24), 11687\u201311692 (2019). https:\/\/doi.org\/10.1073\/pnas.1820553116. https:\/\/www.pnas.org\/doi\/abs\/10.1073\/pnas.1820553116","DOI":"10.1073\/pnas.1820553116"},{"key":"14_CR16","unstructured":"Hu, E.J., et al.: LoRA: Low-Rank adaptation of large language models. In: International Conference on Learning Representations (2022)"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Huang, X., Shen, C., Boix, X., Zhao, Q.: Salicon: reducing the semantic gap in saliency prediction by adapting deep neural networks. In: Proceedings of the IEEE international conference on computer vision, pp. 262\u2013270 (2015)","DOI":"10.1109\/ICCV.2015.38"},{"key":"14_CR18","unstructured":"Itti, L., Koch, C.: A saliency-based search mechanism for guiding visual attention. Cognitive Vision Systems: Spatial Communication and Scene Understanding, pp. 97\u2013106 (2000)"},{"issue":"11","key":"14_CR19","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":"14_CR20","doi-asserted-by":"publisher","unstructured":"Jelinek, F., Mercer, R.L., Bahl, L.R., Baker, J.K.: Perplexity\u2014a measure of the difficulty of speech recognition tasks. J. Acoust. Soc. Am. 62(S1), S63\u2013S63 (2005). https:\/\/doi.org\/10.1121\/1.2016299","DOI":"10.1121\/1.2016299"},{"key":"14_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.103887","volume":"95","author":"S Jia","year":"2020","unstructured":"Jia, S., Bruce, N.D.: Eml-net: An expandable multi-layer network for saliency prediction. Image Vis. Comput. 95, 103887 (2020)","journal-title":"Image Vis. Comput."},{"key":"14_CR22","doi-asserted-by":"publisher","unstructured":"Jiang, Y., et al.: Eyeformer: predicting personalized scanpaths with transformer-guided reinforcement learning. In: Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology, pp. 1\u201315. UIST \u201924, ACM (2024). https:\/\/doi.org\/10.1145\/3654777.3676436","DOI":"10.1145\/3654777.3676436"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Judd, T., Ehinger, K., Durand, F., Torralba, A.: Learning to predict where humans look. In: IEEE International Conference on Computer Vision (ICCV), pp. 2106\u20132113 (2009)","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Khanuja, H.S., K\u00fcmmerer, M., Bethge, M.: Modeling saliency dataset bias. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.02050"},{"key":"14_CR25","unstructured":"K\u00fcmmerer, M., Bethge, M.: State-of-the-art in human scanpath prediction. arXiv preprint arXiv:2102.12112 (2021)"},{"key":"14_CR26","unstructured":"K\u00fcmmerer, M., Theis, L., Bethge, M.: DeepGaze I: boosting saliency prediction with feature maps trained on ImageNet. In: ICLR (2015)"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"K\u00fcmmerer, M., Wallis, T.S., Bethge, M.: Information-theoretic model comparison unifies saliency metrics. In: Proceedings of the National Academy of Sciences, vol. 112, pp. 16054\u201316059 (2015)","DOI":"10.1073\/pnas.1510393112"},{"key":"14_CR28","unstructured":"K\u00fcmmerer, M., Wallis, T.S., Bethge, M.: DeepGaze III: modeling spatial stimulus context and image processing for gaze prediction in scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6817\u20136826 (2021)"},{"key":"14_CR29","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.visres.2016.01.005","volume":"121","author":"O Le Meur","year":"2016","unstructured":"Le Meur, O., Coutrot, A.: Introducing context-dependent and spatially-variant viewing biases in saccadic models. Vision. Res. 121, 72\u201384 (2016)","journal-title":"Vision. Res."},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Linardos, A., K\u00fcmmerer, M., Press, O., Bethge, M.: DeepGaze IIE: calibrated prediction in and out-of-domain for state-of-the-art saliency modeling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6107\u20136116 (2021)","DOI":"10.1109\/ICCV48922.2021.01268"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Mondal, S., et al.: Gazeformer: scalable, effective and fast prediction of goal-directed human attention. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1441\u20131450. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.00145"},{"key":"14_CR32","unstructured":"Mondal, S., et al.: Gazexplain: learning to predict natural language explanations of visual scanpaths. In: European Conference on Computer Vision (ECCV). Springer (2024)"},{"issue":"7","key":"14_CR33","doi-asserted-by":"publisher","first-page":"1720","DOI":"10.1109\/TPAMI.2018.2845370","volume":"41","author":"A Palazzi","year":"2018","unstructured":"Palazzi, A., Abati, D., Calderara, S., Solera, F., Cucchiara, R.: Predicting the driver\u2019s focus of attention: the DR(eye)VE project. IEEE Trans. Pattern Anal. Mach. Intell. 41(7), 1720\u20131733 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR34","unstructured":"Peng, Z., et al.: Kosmos-2: grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824 (2023)"},{"key":"14_CR35","doi-asserted-by":"publisher","unstructured":"Sch\u00fctt, H.H., Rothkegel, L.O.M., Trukenbrod, H.A., Engbert, R., Wichmann, F.A.: Disentangling bottom-up versus top-down and low-level versus high-level influences on eye movements over time. J. Vis. 19(3), 1 (2019). https:\/\/doi.org\/10.1167\/19.3.1","DOI":"10.1167\/19.3.1"},{"issue":"6\u20137","key":"14_CR36","first-page":"1007","volume":"17","author":"TJ Smith","year":"2009","unstructured":"Smith, T.J., Henderson, J.M.: Facilitation of return during scene viewing. Vis. Cogn. 17(6\u20137), 1007\u20131028 (2009)","journal-title":"Vis. Cogn."},{"issue":"1","key":"14_CR37","first-page":"38","volume":"13","author":"RS Sutton","year":"2019","unstructured":"Sutton, R.S.: The bitter lesson. Incomplete Ideas (Blog) 13(1), 38 (2019)","journal-title":"Incomplete Ideas (Blog)"},{"key":"14_CR38","doi-asserted-by":"publisher","unstructured":"Tatler, B.W.: The central fixation bias in scene viewing: selecting an optimal viewing position independently of motor biases and image feature distributions. J. Vis. 7(14), 4 (2007). https:\/\/doi.org\/10.1167\/7.14.4","DOI":"10.1167\/7.14.4"},{"issue":"3","key":"14_CR39","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1080\/13506280444000409","volume":"12","author":"PJA Unema","year":"2005","unstructured":"Unema, P.J.A., Pannasch, S., Joos, M., Velichkovsky, B.M.: Time course of information processing during scene perception. Vis. Cogn. 12(3), 473\u2013494 (2005)","journal-title":"Vis. Cogn."},{"key":"14_CR40","unstructured":"Velichkovsky, B.M., Joos, M., Helmert, J.R., Pannasch, S.: Two visual systems and their eye movements: evidence from static and dynamic scene perception. In: Proceedings of the XXVII Conference of the Cognitive Science Society, pp. 2283\u20132288. Erlbaum (2005)"},{"key":"14_CR41","unstructured":"Wang, Y., et al.: TPP-Gaze: modelling gaze dynamics in space and time with neural temporal point processes. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2025)"},{"key":"14_CR42","doi-asserted-by":"crossref","unstructured":"Wolfe, J.M.: Guided search 6.0: an updated model of visual search. Psychonomic Bulletin Rev. 28(4), 1060\u20131092 (2021)","DOI":"10.3758\/s13423-020-01859-9"},{"key":"14_CR43","doi-asserted-by":"publisher","unstructured":"Xue, R., et al.: Few-shot personalized scanpath prediction. In: 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13497\u201313507. IEEE (2025). https:\/\/doi.org\/10.1109\/cvpr52734.2025.01260","DOI":"10.1109\/cvpr52734.2025.01260"},{"key":"14_CR44","unstructured":"Yang, Z., et al.: Predicting goal-directed human attention using a human attention transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5039\u20135049 (2022)"},{"issue":"4","key":"14_CR45","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1037\/a0013118","volume":"115","author":"GJ Zelinsky","year":"2008","unstructured":"Zelinsky, G.J.: A theory of eye movements during target acquisition. Psychol. Rev. 115(4), 787\u2013835 (2008)","journal-title":"Psychol. Rev."}],"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\/978-3-032-37271-0_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:00:57Z","timestamp":1789038057000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37271-0_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372703","9783032372710"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37271-0_14","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":"11 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"}}]}}