{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:03:41Z","timestamp":1776107021955,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T00:00:00Z","timestamp":1728604800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the Horizon 2020 FET program of the European Union","award":["CHIST-ERA-20-BCI-001"],"award-info":[{"award-number":["CHIST-ERA-20-BCI-001"]}]},{"name":"the Academy of Finland BAD","award":["318559"],"award-info":[{"award-number":["318559"]}]},{"name":"the Academy of Finland through the projects Human Automata","award":["328813"],"award-info":[{"award-number":["328813"]}]},{"name":"the European Innovation Council Pathfinder program SYMBIOTIK project","award":["101071147"],"award-info":[{"award-number":["101071147"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,13]]},"DOI":"10.1145\/3654777.3676436","type":"proceedings-article","created":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T10:50:36Z","timestamp":1728643836000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["EyeFormer: Predicting Personalized Scanpaths with Transformer-Guided Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0022-6512","authenticated-orcid":false,"given":"Yue","family":"Jiang","sequence":"first","affiliation":[{"name":"Aalto University, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7088-2331","authenticated-orcid":false,"given":"Zixin","family":"Guo","sequence":"additional","affiliation":[{"name":"Aalto University, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9466-9148","authenticated-orcid":false,"given":"Hamed","family":"Rezazadegan Tavakoli","sequence":"additional","affiliation":[{"name":"Nokia Technologies, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5011-1847","authenticated-orcid":false,"given":"Luis A.","family":"Leiva","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Luxembourg"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2498-7837","authenticated-orcid":false,"given":"Antti","family":"Oulasvirta","sequence":"additional","affiliation":[{"name":"Aalto University, Finland"}]}],"member":"320","published-online":{"date-parts":[[2024,10,11]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"A comparison of scanpath comparison methods. Behavior research methods 47, 4","author":"Anderson C","year":"2015","unstructured":"Nicola\u00a0C Anderson, Fraser Anderson, Alan Kingstone, and Walter\u00a0F Bischof. 2015. A comparison of scanpath comparison methods. Behavior research methods 47, 4 (2015), 1377\u20131392."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.275"},{"key":"e_1_3_2_2_3_1","volume-title":"PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks. ECCV Workshop on Egocentric Perception, Interaction and Computing (EPIC).","author":"Assens Marc","year":"2018","unstructured":"Marc Assens, Xavier\u00a0Giro i Nieto, Kevin McGuinness, and Noel\u00a0E. O\u2019Connor. 2018. PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks. ECCV Workshop on Egocentric Perception, Interaction and Computing (EPIC)."},{"key":"e_1_3_2_2_4_1","volume-title":"KDD workshop, Vol.\u00a010","author":"Berndt J","year":"1994","unstructured":"Donald\u00a0J Berndt and James Clifford. 1994. Using dynamic time warping to find patterns in time series.. In KDD workshop, Vol.\u00a010. Seattle, WA, USA:, 359\u2013370."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15822-3_23"},{"key":"e_1_3_2_2_6_1","volume-title":"When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations. CoRR abs\/2106.01548","author":"Chen Xiangning","year":"2021","unstructured":"Xiangning Chen, Cho-Jui Hsieh, and Boqing Gong. 2021. When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations. CoRR abs\/2106.01548 (2021). arXiv:2106.01548https:\/\/arxiv.org\/abs\/2106.01548"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01073"},{"key":"e_1_3_2_2_8_1","volume-title":"Scanpath Prediction for Visual Attention Using IOR-ROI LSTM(IJCAI\u201918)","author":"Chen Zhenzhong","unstructured":"Zhenzhong Chen and Wanjie Sun. 2018. Scanpath Prediction for Visual Attention Using IOR-ROI LSTM(IJCAI\u201918). AAAI Press, 642\u2013648."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376553"},{"key":"e_1_3_2_2_10_1","volume-title":"ScanpathNet: A Recurrent Mixture Density Network for Scanpath Prediction. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 5006\u20135016","author":"Jalova de Belen Ryan","year":"2022","unstructured":"Ryan Anthony\u00a0Jalova de Belen, Tomasz Bednarz, and Arcot Sowmya. 2022. ScanpathNet: A Recurrent Mixture Density Network for Scanpath Prediction. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 5006\u20135016."},{"key":"e_1_3_2_2_11_1","volume-title":"It depends on how you look at it: Scanpath comparison in multiple dimensions with MultiMatch, a vector-based approach. Behavior research methods 44","author":"Dewhurst Richard","year":"2012","unstructured":"Richard Dewhurst, Marcus Nystr\u00f6m, Halszka Jarodzka, Tom Foulsham, Roger Johansson, and Kenneth Holmqvist. 2012. It depends on how you look at it: Scanpath comparison in multiple dimensions with MultiMatch, a vector-based approach. Behavior research methods 44 (2012), 1079\u20131100."},{"key":"e_1_3_2_2_12_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR abs\/2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR abs\/2010.11929 (2020). arXiv:2010.11929https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3655602"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3655602"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-020-01441-0"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415825"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.aacl-short.5"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592038"},{"key":"e_1_3_2_2_19_1","volume-title":"Computational Assistance for User Interface Design: Smarter Generation and Evaluation of Design Ideas. In Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems. 1\u20135.","author":"Hegemann Lena","year":"2023","unstructured":"Lena Hegemann, Yue Jiang, Joon\u00a0Gi Shin, Yi-Chi Liao, Markku Laine, and Antti Oulasvirta. 2023. Computational Assistance for User Interface Design: Smarter Generation and Evaluation of Design Ideas. In Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems. 1\u20135."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"e_1_3_2_2_22_1","volume-title":"Computational Representations for Graphical User Interfaces. In Extended Abstracts of the 2024 CHI Conference on Human Factors in Computing Systems(CHI EA \u201924)","author":"Jiang Yue","year":"2024","unstructured":"Yue Jiang. 2024. Computational Representations for Graphical User Interfaces. In Extended Abstracts of the 2024 CHI Conference on Human Factors in Computing Systems(CHI EA \u201924)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300643"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581096"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581096"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3636316"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3573805"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3504030"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445043"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376610"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642822"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0161-6420(01)00769-2"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1167\/jov.22.5.7"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2014.12.026"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379503.3403557"},{"key":"e_1_3_2_2_36_1","volume-title":"Transformer-based convolutional forgetting knowledge tracking. Scientific Reports","author":"Liu Tieyuan","year":"2023","unstructured":"Tieyuan Liu, Meng Zhang, Chuangying Zhu, and Liang Chang. 2023. Transformer-based convolutional forgetting knowledge tracking. Scientific Reports (2023)."},{"key":"e_1_3_2_2_37_1","volume-title":"A probabilistic time-evolving approach to scanpath prediction. arXiv preprint arXiv:2204.09404","author":"Martin Daniel","year":"2022","unstructured":"Daniel Martin, Diego Gutierrez, and Belen Masia. 2022. A probabilistic time-evolving approach to scanpath prediction. arXiv preprint arXiv:2204.09404 (2022)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3150502"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.16910\/jemr.5.1.4"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/375735.376414"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00145"},{"key":"e_1_3_2_2_42_1","unstructured":"Sajad Mousavi Michael Schukat Enda Howley Ali Borji and Nasser Mozayani. 2017. Learning to predict where to look in interactive environments using deep recurrent q-learning. arxiv:1612.05753\u00a0[cs.CV]"},{"key":"e_1_3_2_2_43_1","volume-title":"The Challenge of Anticipation: A Unifying Framework for the Analysis and Design of Artificial Cognitive Systems","author":"Ognibene Dimitri","unstructured":"Dimitri Ognibene, Christian Balkenius, and Gianluca Baldassarre. 2008. A reinforcement-learning model of top-down attention based on a potential-action map. In The Challenge of Anticipation: A Unifying Framework for the Analysis and Design of Artificial Cognitive Systems. Springer, 161\u2013184."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982422"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR59233.2023.00037"},{"key":"e_1_3_2_2_46_1","volume-title":"Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732","author":"Ranzato Marc\u2019Aurelio","year":"2015","unstructured":"Marc\u2019Aurelio Ranzato, Sumit Chopra, Michael Auli, and Wojciech Zaremba. 2015. Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732 (2015)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2013.06.006"},{"key":"e_1_3_2_2_49_1","article-title":"Do Predictions of Visual Perception Aid Design?ACM","volume":"8","author":"Rosenholtz Ruth","year":"2011","unstructured":"Ruth Rosenholtz, Amal Dorai, and Rosalind Freeman. 2011. Do Predictions of Visual Perception Aid Design?ACM Trans. Appl. Percept. 8, 2 (2011).","journal-title":"Trans. Appl. Percept."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.5555\/1367985.1367993"},{"key":"e_1_3_2_2_51_1","volume-title":"Behind the Machine\u2019s Gaze: Neural Networks with Biologically-inspired Constraints Exhibit Human-like Visual Attention. arXiv preprint arXiv:2204.09093","author":"Schwinn Leo","year":"2022","unstructured":"Leo Schwinn, Doina Precup, Bj\u00f6rn Eskofier, and Dario Zanca. 2022. Behind the Machine\u2019s Gaze: Neural Networks with Biologically-inspired Constraints Exhibit Human-like Visual Attention. arXiv preprint arXiv:2204.09093 (2022)."},{"key":"e_1_3_2_2_52_1","volume-title":"Proc. MDDAUI Workshop.","author":"D.","unstructured":"Jeremiah\u00a0D. Still and Christopher\u00a0M. Masciocchi. 2010. A Saliency Model Predicts Fixations in Web Interfaces. In Proc. MDDAUI Workshop."},{"key":"e_1_3_2_2_53_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 6989\u20136999","author":"Sui Xiangjie","year":"2023","unstructured":"Xiangjie Sui, Yuming Fang, Hanwei Zhu, Shiqi Wang, and Zhou Wang. 2023. ScanDMM: A Deep Markov Model of Scanpath Prediction for 360deg Images. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 6989\u20136999."},{"key":"e_1_3_2_2_54_1","volume-title":"Visual scanpath prediction using IOR-ROI recurrent mixture density network","author":"Sun Wanjie","year":"2019","unstructured":"Wanjie Sun, Zhenzhong Chen, and Feng Wu. 2019. Visual scanpath prediction using IOR-ROI recurrent mixture density network. IEEE transactions on pattern analysis and machine intelligence 43, 6 (2019), 2101\u20132118."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247846"},{"key":"e_1_3_2_2_56_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton S","unstructured":"Richard\u00a0S Sutton and Andrew\u00a0G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6059"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300687"},{"key":"e_1_3_2_2_59_1","first-page":"3","article-title":"Embedology","volume":"65","author":"Tim Sauer","year":"1991","unstructured":"Sauer Tim, A\u00a0Yorke James, and Casdagli Martin. 1991. Embedology. Journal of statistical Physics 65, 3-4 (1991), 579\u2013616.","journal-title":"Journal of statistical Physics"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241381"},{"key":"e_1_3_2_2_61_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902643"},{"key":"e_1_3_2_2_63_1","volume-title":"Language Models with Transformers. CoRR abs\/1904.09408","author":"Wang Chenguang","year":"2019","unstructured":"Chenguang Wang, Mu Li, and Alexander\u00a0J. Smola. 2019. Language Models with Transformers. CoRR abs\/1904.09408 (2019). arXiv:1904.09408http:\/\/arxiv.org\/abs\/1904.09408"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995423"},{"key":"e_1_3_2_2_65_1","volume-title":"Scanpath prediction on information visualisations","author":"Wang Yao","year":"2023","unstructured":"Yao Wang, Andreas Bulling, 2023. Scanpath prediction on information visualisations. IEEE Transactions on Visualization and Computer Graphics (2023)."},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3655613"},{"key":"e_1_3_2_2_67_1","volume-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning. Reinforcement learning","author":"Williams J","year":"1992","unstructured":"Ronald\u00a0J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Reinforcement learning (1992), 5\u201332."},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00336"},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2897966"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1167\/14.1.28"},{"key":"e_1_3_2_2_71_1","volume-title":"Predicting head movement in panoramic video: A deep reinforcement learning approach","author":"Xu Mai","year":"2018","unstructured":"Mai Xu, Yuhang Song, Jianyi Wang, MingLang Qiao, Liangyu Huo, and Zulin Wang. 2018. Predicting head movement in panoramic video: A deep reinforcement learning approach. IEEE transactions on pattern analysis and machine intelligence 41, 11 (2018), 2693\u20132708."},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00027"}],"event":{"name":"UIST '24: The 37th Annual ACM Symposium on User Interface Software and Technology","location":"Pittsburgh PA USA","acronym":"UIST '24"},"container-title":["Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654777.3676436","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3654777.3676436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T21:14:31Z","timestamp":1754342071000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654777.3676436"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,11]]},"references-count":72,"alternative-id":["10.1145\/3654777.3676436","10.1145\/3654777"],"URL":"https:\/\/doi.org\/10.1145\/3654777.3676436","relation":{},"subject":[],"published":{"date-parts":[[2024,10,11]]},"assertion":[{"value":"2024-10-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}