{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:23:20Z","timestamp":1777656200740,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T00:00:00Z","timestamp":1697155200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,13]]},"DOI":"10.1145\/3607822.3616408","type":"proceedings-article","created":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T10:37:16Z","timestamp":1697193436000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Simulating Human Visual System Based on Vision Transformer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6766-3824","authenticated-orcid":false,"given":"Mengyu","family":"Qiu","sequence":"first","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7037-5479","authenticated-orcid":false,"given":"Yi","family":"Guo","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2510-2690","authenticated-orcid":false,"given":"Mingguang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5500-9465","authenticated-orcid":false,"given":"Jingwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5434-2573","authenticated-orcid":false,"given":"Tian","family":"Lan","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9725-1945","authenticated-orcid":false,"given":"Zhilin","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Kevin McGuinness, and Noel\u00a0E. O\u2019Connor.","author":"Assens Marc","year":"2018","unstructured":"Marc Assens, Xavier Giro-i Nieto, Kevin McGuinness, and Noel\u00a0E. O\u2019Connor. 2018. PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks. In ECCVW."},{"key":"e_1_3_2_1_2_1","volume-title":"Kevin McGuinness, and Noel\u00a0E O\u2019Connor.","author":"Assens\u00a0Reina Marc","year":"2017","unstructured":"Marc Assens\u00a0Reina, Xavier Giro-i Nieto, Kevin McGuinness, and Noel\u00a0E O\u2019Connor. 2017. Saltinet: Scan-path prediction on 360 degree images using saliency volumes. In ICCV. 2331\u20132338."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Ali Borji Hamed\u00a0R Tavakoli Dicky\u00a0N Sihite and Laurent Itti. 2013. Analysis of scores datasets and models in visual saliency prediction. In ICCV. 921\u2013928.","DOI":"10.1109\/ICCV.2013.118"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Xianyu Chen Ming Jiang and Qi Zhao. 2021. Predicting human scanpaths in visual question answering. In CVPR. 10876\u201310885.","DOI":"10.1109\/CVPR46437.2021.01073"},{"key":"e_1_3_2_1_5_1","volume-title":"ScanMatch: A novel method for comparing fixation sequences. Behavior research methods 42, 3","author":"Cristino Filipe","year":"2010","unstructured":"Filipe Cristino, Sebastiaan Math\u00f4t, Jan Theeuwes, and Iain\u00a0D Gilchrist. 2010. ScanMatch: A novel method for comparing fixation sequences. Behavior research methods 42, 3 (2010), 692\u2013700."},{"key":"e_1_3_2_1_6_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, 4","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, 4 (2012), 1079\u20131100."},{"key":"e_1_3_2_1_7_1","volume-title":"Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850","author":"Graves Alex","year":"2013","unstructured":"Alex Graves. 2013. Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 (2013)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01843"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"e_1_3_2_1_10_1","volume-title":"SALICON: Saliency in Context. In CVPR.","author":"Jiang Ming","year":"2015","unstructured":"Ming Jiang, Shengsheng Huang, Juanyong Duan, and Qi Zhao. 2015. SALICON: Saliency in Context. In CVPR."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3161969"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2014.12.026"},{"key":"e_1_3_2_1_13_1","first-page":"1","article-title":"Anchor retouching via model interaction for robust object detection in aerial images","volume":"60","author":"Liang Dong","year":"2021","unstructured":"Dong Liang, Qixiang Geng, Zongqi Wei, Dmitry\u00a0A Vorontsov, Ekaterina\u00a0L Kim, Mingqiang Wei, and Huiyu Zhou. 2021. Anchor retouching via model interaction for robust object detection in aerial images. IEEE Transactions on Geoscience and Remote Sensing 60 (2021), 1\u201313.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.10.020"},{"key":"e_1_3_2_1_15_1","volume-title":"MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detection","author":"Liang Dong","year":"2023","unstructured":"Dong Liang, Jing-Wei Zhang, Ying-Peng Tang, and Sheng-Jun Huang. 2023. MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detection. IEEE Transactions on Geoscience and Remote Sensing (2023)."},{"key":"e_1_3_2_1_16_1","unstructured":"Niki Parmar Ashish Vaswani Jakob Uszkoreit Lukasz Kaiser Noam Shazeer Alexander Ku and Dustin Tran. 2018. Image transformer. In ICML. PMLR 4055\u20134064."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956930"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Xiaoshuai Sun Hongxun Yao and Rongrong Ji. 2012. What are we looking for: Towards statistical modeling of saccadic eye movements and visual saliency. In CVPR. 1552\u20131559.","DOI":"10.1109\/CVPR.2012.6247846"},{"key":"e_1_3_2_1_19_1","volume-title":"Attention is all you need. NIPS 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. NIPS 30 (2017)."},{"key":"e_1_3_2_1_20_1","volume-title":"Simulating human saccadic scanpaths on natural images","author":"Wang Wei","unstructured":"Wei Wang, Cheng Chen, Yizhou Wang, Tingting Jiang, Fang Fang, and Yuan Yao. 2011. Simulating human saccadic scanpaths on natural images. In CVPR. IEEE, 441\u2013448."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3158903"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568396"},{"key":"e_1_3_2_1_23_1","volume-title":"Balanced Mixup Loss for Long-Tailed Visual Recognition. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1\u20135.","author":"Ye Haibo","year":"2023","unstructured":"Haibo Ye, Fangyu Zhou, Xinjie Li, and Qingheng Zhang. 2023. Balanced Mixup Loss for Long-Tailed Visual Recognition. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1\u20135."}],"event":{"name":"SUI '23: ACM Symposium on Spatial User Interaction","location":"Sydney NSW Australia","acronym":"SUI '23","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2023 ACM Symposium on Spatial User Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3607822.3616408","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3607822.3616408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:21Z","timestamp":1750178841000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3607822.3616408"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,13]]},"references-count":23,"alternative-id":["10.1145\/3607822.3616408","10.1145\/3607822"],"URL":"https:\/\/doi.org\/10.1145\/3607822.3616408","relation":{},"subject":[],"published":{"date-parts":[[2023,10,13]]},"assertion":[{"value":"2023-10-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}