{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T14:41:19Z","timestamp":1780065679934,"version":"3.54.0"},"reference-count":71,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T00:00:00Z","timestamp":1709856000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62311530101, 62132006, and 61961021"],"award-info":[{"award-number":["62311530101, 62132006, and 61961021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Natural Science Foundation of Jiangxi Province of China","award":["20223AEI91002, 20232BAB202001, 20224BAB212012"],"award-info":[{"award-number":["20223AEI91002, 20232BAB202001, 20224BAB212012"]}]},{"name":"Project funded by China Postdoctoral Science Foundation","award":["2022M721417"],"award-info":[{"award-number":["2022M721417"]}]},{"name":"Postgraduate Innovation Special Fund of Jiangxi Province","award":["YC2022-B155"],"award-info":[{"award-number":["YC2022-B155"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2024,6,30]]},"abstract":"<jats:p>\n            Compared with traditional 2D images, omnidirectional images (also referred to as 360\n            <jats:sup>\u2218<\/jats:sup>\n            images) have more complicated perceptual characteristics due to the particularities of imaging and display. How humans perceive omnidirectional images in an immersive environment and form the immersive quality of experience are important problems. Thus, it is crucial to measure the quality of omnidirectional images under different viewing conditions, which suffer from realistic distortions. In this article, we build a large-scale subjective assessment database for omnidirectional images and carry out a comprehensive psychophysical experiment to study the relationships between different factors (viewing conditions and viewing behaviors) and the perceptual quality of omnidirectional images. In addition, we collect both subjective ratings and head movement data. A thorough analysis of the collected subjective data is also provided, where we make several interesting findings. Moreover, with the proposed database, we propose a novel transformer-based omnidirectional image quality assessment model. To be consistent with the human viewing process, viewing conditions and behaviors are naturally incorporated into the proposed model. Specifically, the proposed model mainly consists of three parts: viewport sequence generation, multi-scale feature extraction, and perceptual quality prediction. Extensive experimental results conducted on the proposed database demonstrate the effectiveness of the proposed method over existing image quality assessment methods.\n          <\/jats:p>","DOI":"10.1145\/3640344","type":"journal-article","created":{"date-parts":[[2024,1,26]],"date-time":"2024-01-26T10:03:30Z","timestamp":1706263410000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["Perceptual Quality Assessment of Omnidirectional Images: A Benchmark and Computational Model"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5380-8343","authenticated-orcid":false,"given":"Xuelin","family":"Liu","sequence":"first","affiliation":[{"name":"Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0337-6877","authenticated-orcid":false,"given":"Jiebin","family":"Yan","sequence":"additional","affiliation":[{"name":"Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3999-3478","authenticated-orcid":false,"given":"Liping","family":"Huang","sequence":"additional","affiliation":[{"name":"Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6946-3586","authenticated-orcid":false,"given":"Yuming","family":"Fang","sequence":"additional","affiliation":[{"name":"Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5003-4741","authenticated-orcid":false,"given":"Zheng","family":"Wan","sequence":"additional","affiliation":[{"name":"Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9982-9887","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"SANY Heavy Industry Co., Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,3,8]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"RECOMMENDATION ITU-R BT. 2002. Methodology for the subjective assessment of the quality of television pictures. Retrieved June 17 2021 from http:\/\/www.itu.int"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2956408"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486584"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.5594\/M001758"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"5","key":"e_1_3_2_8_2","first-page":"2567","article-title":"Image quality assessment: Unifying structure and texture similarity","volume":"44","author":"Ding Keyan","year":"2022","unstructured":"Keyan Ding, Kede Ma, Shiqi Wang, and Eero P. Simoncelli. 2022. Image quality assessment: Unifying structure and texture similarity. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 5 (2022), 2567\u20132581.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_9_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Dosovitskiy Alexey","year":"2021","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. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2018.8351786"},{"key":"e_1_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Henry Been-Lirn Duh Donald E Parker James O. Philips and Thomas A. Furness. 2004. Conflicting motion cues to the visual and vestibular self-motion systems around 0.6 Hz evoke simulator sickness. Human Factors 46 1 (2004) 142\u2013153.","DOI":"10.1518\/hfes.46.1.142.30384"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19937"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3272480"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3035679"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2781307"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2916766"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2012.6263851"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00404"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1117\/12.477378"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2865089"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3052073"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2898732"},{"key":"e_1_3_2_24_2","unstructured":"Diederik P. Kingma and Jimmy Ba. 2017. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2017)."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2016.7498936"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413804"},{"key":"e_1_3_2_28_2","article-title":"Toward a no-reference omnidirectional image quality evaluation by using multi-perceptual features","author":"Liu Yun","year":"2023","unstructured":"Yun Liu, Xiaohua Yin, Zuliang Wan, Guanghui Yue, and Zhi Zheng. 2023. Toward a no-reference omnidirectional image quality evaluation by using multi-perceptual features. ACM Transactions On Multimedia Computing, Communications, And Applications 19, 2 (2023), 1\u201319.","journal-title":"ACM Transactions On Multimedia Computing, Communications, And Applications"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"e_1_3_2_31_2","unstructured":"RECOMMENDATION ITU-T P. 1999. Subjective video quality assessment methods for multimedia applications. Retrieved June 17 2021 from http:\/\/www.itu.int"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2219551"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3381846"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506192"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859378"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2793599"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"e_1_3_2_38_2","first-page":"6989","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","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. 6989\u20136999."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3050888"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296923"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2955024"},{"issue":"9","key":"e_1_3_2_42_2","first-page":"1408","article-title":"Weighted-to-spherically-uniform quality evaluation for omnidirectional video","volume":"24","author":"Sun Yule","year":"2017","unstructured":"Yule Sun, Ang Lu, and Lu Yu. 2017. Weighted-to-spherically-uniform quality evaluation for omnidirectional video. IEEE Signal Processing Letters 24, 9 (2017), 1408\u20131412.","journal-title":"IEEE Signal Processing Letters"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/PCS.2016.7906378"},{"key":"e_1_3_2_44_2","unstructured":"VQEG. 2000. Final report from the video quality experts group on the validation of objective models of video quality assessment. Retrieved June 17 2021 from http:\/\/www.vqeg.org"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.5594\/M001774"},{"key":"e_1_3_2_47_2","unstructured":"Tianhe Wu Shuwei Shi Haoming Cai Mingdeng Cao Jing Xiao Yinqiang Zheng and Yujiu Yang. 2023. Assessor360: Multi-sequence network for blind omnidirectional image quality assessment. arXiv preprint arXiv: 2305.10983 (2023)."},{"key":"e_1_3_2_48_2","first-page":"2695","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Xiao Jianxiong","year":"2012","unstructured":"Jianxiong Xiao, Krista A. Ehinger, Aude Oliva, and Antonio Torralba. 2012. Recognizing scene viewpoint using panoramic place representation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2695\u20132702."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00776-8_54"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/PCS48520.2019.8954555"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3015186"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2966864"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3003218"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102888"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3177127"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01450-2"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3444685.3446318"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547748"},{"key":"e_1_3_2_60_2","unstructured":"Yan Ye Elena Alshina and Jill Boyce. 2017. JVET-G1003: Algorithm description of projection format conversion and video quality metrics in 360lib version 4. Retrieved June 17 2021 from http:\/\/phenix.it-sudparis.eu\/jvet"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2015.12"},{"key":"e_1_3_2_62_2","first-page":"99700C","volume-title":"Proceedings of the Optics and Photonics for Information Processing X","author":"Zakharchenko Vladyslav","year":"2016","unstructured":"Vladyslav Zakharchenko, Kwang Pyo Choi, and Jeong Hoon Park. 2016. Quality metric for spherical panoramic video. In Proceedings of the Optics and Photonics for Information Processing X. 99700C."},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2346028"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2015.2426416"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2011.2109730"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2972158"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3081182"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3081162"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP.2018.8652269"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01415"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640344","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:27Z","timestamp":1750287027000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640344"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,8]]},"references-count":71,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,6,30]]}},"alternative-id":["10.1145\/3640344"],"URL":"https:\/\/doi.org\/10.1145\/3640344","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,8]]},"assertion":[{"value":"2023-08-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}