{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:46:46Z","timestamp":1777657606956,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":74,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972162"],"award-info":[{"award-number":["61972162"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Natural Science Funds for Distinguished Young Scholars","award":["2023B1515020097"],"award-info":[{"award-number":["2023B1515020097"]}]},{"name":"Singapore Ministry of Education Academic Research Fund Tier 1","award":["MSS23C002"],"award-info":[{"award-number":["MSS23C002"]}]},{"name":"Key R\\&D Project of Guangzhou Science and Technology Plan","award":["2023B01J0002"],"award-info":[{"award-number":["2023B01J0002"]}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515012894"],"award-info":[{"award-number":["2023A1515012894"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611839","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"2294-2304","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["NPF-200: A Multi-Modal Eye Fixation Dataset and Method for Non-Photorealistic Videos"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1077-5944","authenticated-orcid":false,"given":"Ziyu","family":"Yang","sequence":"first","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4730-8435","authenticated-orcid":false,"given":"Sucheng","family":"Ren","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4568-0560","authenticated-orcid":false,"given":"Zongwei","family":"Wu","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4007-2776","authenticated-orcid":false,"given":"Nanxuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9096-2670","authenticated-orcid":false,"given":"Junle","family":"Wang","sequence":"additional","affiliation":[{"name":"Tecent, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7059-0929","authenticated-orcid":false,"given":"Jing","family":"Qin","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-4644","authenticated-orcid":false,"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8535.2007.00721.x"},{"key":"e_1_3_2_1_2_1","first-page":"29","article-title":"Learning sound representations from unlabeled video","author":"Aytar Yusuf","year":"2016","unstructured":"Yusuf Aytar, Carl Vondrick, and Antonio Torralba. Soundnet: Learning sound representations from unlabeled video. NeurIPS, 29, 2016.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777665"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01519-y"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"e_1_3_2_1_6_1","volume-title":"Cat2000: A large scale fixation dataset for boosting saliency research. arXiv preprint arXiv:1505.03581","author":"Borji Ali","year":"2015","unstructured":"Ali Borji and Laurent Itti. Cat2000: A large scale fixation dataset for boosting saliency research. arXiv preprint arXiv:1505.03581, 2015."},{"key":"e_1_3_2_1_7_1","first-page":"18","article-title":"Saliency based on information maximization","author":"Bruce Neil","year":"2005","unstructured":"Neil Bruce and John Tsotsos. Saliency based on information maximization. NeurIPS, 18, 2005.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_8_1","volume-title":"Integrated model of visual processing. Brain research reviews, 36(2-3):96--107","author":"Bullier Jean","year":"2001","unstructured":"Jean Bullier. Integrated model of visual processing. Brain research reviews, 36(2-3):96--107, 2001."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2815601"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1080\/13825570802151439"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_12_1","volume-title":"Temporal-spatial feature pyramid for video saliency detection. arXiv preprint arXiv:2105.04213","author":"Chang Qinyao","year":"2021","unstructured":"Qinyao Chang and Shiping Zhu. Temporal-spatial feature pyramid for video saliency detection. arXiv preprint arXiv:2105.04213, 2021."},{"key":"e_1_3_2_1_13_1","article-title":"A comprehensive survey on video saliency detection with auditory information: the audio-visual consistency perceptual is the key!","author":"Chen Chenglizhao","year":"2022","unstructured":"Chenglizhao Chen, Mengke Song, Wenfeng Song, Li Guo, and Muwei Jian. A comprehensive survey on video saliency detection with auditory information: the audio-visual consistency perceptual is the key! IEEE Transactions on Circuits and Systems for Video Technology, 2022.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1167\/14.8.5"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362640"},{"key":"e_1_3_2_1_16_1","first-page":"46","volume-title":"The development of eye tracking in empirical research on subtitling and captioning. Seeing into screens: Eye tracking and the moving image","author":"Doherty Stephen","year":"2018","unstructured":"Stephen Doherty, Jan-Louis Kruger, T Dwyer, C Perkins, S Redmond, and J Sita. The development of eye tracking in empirical research on subtitling and captioning. Seeing into screens: Eye tracking and the moving image, pages 46--64, 2018."},{"key":"e_1_3_2_1_17_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv: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, et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_25"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_25"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/1690059.1690190"},{"key":"e_1_3_2_1_21_1","volume-title":"Deliberative versus implemental mindsets in the control of action","author":"Gollwitzer Peter M","year":"1999","unstructured":"Peter M Gollwitzer and Ute C Bayer. Deliberative versus implemental mindsets in the control of action, 1999."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"issue":"2","key":"e_1_3_2_1_23_1","first-page":"898","article-title":"Eye-tracking database for a set of standard video sequences","volume":"21","author":"Hadizadeh Hadi","year":"2011","unstructured":"Hadi Hadizadeh, Mario J Enriquez, and Ivan V Bajic. Eye-tracking database for a set of standard video sequences. IEEE TIP, 21(2):898--903, 2011.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_24_1","first-page":"19","article-title":"Graph-based visual saliency","author":"Harel Jonathan","year":"2006","unstructured":"Jonathan Harel, Christof Koch, and Pietro Perona. Graph-based visual saliency. NeurIPS, 19, 2006.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933439"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.120"},{"key":"e_1_3_2_1_27_1","first-page":"110","volume-title":"Proceedings, Part III 13","author":"He Shengfeng","year":"2014","unstructured":"Shengfeng He and Rynson WH Lau. Saliency detection with flash and no-flash image pairs. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part III 13, pages 110--124. Springer, 2014."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.617"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635989"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"e_1_3_2_1_32_1","volume-title":"Video game design using an eye-movement-dependent model of visual attention. ACM Transactions on Multimedia Computing, Communications, and Applications, 4(3):1--16","author":"Jie Li","year":"2008","unstructured":"Li Jie and James J Clark. Video game design using an eye-movement-dependent model of visual attention. ACM Transactions on Multimedia Computing, Communications, and Applications, 4(3):1--16, 2008."},{"key":"e_1_3_2_1_33_1","volume-title":"The kinetics human action video dataset. arXiv preprint arXiv:1705.06950","author":"Kay Will","year":"2017","unstructured":"Will Kay, Joao Carreira, Karen Simonyan, Brian Zhang, Chloe Hillier, Sudheendra Vijayanarasimhan, Fabio Viola, Tim Green, Trevor Back, Paul Natsev, et al. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950, 2017."},{"key":"e_1_3_2_1_34_1","volume-title":"A preliminary investigation into eye gaze data in a first person shooter game","author":"Kenny Alan","year":"2005","unstructured":"Alan Kenny, Hendrik Koesling, Declan Delaney, Seamus McLoone, and Tomas E Ward. A preliminary investigation into eye gaze data in a first person shooter game. 2005."},{"key":"e_1_3_2_1_35_1","volume-title":"ICLR","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In ICLR, 2015."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2015.08.004"},{"key":"e_1_3_2_1_37_1","volume-title":"CVPRW","author":"Koutras Petros","year":"2019","unstructured":"Petros Koutras and Petros Maragos. Susinet: See, understand and summarize it. In CVPRW, 2019."},{"key":"e_1_3_2_1_38_1","first-page":"1113","article-title":"Video saliency prediction using spatiotemporal residual attentive networks","volume":"29","author":"Lai Qiuxia","year":"2019","unstructured":"Qiuxia Lai, Wenguan Wang, Hanqiu Sun, and Jianbing Shen. Video saliency prediction using spatiotemporal residual attentive networks. IEEE TIP, 29:1113--1126, 2019.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.86"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3172971"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1167\/14.10.100"},{"key":"e_1_3_2_1_43_1","first-page":"2394","volume-title":"ICCV","author":"Min Kyle","year":"2019","unstructured":"Kyle Min and Jason J Corso. Tased-net: Temporally-aggregating spatial encoderdecoder network for video saliency detection. In ICCV, pages 2394--2403, 2019."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1109\/QoMEX.2014.6982312","volume-title":"2014 Sixth International Workshop on Quality of Multimedia Experience (QoMEX)","author":"Min Xiongkuo","year":"2014","unstructured":"Xiongkuo Min, Guangtao Zhai, Zhongpai Gao, Chunjia Hu, and Xiaokang Yang. Sound influences visual attention discriminately in videos. In 2014 Sixth International Workshop on Quality of Multimedia Experience (QoMEX), pages 153--158, 2014."},{"key":"e_1_3_2_1_45_1","volume-title":"Fixation prediction through multimodal analysis. ACM Transactions on Multimedia Computing, Communications, and Applications, 13(1):1--23","author":"Min Xiongkuo","year":"2016","unstructured":"Xiongkuo Min, Guangtao Zhai, Ke Gu, and Xiaokang Yang. Fixation prediction through multimodal analysis. ACM Transactions on Multimedia Computing, Communications, and Applications, 13(1):1--23, 2016."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2966082"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-010-9074-z"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502128"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028170"},{"key":"e_1_3_2_1_50_1","volume-title":"How do vision transformers work? arXiv preprint arXiv:2202.06709","author":"Park Namuk","year":"2022","unstructured":"Namuk Park and Songkuk Kim. How do vision transformers work? arXiv preprint arXiv:2202.06709, 2022."},{"key":"e_1_3_2_1_51_1","first-page":"32","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. Pytorch: An imperative style, high-performance deep learning library. NeurIPS, 32, 2019.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.3758\/BF03211521"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_13"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"e_1_3_2_1_55_1","first-page":"1","volume-title":"Symposium on Eye Tracking Research and Applications","author":"Saaty Morva","year":"2022","unstructured":"Morva Saaty and Mahmoud Reza Hashemi. Game audio impacts on players' visual attention, model performance for cloud gaming. In Symposium on Eye Tracking Research and Applications, pages 1--7, 2022."},{"key":"e_1_3_2_1_56_1","volume-title":"Visually directing user's attention in interactive 3d environments","author":"El-Nasr Magy Seif","year":"2004","unstructured":"Magy Seif El-Nasr and Chinmay Rao. Visually directing user's attention in interactive 3d environments. 2004."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.16910\/jemr.6.4.1"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.103"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/1394281.1394288"},{"key":"e_1_3_2_1_60_1","volume-title":"Dave: A deep audiovisual embedding for dynamic saliency prediction. arXiv preprint arXiv:1905.10693","author":"Tavakoli Hamed R","year":"2019","unstructured":"Hamed R Tavakoli, Ali Borji, Esa Rahtu, and Juho Kannala. Dave: A deep audiovisual embedding for dynamic saliency prediction. arXiv preprint arXiv:1905.10693, 2019."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2019.05.001"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00482"},{"key":"e_1_3_2_1_63_1","first-page":"30","article-title":"Attention is all you need","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. Attention is all you need. NeurIPS, 30, 2017.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_64_1","volume-title":"Sound enhances visual perception: crossmodal effects of auditory organization on vision. Journal of experimental psychology: Human perception and performance, 26(5):1583","author":"Vroomen Jean","year":"2000","unstructured":"Jean Vroomen and Beatrice de Gelder. Sound enhances visual perception: crossmodal effects of auditory organization on vision. Journal of experimental psychology: Human perception and performance, 26(5):1583, 2000."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3023591"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01487"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00514"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2924417"},{"key":"e_1_3_2_1_69_1","article-title":"Spatio-temporal self-attention network for video saliency prediction","author":"Wang Ziqiang","year":"2021","unstructured":"Ziqiang Wang, Zhi Liu, Gongyang Li, YangWang, Tianhong Zhang, Lihua Xu, and JijunWang. Spatio-temporal self-attention network for video saliency prediction. IEEE Transactions on Multimedia, 2021.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6927"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"issue":"12","key":"e_1_3_2_1_72_1","first-page":"3544","article-title":"Video saliency prediction based on spatial temporal two-stream network","volume":"29","author":"Zhang Kao","year":"2018","unstructured":"Kao Zhang and Zhenzhong Chen. Video saliency prediction based on spatial temporal two-stream network. IEEE TCSVT, 29(12):3544--3557, 2018.","journal-title":"IEEE TCSVT"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1167\/8.7.32"},{"key":"e_1_3_2_1_74_1","first-page":"6811","volume-title":"Proceedings of the AAAI conference on artificial intelligence","volume":"34","author":"Zhang Ruohan","year":"2020","unstructured":"Ruohan Zhang, Calen Walshe, Zhuode Liu, Lin Guan, Karl Muller, Jake Whritner, Luxin Zhang, Mary Hayhoe, and Dana Ballard. Atari-head: Atari human eyetracking and demonstration dataset. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 6811--6820, 2020."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611839","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611839","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:57:41Z","timestamp":1755820661000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611839"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":74,"alternative-id":["10.1145\/3581783.3611839","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611839","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}