{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T08:29:37Z","timestamp":1765268977805,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3689093.3689183","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T18:09:19Z","timestamp":1729447759000},"page":"39-47","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Visual-Saliency Guided Multi-modal Learning for No Reference Point Cloud Quality Assessment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1967-596X","authenticated-orcid":false,"given":"Xuemei","family":"Zhou","sequence":"first","affiliation":[{"name":"Centrum Wiskunde & Informatica & Delft University of Technology, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8990-2665","authenticated-orcid":false,"given":"Irene","family":"Viola","sequence":"additional","affiliation":[{"name":"Centrum Wiskunde & Informatica, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5989-8976","authenticated-orcid":false,"given":"Ruihong","family":"Yin","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1752-6837","authenticated-orcid":false,"given":"Pablo","family":"Cesar","sequence":"additional","affiliation":[{"name":"Centrum Wiskunde & Informatica & Delft University of Technology, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"BASICS: Broad quality assessment of static point clouds in a compression scenario","author":"Ak Ali","year":"2024","unstructured":"Ali Ak, Emin Zerman, Maurice Quach, Aladine Chetouani, Aljosa Smolic, Giuseppe Valenzise, and Patrick Le Callet. 2024. BASICS: Broad quality assessment of static point clouds in a compression scenario. IEEE Transactions on Multimedia (2024)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2019.8743277"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Evangelos Alexiou and Touradj Ebrahimi. 2020. Towards a point cloud structural similarity metric. In ICMEW. 1--6.","DOI":"10.1109\/ICMEW46912.2020.9106005"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803479"},{"key":"e_1_3_2_1_5_1","volume-title":"PointPCA: Point cloud objective quality assessment using PCA-based descriptors. arXiv preprint arXiv:2111.12663","author":"Alexiou Evangelos","year":"2021","unstructured":"Evangelos Alexiou, Xuemei Zhou, Irene Viola, and Pablo Cesar. 2021. PointPCA: Point cloud objective quality assessment using PCA-based descriptors. arXiv preprint arXiv:2111.12663 (2021)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552469.3555713"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2707807"},{"key":"e_1_3_2_1_9_1","volume-title":"Imagenet: A large-scale hierarchical image database","author":"Deng Jia","year":"2009","unstructured":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In IEEE\/CVF CVPR. 248--255."},{"key":"e_1_3_2_1_10_1","volume-title":"International Conference on Learning Representations.","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. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"volume-title":"Deep residual learning for image recognition","author":"He Kaiming","key":"e_1_3_2_1_11_1","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In IEEE\/CVF CVPR. 770--778."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of NAACL-HLT. 4171--4186","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_1_13_1","volume-title":"Adam: A Method for Stochastic Optimization. In ICLR.","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/WINCOM55661.2022.9966464"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/WINCOM55661.2022.9966464"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.78"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01696"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2011.01.005"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000125"},{"key":"e_1_3_2_1_20_1","volume-title":"Progressive Knowledge Transfer Based on Human Visual Perception Mechanism for Perceptual Quality Assessment of Point Clouds. arXiv preprint arXiv:2211.16646","author":"Liu Qi","year":"2022","unstructured":"Qi Liu, Yiyun Liu, Honglei Su, Hui Yuan, and Raouf Hamzaoui. 2022. Progressive Knowledge Transfer Based on Human Visual Perception Mechanism for Perceptual Quality Assessment of Point Clouds. arXiv preprint arXiv:2211.16646 (2022)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3167151"},{"key":"e_1_3_2_1_22_1","first-page":"4645","article-title":"PQA-Net: Deep No Reference Point Cloud Quality Assessment via Multi- View Projection","volume":"31","author":"Liu Qi","year":"2021","unstructured":"Qi Liu, Hui Yuan, Honglei Su, Hao Liu, Yu Wang, Huan Yang, and Junhui Hou. 2021. PQA-Net: Deep No Reference Point Cloud Quality Assessment via Multi- View Projection. IEEE TCSVT 31, 12 (2021), 4645--4660.","journal-title":"IEEE TCSVT"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.080"},{"key":"e_1_3_2_1_24_1","volume-title":"Evaluation criteria for point cloud compression. ISO\/IEC MPEG 16332","author":"Mekuria R","year":"2016","unstructured":"R Mekuria, Z Li, C Tulvan, and P Chou. 2016. Evaluation criteria for point cloud compression. ISO\/IEC MPEG 16332 (2016)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/su15021059"},{"key":"e_1_3_2_1_26_1","volume-title":"PCQM: A full-reference quality metric for colored 3D point clouds.","author":"Meynet Gabriel","year":"2020","unstructured":"Gabriel Meynet, Yana Nehm\u00e9, Julie Digne, and Guillaume Lavou\u00e9. 2020. PCQM: A full-reference quality metric for colored 3D point clouds. In QoMEX. 1--6."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10055-022-00651-5"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00886"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Wei Sun Xiongkuo Min Wei Lu and Guangtao Zhai. 2022. A deep learning based no-reference quality assessment model for ugc videos. In ACM MM. 856--865.","DOI":"10.1145\/3503161.3548329"},{"key":"e_1_3_2_1_30_1","first-page":"174","article-title":"A novel methodology for quality assessment of voxelized point clouds","volume":"10752","author":"Torlig Eric M","year":"2018","unstructured":"Eric M Torlig, Evangelos Alexiou, Tiago A Fonseca, Ricardo L de Queiroz, and Touradj Ebrahimi. 2018. A novel methodology for quality assessment of voxelized point clouds. In Applications of Digital Image Processing XLI, Vol. 10752. 174--190.","journal-title":"Applications of Digital Image Processing XLI"},{"key":"e_1_3_2_1_31_1","unstructured":"VEQG. [n. d.]. Final report from the Video Quality Experts Group on the validation of objective models of video quality assessment. [online]. Availabel httpwww.its.bldrdoc.govvqegvqeg-home.aspx ([n. d.])."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2023.3263943"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Songtao Wang Xiaoqi Wang Hao Gao and Jian Xiong. 2023. Non-Local Geometry and Color Gradient Aggregation Graph Model for No-Reference Point Cloud Quality Assessment. In ACM MM. 6803--6810.","DOI":"10.1145\/3581783.3612169"},{"key":"e_1_3_2_1_34_1","volume-title":"Point cloud quality assessment using 3D saliency maps. arXiv preprint arXiv:2209.15475","author":"Wang Zhengyu","year":"2022","unstructured":"Zhengyu Wang, Yujie Zhang, Qi Yang, Yiling Xu, Jun Sun, and Shan Liu. 2022. Point cloud quality assessment using 3D saliency maps. arXiv preprint arXiv:2209.15475 (2022)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101484"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Wuyuan Xie Kaimin Wang Yakun Ju and Miaohui Wang. 2023. pmBQA: Projection-based Blind Point Cloud Quality Assessment via Multimodal Learning. In ACM MM. 3250--3258.","DOI":"10.1145\/3581783.3611998"},{"key":"e_1_3_2_1_37_1","volume-title":"Predicting the Perceptual Quality of Point Cloud: A 3D-to-2D Projection-Based Exploration","author":"Yang Qi","year":"2020","unstructured":"Qi Yang, Hao Chen, Zhan Ma, Yiling Xu, Rongjun Tang, and Jun Sun. 2020. Predicting the Perceptual Quality of Point Cloud: A 3D-to-2D Projection-Based Exploration. IEEE Transactions on Multimedia (2020), 1--1. https:\/\/doi.org\/10. 1109\/TMM.2020.3033117"},{"volume-title":"No-Reference Point Cloud Quality Assessment via Domain Adaptation","author":"Yang Qi","key":"e_1_3_2_1_38_1","unstructured":"Qi Yang, Yipeng Liu, Siheng Chen, Yiling Xu, and Jun Sun. 2022. No-Reference Point Cloud Quality Assessment via Domain Adaptation. In IEEE\/CVF CVPR. 21179--21188."},{"key":"e_1_3_2_1_39_1","volume-title":"Inferring point cloud quality via graph similarity","author":"Yang Qi","year":"2020","unstructured":"Qi Yang, Zhan Ma, Yiling Xu, Zhu Li, and Jun Sun. 2020. Inferring point cloud quality via graph similarity. IEEE TAMI (2020)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2346028"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.537"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3186894"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Zicheng Zhang Wei Sun Xiongkuo Min Quan Zhou Jun He Qiyuan Wang and Guangtao Zhai. 2023. MM-PCQA: Multi-Modal Learning for No-reference Point Cloud Quality Assessment. In IJCAI.","DOI":"10.24963\/ijcai.2023\/195"},{"key":"e_1_3_2_1_44_1","volume-title":"GMS-3DQA: Projection-based Grid Minipatch Sampling for 3D Model Quality Assessment. arXiv preprint arXiv:2306.05658","author":"Zhang Zicheng","year":"2023","unstructured":"Zicheng Zhang, Wei Sun, Houning Wu, Yingjie Zhou, Chunyi Li, Xiongkuo Min, Guangtao Zhai, and Weisi Lin. 2023. GMS-3DQA: Projection-based Grid Minipatch Sampling for 3D Model Quality Assessment. arXiv preprint arXiv:2306.05658 (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"Open3D: A modern library for 3D data processing. arXiv preprint arXiv:1801.09847","author":"Zhou Qian-Yi","year":"2018","unstructured":"Qian-Yi Zhou, Jaesik Park, and Vladlen Koltun. 2018. Open3D: A modern library for 3D data processing. arXiv preprint arXiv:1801.09847 (2018)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3264105"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIPC59416.2023.10328338"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2021.3056231"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 3rd Workshop on Quality of Experience in Visual Multimedia Applications"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689093.3689183","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689093.3689183","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:55Z","timestamp":1750294675000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689093.3689183"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":48,"alternative-id":["10.1145\/3689093.3689183","10.1145\/3689093"],"URL":"https:\/\/doi.org\/10.1145\/3689093.3689183","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}