{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T18:06:11Z","timestamp":1770228371357,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":43,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSFC","award":["62250001?62231002"],"award-info":[{"award-number":["62250001?62231002"]}]},{"name":"Beijing Natural Science Foundation","award":["L223021"],"award-info":[{"award-number":["L223021"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3689093.3689181","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T18:09:19Z","timestamp":1729447759000},"page":"30-38","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["MT-VQA: A Multi-task Approach for Quality Assessment of Short-form Videos"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7478-2351","authenticated-orcid":false,"given":"Shijie","family":"Wen","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9591-2568","authenticated-orcid":false,"given":"Minglang","family":"Qiao","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4639-8136","authenticated-orcid":false,"given":"Lai","family":"Jiang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0277-3301","authenticated-orcid":false,"given":"Mai","family":"Xu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4708-6572","authenticated-orcid":false,"given":"Xin","family":"Deng","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4979-9290","authenticated-orcid":false,"given":"Shengxi","family":"Li","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"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":"TikTok Stats and Analytics to Know","author":"Anderson Sarah","year":"2024","unstructured":"Sarah Anderson. 2024. TikTok Stats and Analytics to Know in 2024. (2024). https:\/\/www.socialchamp.io\/blog\/tiktok-stats\/"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777665"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01519-y"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3088505"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107615"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_25"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500021"},{"key":"e_1_3_2_1_9_1","volume-title":"Graph-based visual saliency. Advances in neural information processing systems 19","author":"Harel Jonathan","year":"2006","unstructured":"Jonathan Harel, Christof Koch, and Pietro Perona. 2006. Graph-based visual saliency. Advances in neural information processing systems 19 (2006)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/2919332.2919806"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"e_1_3_2_1_13_1","volume-title":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 3520--3527","author":"Jain Samyak","year":"2020","unstructured":"Samyak Jain, Pradeep Yarlagadda, Shreyank Jyoti, Shyamgopal Karthik, Ramanathan Subramanian, and Vineet Gandhi. 2020. Vinet: Pushing the limits of visual modality for audio-visual saliency prediction. In 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 3520--3527."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01371-6"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923051"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2936112"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3055197"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3122347"},{"key":"e_1_3_2_1_20_1","volume-title":"Noel E O'Connor, Xavier Giro-i Nieto, and Kevin McGuinness.","author":"Linardos Panagiotis","year":"2019","unstructured":"Panagiotis Linardos, Eva Mohedano, Juan Jose Nieto, Noel E O'Connor, Xavier Giro-i Nieto, and Kevin McGuinness. 2019. Simple vs complex temporal recurrences for video saliency prediction. arXiv preprint arXiv:1907.01869 (2019)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.80"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02453"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3172971"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00248"},{"key":"e_1_3_2_1_27_1","volume-title":"International Journal of Computer Vision","author":"Qiao Minglang","year":"2023","unstructured":"Minglang Qiao, Yufan Liu, Mai Xu, Xin Deng, Bing Li, Weiming Hu, and Ali Borji. 2023. Joint learning of audio--visual saliency prediction and sound source localization on multi-face videos. International Journal of Computer Vision (2023), 1--23."},{"key":"e_1_3_2_1_28_1","volume-title":"HyperSOR: Context-aware Graph Hypernetwork for Salient Object Ranking","author":"Qiao Minglang","year":"2024","unstructured":"Minglang Qiao, Mai Xu, Lai Jiang, Peng Lei, ShijieWen, Yunjin Chen, and Leonid Sigal. 2024. HyperSOR: Context-aware Graph Hypernetwork for Salient Object Ranking. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2299154"},{"key":"e_1_3_2_1_30_1","volume-title":"Methodology for the subjective assessment of the quality of television pictures. Recommendation ITU-R BT 500, 13","author":"Series BT","year":"2012","unstructured":"BT Series. 2012. Methodology for the subjective assessment of the quality of television pictures. Recommendation ITU-R BT 500, 13 (2012)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455999"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2924417"},{"key":"e_1_3_2_1_35_1","volume-title":"Spatio-Temporal Self-Attention Network for Video Saliency Prediction","author":"Wang Ziqiang","year":"2021","unstructured":"Ziqiang Wang, Zhi Liu, Gongyang Li, Yang Wang, Tianhong Zhang, Lihua Xu, and JijunWang. 2021. Spatio-Temporal Self-Attention Network for Video Saliency Prediction. IEEE Transactions on Multimedia (2021)."},{"key":"e_1_3_2_1_36_1","volume-title":"Saliency Prediction on Mobile Videos: A Fixation Mapping-Based Dataset and A Transformer Approach","author":"Wen Shijie","year":"2023","unstructured":"Shijie Wen, Li Yang, Mai Xu, Minglang Qiao, Tao Xu, and Lin Bai. 2023. Saliency Prediction on Mobile Videos: A Fixation Mapping-Based Dataset and A Transformer Approach. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_2_1_37_1","volume-title":"Modular Blind Video Quality Assessment. arXiv preprint arXiv:2402.19276","author":"Wen Wen","year":"2024","unstructured":"Wen Wen, Mu Li, Yabin Zhang, Yiting Liao, Junlin Li, Li Zhang, and Kede Ma. 2024. Modular Blind Video Quality Assessment. arXiv preprint arXiv:2402.19276 (2024)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"e_1_3_2_1_39_1","volume-title":"Disentangling aesthetic and technical effects for video quality assessment of user generated content. arXiv preprint arXiv:2211.04894 2, 5","author":"Wu Haoning","year":"2022","unstructured":"Haoning Wu, Liang Liao, Chaofeng Chen, Jingwen Hou, Annan Wang, Wenxiu Sun, Qiong Yan, and Weisi Lin. 2022. Disentangling aesthetic and technical effects for video quality assessment of user generated content. arXiv preprint arXiv:2211.04894 2, 5 (2022), 6."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350990"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2947352"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 14019--14029","author":"Ying Zhenqiang","year":"2021","unstructured":"Zhenqiang Ying, Maniratnam Mandal, Deepti Ghadiyaram, and Alan Bovik. 2021. Patch-vq:'patching up'the video quality problem. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 14019--14029."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3215311"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"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\/3689093.3689181","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689093.3689181","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\/3689093.3689181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":43,"alternative-id":["10.1145\/3689093.3689181","10.1145\/3689093"],"URL":"https:\/\/doi.org\/10.1145\/3689093.3689181","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"}}]}}