{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:26:20Z","timestamp":1780673180939,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401365, 62225112, 62271312, 62132006, U24A20220"],"award-info":[{"award-number":["62401365, 62225112, 62271312, 62132006, U24A20220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX20250411, 2025M773473"],"award-info":[{"award-number":["BX20250411, 2025M773473"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"STCSM","award":["22DZ2229005"],"award-info":[{"award-number":["22DZ2229005"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758304","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:38Z","timestamp":1761377198000},"page":"13413-13420","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["RGC-VQA: An Exploration Database for Robotic-Generated Video Quality Assessment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3173-8334","authenticated-orcid":false,"given":"Jianing","family":"Jin","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8819-8538","authenticated-orcid":false,"given":"Jiangyong","family":"Ying","sequence":"additional","affiliation":[{"name":"China Telecom, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6519-4067","authenticated-orcid":false,"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1300-7401","authenticated-orcid":false,"given":"Liu","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7753-1596","authenticated-orcid":false,"given":"Sijing","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7337-1748","authenticated-orcid":false,"given":"Yunhao","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1010-0804","authenticated-orcid":false,"given":"Yushuo","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413827"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915620033"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917720510"},{"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","unstructured":"Younggun Cho. 2025. Awesome SLAM Datasets. https:\/\/github.com\/youngguncho\/awesome-slam-datasets. Accessed: 2025-05-28."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5496296"},{"key":"e_1_3_2_1_7_1","volume-title":"The UZH-FPV Drone Racing Dataset. In IEEE Int. Conf. Robot. Autom. (ICRA).","author":"Delmerico Jeffrey","year":"2019","unstructured":"Jeffrey Delmerico, Titus Cieslewski, Henri Rebecq, Matthias Faessler, and Davide Scaramuzza. 2019. Are We Ready for Autonomous Drone Racing? The UZH-FPV Drone Racing Dataset. In IEEE Int. Conf. Robot. Autom. (ICRA)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Huiyu Duan Qiang Hu Jiarui Wang Liu Yang Zitong Xu Lu Liu Xiongkuo Min Chunlei Cai Tianxiao Ye Xiaoyun Zhang and Guangtao Zhai. 2025. FineVQ: Fine-Grained User Generated Content Video Quality Assessment. arXiv:2412.19238 [cs.CV] https:\/\/arxiv.org\/abs\/2412.19238","DOI":"10.1109\/CVPR52734.2025.00305"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV).","author":"Duan Huiyu","year":"2024","unstructured":"Huiyu Duan, Xiongkuo Min, Sijing Wu, Wei Shen, and Guangtao Zhai. 2024. UniProcessor: A Text-induced Unified Low-level Image Processor. In Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2022.3220404"},{"key":"e_1_3_2_1_11_1","unstructured":"Open X-Embodiment Collaboration et al. 2023. Open X-Embodiment: Robotic Learning Datasets and RT-X Models. https:\/\/arxiv.org\/abs\/2310.08864."},{"key":"e_1_3_2_1_12_1","volume-title":"RSS 2023 Workshop on Learning for Task and Motion Planning.","author":"Fang Hao-Shu","year":"2023","unstructured":"Hao-Shu Fang, Hongjie Fang, Zhenyu Tang, Jirong Liu, Junbo Wang, Haoyi Zhu, and Cewu Lu. 2023. RH20T: A Robotic Dataset for Learning Diverse Skills in One-Shot. In RSS 2023 Workshop on Learning for Task and Motion Planning."},{"key":"e_1_3_2_1_13_1","unstructured":"Yao Mu Fourier ActionNet Team. 2025. ActionNet: A dataset for dexterous bimanual manipulation. (2025)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2707479"},{"key":"e_1_3_2_1_16_1","unstructured":"Kristen Grauman Andrew Westbury and Lorenzo Torresani et al. 2024. Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives. arXiv:2311.18259 [cs.CV] https:\/\/arxiv.org\/abs\/2311.18259"},{"key":"e_1_3_2_1_17_1","volume-title":"ICME 2021 UGC-VQA Challenge. http:\/\/ugcvqa.com\/. [Online]..","author":"Haiqiang Wang","unstructured":"Wang Haiqiang, Li Gary, Liu Shan, and Kuo C.-C. Jay. 2021. ICME 2021 UGC-VQA Challenge. http:\/\/ugcvqa.com\/. [Online].."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2017.7965673"},{"key":"e_1_3_2_1_19_1","unstructured":"Bilibili Inc. 2010. Bilibili. https:\/\/www.bilibili.com."},{"key":"e_1_3_2_1_20_1","volume-title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset.","author":"Khazatsky Alexander","year":"2024","unstructured":"Alexander Khazatsky, Karl Pertsch, and Suraj Nair et al., 2024. DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset. (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923051"},{"key":"e_1_3_2_1_22_1","unstructured":"Chunyi Li Yuan Tian Xiaoyue Ling Zicheng Zhang Haodong Duan Haoning Wu Ziheng Jia Xiaohong Liu Xiongkuo Min Guo Lu Weisi Lin and Guangtao Zhai. 2025a. Image Quality Assessment: From Human to Machine Preference. arXiv:2503.10078 [cs.CV] https:\/\/arxiv.org\/abs\/2503.10078"},{"key":"e_1_3_2_1_23_1","unstructured":"Chunyi Li Jiaohao Xiao Jianbo Zhang Farong Wen Zicheng Zhang Yuan Tian Xiangyang Zhu Xiaohong Liu Zhengxue Cheng Weisi Lin and Guangtao Zhai. 2025b. Perceptual Quality Assessment for Embodied AI. arXiv:2505.16815 [cs.CV] https:\/\/arxiv.org\/abs\/2505.16815"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR49039.2020.00015"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02453"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917702237"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2012.2212417"},{"key":"e_1_3_2_1_30_1","volume-title":"ERA: A Dataset and Deep Learning Benchmark for Event Recognition in Aerial Videos. arXiv:2001.11394 [cs.CV] https:\/\/arxiv.org\/abs\/2001.11394","author":"Mou Lichao","year":"2020","unstructured":"Lichao Mou, Yuansheng Hua, Pu Jin, and Xiao Xiang Zhu. 2020. ERA: A Dataset and Deep Learning Benchmark for Event Recognition in Aerial Videos. arXiv:2001.11394 [cs.CV] https:\/\/arxiv.org\/abs\/2001.11394"},{"key":"e_1_3_2_1_31_1","first-page":"3073","volume-title":"CVD2014-A database for evaluating no-reference video quality assessment algorithms. IEEE Transactions on Image Processing (TIP)","volume":"25","author":"Nuutinen Mikko","year":"2016","unstructured":"Mikko Nuutinen, Toni Virtanen, Mikko Vaahteranoksa, Tero Vuori, Pirkko Oittinen, and Jukka H\u00e4kkinen. 2016. CVD2014-A database for evaluating no-reference video quality assessment algorithms. IEEE Transactions on Image Processing (TIP), Vol. 25, 7 (2016), 3073-3086."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995586"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911400640"},{"key":"e_1_3_2_1_34_1","first-page":"206","article-title":"Are They Going to Cross","author":"Rasouli Amir","year":"2017","unstructured":"Amir Rasouli, Iuliia Kotseruba, and John K Tsotsos. 2017. Are They Going to Cross? A Benchmark Dataset and Baseline for Pedestrian Crosswalk Behavior. In ICCVW. 206-213.","journal-title":"In ICCVW."},{"key":"e_1_3_2_1_35_1","volume-title":"Methodology for the subjective assessment of the quality of television pictures. Recommendation ITU-R BT","author":"Series BT","year":"2012","unstructured":"BT Series. 2012. Methodology for the subjective assessment of the quality of television pictures. Recommendation ITU-R BT (2012), 500-13."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2042111"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2869673"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3090333"},{"key":"e_1_3_2_1_41_1","unstructured":"Unitree Robotics. 2024. Unitree Robotics Open Source Resources. https:\/\/www.unitree.com\/opensource. Accessed: 2025-05-28."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01758"},{"key":"e_1_3_2_1_44_1","unstructured":"Jiarui Wang Huiyu Duan Yu Zhao Juntong Wang Guangtao Zhai and Xiongkuo Min. 2025b. LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMs. arXiv:2504.08358 [cs.CV] https:\/\/arxiv.org\/abs\/2504.08358"},{"key":"e_1_3_2_1_45_1","unstructured":"Juntong Wang Jiarui Wang Huiyu Duan Guangtao Zhai and Xiongkuo Min. 2025c. TDVE-Assessor: Benchmarking and Evaluating the Quality of Text-Driven Video Editing with LMMs. arXiv:2505.19535 [cs.CV] https:\/\/arxiv.org\/abs\/2505.19535"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901772"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01323"},{"key":"e_1_3_2_1_48_1","unstructured":"Zhiqiang Wang Hao Zheng Yunshuang Nie Wenjun Xu Qingwei Wang Hua Ye Zhe Li Kaidong Zhang Xuewen Cheng Wanxi Dong Chang Cai Liang Lin Feng Zheng and Xiaodan Liang. 2024. All Robots in One: A New Standard and Unified Dataset for Versatile General-Purpose Embodied Agents. arXiv:2408.10899 [cs.RO] https:\/\/arxiv.org\/abs\/2408.10899"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"e_1_3_2_1_51_1","volume-title":"FVQ: A Large-Scale Dataset and A LMM-based Method for Face Video Quality Assessment. arXiv:2504.09255 [cs.CV] https:\/\/arxiv.org\/abs\/2504.09255","author":"Wu Sijing","year":"2025","unstructured":"Sijing Wu, Yunhao Li, Ziwen Xu, Yixuan Gao, Huiyu Duan, Wei Sun, and Guangtao Zhai. 2025. FVQ: A Large-Scale Dataset and A LMM-based Method for Face Video Quality Assessment. arXiv:2504.09255 [cs.CV] https:\/\/arxiv.org\/abs\/2504.09255"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2585880"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.133"},{"key":"e_1_3_2_1_54_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 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 Conference on Computer Vision and Pattern Recognition (CVPR). 14019-14029."},{"key":"e_1_3_2_1_55_1","unstructured":"Fisher Yu Haofeng Chen Xin Wang Wenqi Xian Yingying Chen Fangchen Liu Vashisht Madhavan and Trevor Darrell. 2020. BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning. arXiv:1805.04687 [cs.CV] https:\/\/arxiv.org\/abs\/1805.04687"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3107213"},{"key":"e_1_3_2_1_57_1","unstructured":"Jianbo Zhang Chunyi Li Liang Yuan Guoquan Zheng Jie Hao and Guangtao Zhai. 2024. Embodied Image Quality Assessment for Robotic Intelligence. arXiv:2412.18774 [cs.CV] https:\/\/arxiv.org\/abs\/2412.18774"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00174"},{"key":"e_1_3_2_1_59_1","volume-title":"ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos. arXiv:2412.20423 [cs.CV] https:\/\/arxiv.org\/abs\/2412.20423","author":"Zhu Xilei","year":"2025","unstructured":"Xilei Zhu, Huiyu Duan, Liu Yang, Yucheng Zhu, Xiongkuo Min, Guangtao Zhai, and Patrick Le Callet. 2025. ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos. arXiv:2412.20423 [cs.CV] https:\/\/arxiv.org\/abs\/2412.20423"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:46:22Z","timestamp":1765309582000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758304"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":59,"alternative-id":["10.1145\/3746027.3758304","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758304","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}