{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T15:27:35Z","timestamp":1719934055359},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1016\/j.jvcir.2024.104118","type":"journal-article","created":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T03:13:43Z","timestamp":1710299623000},"page":"104118","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Spatiotemporal feature learning for no-reference gaming content video quality assessment"],"prefix":"10.1016","volume":"100","author":[{"given":"Ngai-Wing","family":"Kwong","sequence":"first","affiliation":[]},{"given":"Yui-Lam","family":"Chan","sequence":"additional","affiliation":[]},{"given":"Sik-Ho","family":"Tsang","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-3162-6105","authenticated-orcid":false,"given":"Ziyin","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Kin-Man","family":"Lam","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2024.104118_b1","doi-asserted-by":"crossref","unstructured":"N. Barman, S. Schmidt, S. Zadtootaghaj, M. Martini, S. M\u00f6ller, An evaluation of Video quality assessment metrics for passive gaming video streaming, in: Proc. 23rd Packet Video Workshop, 2018, pp. 7\u201312.","DOI":"10.1145\/3210424.3210434"},{"key":"10.1016\/j.jvcir.2024.104118_b2","doi-asserted-by":"crossref","unstructured":"N. Barman, M. Martini, S. Zadtootaghaj, S. M\u00f6ller, S. Lee, A comparative quality assessment study for gaming and non-gaming videos, in: Proc. 2018 Tenth Int. Conf. Qual. Multimedia Exper., QoMEX, 2018, pp. 1\u20136.","DOI":"10.1109\/QoMEX.2018.8463403"},{"key":"10.1016\/j.jvcir.2024.104118_b3","series-title":"Toward a practical perceptual video quality metric","author":"Netflix","year":"2023"},{"key":"10.1016\/j.jvcir.2024.104118_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2022.103676","article-title":"No-Reference Video Quality Assessment using novel hybrid features and two-stage hybrid regression for score level fusion","volume":"89","author":"Vishwakarma","year":"2022","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2024.104118_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2023.103912","article-title":"Screen content video quality assessment based on spatiotemporal sparse feature","volume":"96","author":"Ding","year":"2023","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2024.104118_b6","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/j.jvcir.2017.01.002","article-title":"No-reference pixel based video quality assessment for HEVC decoded video","volume":"43","author":"Huang","year":"2017","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2024.104118_b7","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1109\/TMM.2021.3122347","article-title":"User-generated video quality assessment: A subjective and objective study","volume":"25","author":"Li","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.jvcir.2024.104118_b8","doi-asserted-by":"crossref","unstructured":"D. Li, T. Jiang, M. Jiang, Quality assessment of in-the-wild videos, in: Proc. of 27th ACM Int. Conf. Multimedia, 2019, pp. 2351\u20132359.","DOI":"10.1145\/3343031.3351028"},{"key":"10.1016\/j.jvcir.2024.104118_b9","doi-asserted-by":"crossref","unstructured":"J. Korhonen, Y. Su, J. You, Blind natural video quality prediction via statistical temporal features and deep spatial features, in: Proc. of 28th ACM Int. Conf. Multimedia, 2020, pp. 3311\u20133319.","DOI":"10.1145\/3394171.3413845"},{"key":"10.1016\/j.jvcir.2024.104118_b10","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1109\/OJSP.2021.3090333","article-title":"RAPIQUE: Rapid and accurate video quality prediction of user generated content","volume":"2","author":"Tu","year":"2021","journal-title":"IEEE Open J. Signal Process."},{"key":"10.1016\/j.jvcir.2024.104118_b11","doi-asserted-by":"crossref","first-page":"4449","DOI":"10.1109\/TIP.2021.3072221","article-title":"UGC-VQA: Benchmarking blind video quality assessment for user generated content","volume":"30","author":"Tu","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2024.104118_b12","doi-asserted-by":"crossref","unstructured":"N. Barman, S. Zadtootaghaj, S. Schmidt, M. Martini, S. M\u00f6ller, GamingVideoSET: A dataset for gaming video streaming applications, in: Proc. 16th Annu. Workshop Netw. Syst. Support Games, NetGames, 2018, pp. 1\u20136.","DOI":"10.1109\/NetGames.2018.8463362"},{"key":"10.1016\/j.jvcir.2024.104118_b13","doi-asserted-by":"crossref","first-page":"74511","DOI":"10.1109\/ACCESS.2019.2920477","article-title":"No-reference video quality estimation based on machine learning for passive gaming video streaming applications","author":"Barman","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvcir.2024.104118_b14","doi-asserted-by":"crossref","unstructured":"S. Zadtootaghaj, N. Barman, S. Schmidt, M. Martini, S. M\u00f6ller, NR-GVQM: A no reference gaming video quality metric, in: Proc. 2018 IEEE Int. Symposium Multimedia, ISM, 2018, pp. 131\u2013134.","DOI":"10.1109\/ISM.2018.00031"},{"key":"10.1016\/j.jvcir.2024.104118_b15","doi-asserted-by":"crossref","unstructured":"S. G\u00f6ring, R. Rao, A. Raake, nofu-A lightweight no-reference pixel based video quality model for gaming content, in: Proc. 11th Int. Conf. Qual. Multimedia Exper., QoMEX, 2019, pp. 1\u20136.","DOI":"10.1109\/QoMEX.2019.8743262"},{"key":"10.1016\/j.jvcir.2024.104118_b16","first-page":"1","article-title":"NDNetGaming-development of a no-reference deep CNN for gaming video quality prediction","author":"Utke","year":"2020","journal-title":"Multimedia Tools Appl."},{"key":"10.1016\/j.jvcir.2024.104118_b17","doi-asserted-by":"crossref","unstructured":"S. Zadtootaghaj, N. Barman, R. Rao, S. G\u00f6ring, M. Martini, A. Raake, S. M\u00f6ller, DEMI: Deep video quality estimation model using perceptual video quality dimensions, in: Proc. 2020 IEEE 22nd Int. Workshop Multimedia Signal Process., MMSP, 2020, pp. 1\u20136.","DOI":"10.1109\/MMSP48831.2020.9287080"},{"key":"10.1016\/j.jvcir.2024.104118_b18","first-page":"1","article-title":"Subjective and objective analysis of streamed gaming videos","author":"Yu","year":"2023","journal-title":"IEEE Trans. Games"},{"key":"10.1016\/j.jvcir.2024.104118_b19","doi-asserted-by":"crossref","unstructured":"G. Huang, Z. Liu, L. Maaten, K. Weinberger, Densely connected convolutional networks, in: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., CVPR, 2017, pp. 4700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"10.1016\/j.jvcir.2024.104118_b20","doi-asserted-by":"crossref","unstructured":"J. Deng, W. Dong, R. Socher, L. Li, K. Li, F.F. Li, Imagenet: A large-scale hierarchical image database, in: Proc. of the IEEE Conf. Comput. Vis. Pattern Recognit., CVPR, 2009, pp. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10.1016\/j.jvcir.2024.104118_b21","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2024.104118_b22","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1109\/TIP.2013.2293423","article-title":"Gradient magnitude similarity deviation: A highly efficient perceptual image quality index","volume":"23","author":"Xue","year":"2014","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2024.104118_b23","unstructured":"Z. Wang, E. Simoncelli, A. Bovik, Multiscale structural similarity for image quality assessment, in: Proc. 38th Asilomar Conf. Signals Systems Comput., 2003, pp. 1398\u20131402."},{"key":"10.1016\/j.jvcir.2024.104118_b24","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1109\/TIP.2005.859378","article-title":"Image information and visual quality","volume":"15","author":"Sheikh","year":"2006","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2024.104118_b25","doi-asserted-by":"crossref","first-page":"2378","DOI":"10.1109\/TIP.2011.2109730","article-title":"FSIM: A feature similarity index for image quality assessment","author":"Zhang","year":"2011","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2024.104118_b26","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1109\/LSP.2010.2043888","article-title":"A two-step framework for constructing blind image quality indices","volume":"17","author":"Moorthy","year":"2010","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.jvcir.2024.104118_b27","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","article-title":"Making a \u201ccompletely blind\u201d image quality analyzer","volume":"20","author":"Mittal","year":"2013","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.jvcir.2024.104118_b28","doi-asserted-by":"crossref","first-page":"4695","DOI":"10.1109\/TIP.2012.2214050","article-title":"No-reference image quality assessment in the spatial domain","volume":"21","author":"Mittal","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2024.104118_b29","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1016\/j.image.2012.04.005","article-title":"Perceptual image quality assessment based on structural similarity and visual masking","author":"Fei","year":"2012","journal-title":"Signal Process. Image Commun."},{"key":"10.1016\/j.jvcir.2024.104118_b30","doi-asserted-by":"crossref","unstructured":"X. Liu, J.V.D. Weijer, A.D. Bagdanov, RankIQA: Learning from rankings for no-reference image quality assessment, in: Proc. of IEEE Int. Conf. Image Process., ICIP, 2017, pp. 1040\u20131049.","DOI":"10.1109\/ICCV.2017.118"},{"key":"10.1016\/j.jvcir.2024.104118_b31","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1007\/s11263-020-01408-w","article-title":"Unified quality assessment of in-the-wild videos with mixed datasets training","author":"Li","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jvcir.2024.104118_b32","doi-asserted-by":"crossref","first-page":"5923","DOI":"10.1109\/TIP.2019.2923051","article-title":"Two-level approach for no-reference consumer video quality assessment","volume":"28","author":"Korhonen","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2024.104118_b33","doi-asserted-by":"crossref","unstructured":"J. You, J. Korhonen, Deep neural networks for no-reference video quality assessment, in: Proc. of IEEE Int. Conf. Image Process., ICIP, 2019, pp. 2349\u20132353.","DOI":"10.1109\/ICIP.2019.8803395"},{"key":"10.1016\/j.jvcir.2024.104118_b34","doi-asserted-by":"crossref","unstructured":"W. Liu, Z. Duanmu, Z. Wang, End-to-End Blind Quality Assessment of Compressed Videos Using Deep Neural Networks, in: Proc. of ACM Multimedia, 2018, pp. 546\u2013554.","DOI":"10.1145\/3240508.3240643"},{"key":"10.1016\/j.jvcir.2024.104118_b35","doi-asserted-by":"crossref","unstructured":"A. Rehman, K. Zeng, Z. Wang, Display device-adapted video quality-of-experience assessment, in: Proc. of Human Vision Electronic Imaging, 2015, pp. 1\u201311.","DOI":"10.1117\/12.2077917"},{"key":"10.1016\/j.jvcir.2024.104118_b36","doi-asserted-by":"crossref","first-page":"3500","DOI":"10.1109\/TCSVT.2021.3114509","article-title":"Spatiotemporal representation learning for blind video quality assessment","volume":"32","author":"Liu","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2024.104118_b37","series-title":"GISET: Gaming image quality dataset","author":"Utke","year":"2023"},{"key":"10.1016\/j.jvcir.2024.104118_b38","doi-asserted-by":"crossref","DOI":"10.1109\/TKDE.2022.3172903","article-title":"Graph self-supervised learning: A survey","author":"Liu","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.jvcir.2024.104118_b39","series-title":"Multi-task learning with deep neural networks: A survey","author":"Crawshaw","year":"2020"},{"key":"10.1016\/j.jvcir.2024.104118_b40","doi-asserted-by":"crossref","first-page":"4516","DOI":"10.1109\/TIP.2018.2839890","article-title":"A gabor feature-based quality assessment model for the screen content images","volume":"27","author":"Ni","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2024.104118_b41","doi-asserted-by":"crossref","unstructured":"T. Akilan, Q. Wu, W. Jiang, A. Safaei, J. Huo, New trend in video foreground detection using deep learning, in: Proc. Midwest Symposium Circuits Syst., 2018, pp. 889\u2013892.","DOI":"10.1109\/MWSCAS.2018.8623825"},{"key":"10.1016\/j.jvcir.2024.104118_b42","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1016\/j.ins.2020.09.003","article-title":"CNN-based encoder-decoder networks for salient object detection: A comprehensive review and recent advances","author":"Ji","year":"2021","journal-title":"Inform. Sci."},{"key":"10.1016\/j.jvcir.2024.104118_b43","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, Attention is all you need, in: Proc. Advances Neural Inf. Process. Syst., 2017."},{"key":"10.1016\/j.jvcir.2024.104118_b44","unstructured":"J. Devlin, M. Chang, K. Lee, K. Toutanova, BERT: Pre-training of deep bidirectional transformers for language understanding, in: Proc. naacL-HLT, 2019, p. 2."},{"key":"10.1016\/j.jvcir.2024.104118_b45","doi-asserted-by":"crossref","unstructured":"S. Zadtootaghaj, S. Schmidt, S. Sabet, S. M\u00f6ller, C. Griwodz, Quality estimation models for gaming video streaming services using perceptual video quality dimensions, in: Proc. 11th Int. Conf. Multimedia Syst., ACM, 2020.","DOI":"10.1145\/3339825.3391872"},{"key":"10.1016\/j.jvcir.2024.104118_b46","doi-asserted-by":"crossref","unstructured":"H. Wu, C. Chen, J. Hou, L. Liao, A. Wang, W. Sun, Q. Yan, W. Lin, FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling, in: Proc. of European Conf. Comput. Vis., ECCV, 2022, pp. 538\u2013554.","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"10.1016\/j.jvcir.2024.104118_b47","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.1109\/TCSVT.2022.3209007","article-title":"Quality assessment of UGC videos based on decomposition and recomposition","volume":"33","author":"Liu","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2024.104118_b48","series-title":"Final report from the video quality experts group on the validation of objective quailty metrics for video quality assessmen","author":"Group","year":"2021"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320324000737?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320324000737?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T09:44:29Z","timestamp":1717407869000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320324000737"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":48,"alternative-id":["S1047320324000737"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2024.104118","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2024,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Spatiotemporal feature learning for no-reference gaming content video quality assessment","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2024.104118","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"104118"}}