{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T06:57:47Z","timestamp":1769065067594,"version":"3.49.0"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T00:00:00Z","timestamp":1676592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T00:00:00Z","timestamp":1676592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s11042-023-14560-5","type":"journal-article","created":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T08:39:57Z","timestamp":1676623197000},"page":"21085-21099","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Deep learning for video game genre classification"],"prefix":"10.1007","volume":"82","author":[{"given":"Yuhang","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8253-1267","authenticated-orcid":false,"given":"Lukun","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,17]]},"reference":[{"key":"14560_CR1","doi-asserted-by":"crossref","unstructured":"Amiriparian S, Cummins N, Gerczuk M, Pugachevskiy S, Ottl S, Schuller B (2019) are you playing a shooter again?! deep representation learning for audio-based video game genre recognition. IEEE Transactions on Games","DOI":"10.1109\/TG.2019.2894532"},{"key":"14560_CR2","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.compedu.2017.05.016","volume":"113","author":"M Barr","year":"2017","unstructured":"Barr M (2017) Video games can develop graduate skills in higher education students: a randomised trial. Comput Educ 113:86\u201397","journal-title":"Comput Educ"},{"issue":"5","key":"14560_CR3","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1037\/pro0000150","volume":"48","author":"AM Bean","year":"2017","unstructured":"Bean AM, Nielsen RK, Van Rooij AJ, Ferguson CJ (2017) Video game addiction: the push to pathologize video games. Professional Psychology Research and Practice 48(5):378","journal-title":"Professional Psychology Research and Practice"},{"key":"14560_CR4","doi-asserted-by":"crossref","unstructured":"Biradar GR, Raagini JM, Varier A, Sudhir M (2019) Classification of book genres using book cover and title. In: 2019 IEEE international conference on intelligent systems and green technology (ICISGT). IEEE, pp 72\u2013723","DOI":"10.1109\/ICISGT44072.2019.00031"},{"key":"14560_CR5","doi-asserted-by":"crossref","unstructured":"Buczkowski P, Sobkowicz A, Kozlowski M (2018) Deep learning approaches towards book covers classification. In: ICPRAM, pp 309\u2013316","DOI":"10.5220\/0006556103090316"},{"issue":"1","key":"14560_CR6","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.gpb.2017.07.003","volume":"16","author":"C Cao","year":"2018","unstructured":"Cao C, Liu F, Tan H, Song D, Shu W, Li W, Xie Z (2018) Deep learning and its applications in biomedicine. Genomics, proteomics & bioinformatics 16(1):17\u201332","journal-title":"Genomics, proteomics & bioinformatics"},{"key":"14560_CR7","unstructured":"Cer D, Yang Y, Kong SY, Hua N, Limtiaco N, John RS, Sung YH (2018) Universal sentence encoder. arXiv:1803.11175"},{"key":"14560_CR8","unstructured":"Chiang H, Ge Y, Wu C (2015) Classification of book genres by cover and title"},{"key":"14560_CR9","doi-asserted-by":"crossref","unstructured":"Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1251\u20131258","DOI":"10.1109\/CVPR.2017.195"},{"issue":"5","key":"14560_CR10","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1177\/1555412015591900","volume":"12","author":"RI Clarke","year":"2017","unstructured":"Clarke RI, Lee JH, Clark N (2017) Why video game genres fail: a classificatory analysis. Games and Culture 12(5):445\u2013465","journal-title":"Games and Culture"},{"key":"14560_CR11","doi-asserted-by":"crossref","unstructured":"Costa YM, Oliveira LS, Silla Jr CN (2017) An evaluation of convolutional neural networks for music classification using spectrograms. Applied soft computing 52:28\u201338","DOI":"10.1016\/j.asoc.2016.12.024"},{"key":"14560_CR12","doi-asserted-by":"crossref","unstructured":"Cui C, Yang H, Wang Y, Zhao S, Asad Z, Coburn LA, Huo Y (2022) Deep multi-modal fusion of image and non-image data in disease diagnosis and prognosis: a Review. arXiv:2203.15588","DOI":"10.1088\/2516-1091\/acc2fe"},{"key":"14560_CR13","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. Ieee, pp 248\u2013 255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"14560_CR14","unstructured":"Dieleman S, Brakel P, Schrauwen B (2011) Audio-based music classification with a pretrained convolutional network. In: 12th international society for music information retrieval conference (ISMIR-2011). University of Miami, pp 669\u2013674"},{"key":"14560_CR15","doi-asserted-by":"crossref","unstructured":"Dong M (2018) Convolutional neural network achieves human-level accuracy in music genre classification. arXiv:1802.09697","DOI":"10.32470\/CCN.2018.1153-0"},{"key":"14560_CR16","unstructured":"Ebner M, Levine J, Lucas SM, Schaul T, Thompson T, Togelius J (2013) Towards a video game description language. Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik"},{"key":"14560_CR17","unstructured":"Fang J, Grunberg D, Litman DT, Wang Y (2017) Discourse analysis of lyric and Lyric-Based classification of music. In: ISMIR, pp 464\u2013471"},{"issue":"3","key":"14560_CR18","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2020","unstructured":"Feng D, Haase-Sch\u00fctz C., Rosenbaum L, Hertlein H, Glaeser C, Timm F, Dietmayer K (2020) Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges. IEEE Trans Intell Transp Syst 22(3):1341\u20131360","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"14560_CR19","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1146\/annurev-lawsocsci-101317-031036","volume":"14","author":"CJ Ferguson","year":"2018","unstructured":"Ferguson CJ (2018) Violent video games, sexist video games, and the law: why can\u2019t we find effects?. Annual Review of Law and Social Science 14:411\u2013426","journal-title":"Annual Review of Law and Social Science"},{"issue":"16","key":"14560_CR20","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1002\/jcc.24764","volume":"38","author":"GB Goh","year":"2017","unstructured":"Goh GB, Hodas NO, Vishnu A (2017) Deep learning for computational chemistry. Journal of computational chemistry 38(16):1291\u20131307","journal-title":"Journal of computational chemistry"},{"key":"14560_CR21","unstructured":"Gouyon F, Dixon S, Pampalk E, Widmer G (2004, June) Evaluating rhythmic descriptors for musical genre classification. In: Proceedings of the AES 25th International Conference, pp 196\u2013204"},{"key":"14560_CR22","doi-asserted-by":"publisher","first-page":"e101432","DOI":"10.1016\/j.avb.2020.101432","volume":"53","author":"M Guggisberg","year":"2020","unstructured":"Guggisberg M (2020) Sexually explicit video games and online pornography-the promotion of sexual violence: a critical commentary. Aggress Violent Beh 53:e101432\u2013e101432","journal-title":"Aggress Violent Beh"},{"key":"14560_CR23","doi-asserted-by":"crossref","unstructured":"Guo Y, Wang H, Hu Q, Liu H, Liu L, Bennamoun M (2020) Deep learning for 3d point clouds: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2020.3005434"},{"issue":"8","key":"14560_CR24","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"14560_CR25","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861"},{"key":"14560_CR26","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"14560_CR27","first-page":"10944","volume":"34","author":"Y Huang","year":"2021","unstructured":"Huang Y, Du C, Xue Z, Chen X, Zhao H, Huang L (2021) What makes multi-modal learning better than single (provably). Adv Neural Inf Process Syst 34:10944\u201310956","journal-title":"Adv Neural Inf Process Syst"},{"key":"14560_CR28","unstructured":"Iwana BK, Rizvi STR, Ahmed S, Dengel A, Uchida S (2016) Judging a book by its cover. arXiv:1610.09204"},{"key":"14560_CR29","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.compag.2018.02.016","volume":"147","author":"A Kamilaris","year":"2018","unstructured":"Kamilaris A, Prenafeta-Bold\u00fa FX (2018) Deep learning in agriculture: a survey. Comput Electron Agric 147:70\u201390","journal-title":"Comput Electron Agric"},{"key":"14560_CR30","unstructured":"Keeler KR (2020) Video Games in Music Education: the Impact of Video Games on Rhythmic Performance. Visions of Research in Music Education, (37)"},{"key":"14560_CR31","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"key":"14560_CR32","unstructured":"Kundu C, Zheng L (2020) Deep multi-modal networks for book genre classification based on its cover. arXiv:2011.07658"},{"key":"14560_CR33","doi-asserted-by":"crossref","unstructured":"Laurier C, Grivolla J, Herrera P (2008) Multimodal music mood classification using audio and lyrics. In: 2008 Seventh international conference on machine learning and applications. IEEE, pp 688\u2013693","DOI":"10.1109\/ICMLA.2008.96"},{"key":"14560_CR34","unstructured":"Logan B (2000) Mel frequency cepstral coefficients for music modeling. In: Ismir, vol 270, pp 1\u201311"},{"key":"14560_CR35","doi-asserted-by":"crossref","unstructured":"Lougheed T (2019) Video games bring new aspects to medical education and training","DOI":"10.1503\/cmaj.1095784"},{"key":"14560_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42979-020-00132-z","volume":"1","author":"A Lucieri","year":"2020","unstructured":"Lucieri A, Sabir H, Siddiqui SA, Rizvi STR, Iwana BK, Uchida S, Ahmed S (2020) Benchmarking deep learning models for classification of book covers. SN Computer Science 1:1\u201316","journal-title":"SN Computer Science"},{"issue":"6","key":"14560_CR37","doi-asserted-by":"publisher","first-page":"2545","DOI":"10.1021\/acs.jcim.9b00266","volume":"59","author":"AC Mater","year":"2019","unstructured":"Mater AC, Coote ML (2019) Deep learning in chemistry. Journal of chemical information and modeling 59(6):2545\u20132559","journal-title":"Journal of chemical information and modeling"},{"issue":"5910","key":"14560_CR38","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1126\/science.1166900","volume":"323","author":"MJ Mayo","year":"2009","unstructured":"Mayo MJ (2009) Video games: a route to large-scale STEM education? Science 323(5910):79\u201382","journal-title":"Science"},{"key":"14560_CR39","doi-asserted-by":"crossref","unstructured":"Newman JA (2013) Videogames. Routledge","DOI":"10.4324\/9780203143421"},{"issue":"1","key":"14560_CR40","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1038\/s43588-021-00185-x","volume":"2","author":"ND Nguyen","year":"2022","unstructured":"Nguyen ND, Huang J, Wang D (2022) A deep manifold-regularized learning model for improving phenotype prediction from multi-modal data. Nature Computational Science 2(1):38\u201346","journal-title":"Nature Computational Science"},{"issue":"1","key":"14560_CR41","doi-asserted-by":"publisher","first-page":"4","DOI":"10.5334\/tismir.10","volume":"1","author":"S Oramas","year":"2018","unstructured":"Oramas S, Barbieri F, Nieto O, Serra X (2018) Multimodal deep learning for music genre classification. Transactions of the international society for music information retrieval 2018 1(1):4\u201321","journal-title":"Transactions of the international society for music information retrieval 2018"},{"key":"14560_CR42","unstructured":"Oramas S, Espinosa-Anke L, Lawlor A (2016) Exploring Customer reviews for music genre classification and evolutionary studies. In: The 17th international society for music information retrieval conference (ISMIR 2016), New York City, United States of America, 7\u201311 August 2016"},{"key":"14560_CR43","unstructured":"Oramas S, Nieto O, Barbieri F, Serra X (2017) Multi-label music genre classification from audio, text, and images using deep features. arXiv:1707.04916"},{"key":"14560_CR44","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"issue":"1","key":"14560_CR45","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/JBHI.2016.2636665","volume":"21","author":"D Rav\u00ec","year":"2016","unstructured":"Rav\u00ec D, Wong C, Deligianni F, Berthelot M, Andreu-Perez J, Lo B, Yang GZ (2016) Deep learning for health informatics. IEEE J Biomed Health Inform 21(1):4\u201321","journal-title":"IEEE J Biomed Health Inform"},{"key":"14560_CR46","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"14560_CR47","doi-asserted-by":"crossref","unstructured":"Sahu S, Mitra V, Seneviratne N, Espy-Wilson CY (2019, September) Multi-Modal Learning for speech emotion recognition: an analysis and comparison of ASR outputs with ground truth transcription. In: Interspeech, pp 3302\u20133306","DOI":"10.21437\/Interspeech.2019-1149"},{"key":"14560_CR48","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1146\/annurev-bioeng-071516-044442","volume":"19","author":"D Shen","year":"2017","unstructured":"Shen D, Wu G, Suk HI (2017) Deep learning in medical image analysis. Annu Rev Biomed Eng 19:221\u2013248","journal-title":"Annu Rev Biomed Eng"},{"issue":"1","key":"14560_CR49","first-page":"49","volume":"2","author":"K Squire","year":"2003","unstructured":"Squire K (2003) Video games in education. Int J Intell Games Simulation 2(1):49\u201362","journal-title":"Int J Intell Games Simulation"},{"key":"14560_CR50","doi-asserted-by":"crossref","unstructured":"Strubell E, Ganesh A, Mccallum A (2019) Energy and policy considerations for deep learning in NLP. arXiv: 1906.02243","DOI":"10.18653\/v1\/P19-1355"},{"key":"14560_CR51","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"14560_CR52","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v31i1.11231"},{"issue":"1","key":"14560_CR53","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1109\/TCDS.2018.2866587","volume":"11","author":"L Tang","year":"2018","unstructured":"Tang L, Yang ZX, Jia K (2018) Canonical correlation analysis regularization: an effective deep multiview learning baseline for RGB-d object recognition. IEEE Transactions on Cognitive and Developmental Systems 11(1):107\u2013118","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"issue":"5","key":"14560_CR54","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TSA.2002.800560","volume":"10","author":"G Tzanetakis","year":"2002","unstructured":"Tzanetakis G, Cook P (2002) Musical genre classification of audio signals. IEEE Transactions on Speech and Audio Processing 10(5):293\u2013302","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"14560_CR55","doi-asserted-by":"crossref","unstructured":"Zhang W, Lei W, Xu X, Xing X (2016, September) Improved music genre classification with convolutional neural networks. In: Interspeech, pp 3304\u20133308","DOI":"10.21437\/Interspeech.2016-1236"},{"key":"14560_CR56","unstructured":"Zhang Z, Cui P, Zhu W (2020) Deep learning on graphs: a survey. IEEE Transactions on Knowledge and Data Engineering"},{"issue":"2","key":"14560_CR57","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1016\/j.acha.2019.06.004","volume":"48","author":"DX Zhou","year":"2020","unstructured":"Zhou DX (2020) Universality of deep convolutional neural networks. Appl Comput Harmon Anal 48(2):787\u2013794","journal-title":"Appl Comput Harmon Anal"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14560-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-14560-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14560-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T09:25:09Z","timestamp":1685006709000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-14560-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,17]]},"references-count":57,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["14560"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-14560-5","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,17]]},"assertion":[{"value":"12 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}