{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T04:46:27Z","timestamp":1772772387392,"version":"3.50.1"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["PID2020-120311RB-I00"],"award-info":[{"award-number":["PID2020-120311RB-I00"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR202211180156"],"award-info":[{"award-number":["ZR202211180156"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-19654-2","type":"journal-article","created":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T07:03:26Z","timestamp":1718694206000},"page":"14915-14939","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Audio-visual scene recognition using attention-based graph convolutional model"],"prefix":"10.1007","volume":"84","author":[{"given":"Ziqi","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yikai","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7805-3629","authenticated-orcid":false,"given":"Wenjuan","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"and Jordi","family":"Gonz\u00e0lez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,18]]},"reference":[{"key":"19654_CR1","doi-asserted-by":"publisher","first-page":"108580","DOI":"10.1016\/j.knosys.2022.108580","volume":"244","author":"AI Middya","year":"2022","unstructured":"Middya AI, Nag B, Roy S (2022) Deep learning based multimodal emotion recognition using model-level fusion of audio-visual modalities. Knowl-Based Syst 244:108580","journal-title":"Knowl-Based Syst"},{"key":"19654_CR2","doi-asserted-by":"crossref","unstructured":"Ye, M., You, Q., Ma, F.: Qualifier: Question-guided self-attentive multimodal fusion network for audio visual scene-aware dialog. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), 248\u2013256 (2022)","DOI":"10.1109\/WACV51458.2022.00256"},{"key":"19654_CR3","unstructured":"Akbari M, Karaman S (2019) Deep multimodal representation learning for robust scene understanding. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), 4137\u20134146"},{"key":"19654_CR4","unstructured":"Zhao H, Xiong Y, Shao L (2018) Audio-visual scene recognition with multimodal attention fusion. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 1092\u20131100"},{"key":"19654_CR5","doi-asserted-by":"crossref","unstructured":"Owens A, Efros AA (2018) Audio-visual scene analysis with self-supervised multisensory features. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 631\u2013648","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"19654_CR6","unstructured":"Dai W (2016) Acoustic scene recognition with deep learning. Detection and classification of acoustic scenes and events (DCASE) challenge. Carnegie Mellon University, Pittsburg, Pennsylvania, USA"},{"key":"19654_CR7","doi-asserted-by":"crossref","unstructured":"Owens A, Efros AA (2018) Audio-visual scene analysis with self-supervised multisensory features. Proceedings of the European conference on computer vision (ECCV), 631\u2013648","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"19654_CR8","doi-asserted-by":"crossref","unstructured":"Chen Y, Xian Y, Koepke A, Shan Y, Akata Z (2021) Distilling audio-visual knowledge by compositional contrastive learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7016\u20137025","DOI":"10.1109\/CVPR46437.2021.00694"},{"key":"19654_CR9","doi-asserted-by":"crossref","unstructured":"Zhu H, Weibel J-B, Lu S (2016) Discriminative multi-modal feature fusion for rgbd indoor scene recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2969\u20132976","DOI":"10.1109\/CVPR.2016.324"},{"key":"19654_CR10","unstructured":"Rahman MA, et al (2019) Deep multimodal fusion for audio-visual scene recognition. Proc ACM Int Conf Multimed"},{"key":"19654_CR11","unstructured":"Li Y, Vasconcelos N, Morency L-P (2019) Gcn for multimodal scene understanding from audio and vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"19654_CR12","unstructured":"Gao P, Zhang H, Xia ST, Li X (2020) Multi-modal graph convolutional networks for audio-visual scene recognition. Neurocomputing, 244\u2013253"},{"key":"19654_CR13","unstructured":"Kim W, Son B, Kim I (2021) ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"},{"key":"19654_CR14","doi-asserted-by":"crossref","unstructured":"Tao Z, Wei Y, Wang X, He X, Huang X, Chua T-S (2020) Mgat: Multimodal graph attention network for recommendation. Information Processing & Management, 102277","DOI":"10.1016\/j.ipm.2020.102277"},{"key":"19654_CR15","unstructured":"Rana A, Jha S (2022) Emotion based hate speech detection using multimodal learning. arXiv:2202.06218"},{"key":"19654_CR16","doi-asserted-by":"crossref","unstructured":"Abdullah SMSA, Ameen SYA, M\u00a0Sadeeq MA, Zeebaree S (2021) Multimodal emotion recognition using deep learning. Journal of Applied Science and Technology Trends (JASTT), 52\u201358","DOI":"10.38094\/jastt20291"},{"key":"19654_CR17","unstructured":"Lee J, Kim S, Lee K (2018) Listen to dance: Music-driven choreography generation using autoregressive encoder-decoder network. arXiv:1811.00818"},{"key":"19654_CR18","doi-asserted-by":"crossref","unstructured":"Yu W, Xu H, Yuan Z, Wu J (2021) Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 10790\u201310797","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"19654_CR19","unstructured":"Tran TN, Li Z, Bui T-D, Phung DQ (2019) Multimodal scene analysis: Algorithms and systems\u2013a literature survey. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 1\u201332"},{"key":"19654_CR20","unstructured":"Zhang J, Wu Y, Wang X, Tang S (2018) Multimodal scene classification with semantic hierarchy. IEEE Trans Multimedia, 84\u201395"},{"key":"19654_CR21","unstructured":"Huang X, Liu C, Jiang W (2020) A survey on multimodal scene analysis: Audio, visual, and beyond. ACM Computing Surveys (CSUR), 1\u201336"},{"key":"19654_CR22","doi-asserted-by":"crossref","unstructured":"Tang S, Luo Z, Nan G, Baba J, Yoshikawa Y, Ishiguro H (2022) Fusion with hierarchical graphs for multimodal emotion recognition. 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 1288\u20131296","DOI":"10.23919\/APSIPAASC55919.2022.9979932"},{"key":"19654_CR23","doi-asserted-by":"crossref","unstructured":"Liu X, Xu Z, Huang K, et al (2023) Multimodal emotion recognition based on cascaded multichannel and hierarchical fusion. Comput Intell Neurosci","DOI":"10.1155\/2023\/9645611"},{"key":"19654_CR24","doi-asserted-by":"crossref","unstructured":"Paier W, Hilsmann A, Eisert P (2020) Neural face models for example-based visual speech synthesis. Proceedings of the 17th ACM SIGGRAPH European Conference on Visual Media Production, 1\u201310","DOI":"10.1145\/3429341.3429356"},{"key":"19654_CR25","unstructured":"Mira R, Haliassos A, Petridis S, Schuller BW, Pantic M (2022) Svts: scalable video-to-speech synthesis. arXiv:2205.02058"},{"key":"19654_CR26","unstructured":"Liu F, Qian X, Jiao L, Zhang X, Li L, Cui Y (2022) Contrastive learning-based dual dynamic gcn for sar image scene classification. IEEE Trans Neural Netw Learn Syst, 1\u201315"},{"key":"19654_CR27","doi-asserted-by":"crossref","unstructured":"Zhang W, Tang P, Zhao L (2019) Remote sensing image scene classification using cnn-capsnet. Remote Sensing, 2072\u20134292","DOI":"10.3390\/rs11050494"},{"key":"19654_CR28","doi-asserted-by":"crossref","unstructured":"Khan A, Chefranov A, Demirel H (2023) Building discriminative features of scene recognition using multi-stages of inception-resnet-v2. Applied Intelligence, 1\u201319","DOI":"10.1007\/s10489-023-04460-4"},{"key":"19654_CR29","doi-asserted-by":"crossref","unstructured":"Abrol V, Sharma P (2020) Learning hierarchy aware embedding from raw audio for acoustic scene classification. IEEE\/ACM Trans Audio Speech Lang Process, 1964\u20131973","DOI":"10.1109\/TASLP.2020.3001969"},{"key":"19654_CR30","unstructured":"Zhao M, Liu S, Liu X, Liu J, Chen Z, Li Y (2019) Environmental sound classification using a hybrid deep neural network. Applied Sciences, 4944"},{"key":"19654_CR31","doi-asserted-by":"crossref","unstructured":"Wu P, Liu J, Shi Y, Sun Y, Shao F, Wu Z, Yang Z (2020) Not only look, but also listen: Learning multimodal violence detection under weak supervision. Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, 23\u201328 August 2020, Proceedings, Part XXX 16, 322\u2013339","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"19654_CR32","doi-asserted-by":"crossref","unstructured":"Sultani, W, Chen C, Shah M (2018) Real-world anomaly detection in surveillance videos. Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 6479\u20136488","DOI":"10.1109\/CVPR.2018.00678"},{"key":"19654_CR33","doi-asserted-by":"crossref","unstructured":"Hu D, Li X, Mou L, Jin, P, Chen D, Jing L, Zhu X, Dou D (2020) Cross-task transfer for geotagged audiovisual aerial scene recognition. Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, 23\u201328 August 2020, Proceedings, Part XXIV 16, 68\u201384","DOI":"10.1007\/978-3-030-58586-0_5"},{"key":"19654_CR34","doi-asserted-by":"crossref","unstructured":"Yu J, Cheng Y, Feng R (2021) Mpn: Multimodal parallel network for audio-visual event localization. 2021 IEEE International Conference on Multimedia and Expo (ICME), 1\u20136","DOI":"10.1109\/ICME51207.2021.9428373"},{"key":"19654_CR35","doi-asserted-by":"crossref","unstructured":"Ramaswamy J (2020) What makes the sound?: A dual-modality interacting network for audio-visual event localization. ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4372\u20134376","DOI":"10.1109\/ICASSP40776.2020.9053895"},{"key":"19654_CR36","doi-asserted-by":"crossref","unstructured":"Khan A, Chefranov A, Demirel H (2023) Building discriminative features of scene recognition using multi-stages of inception-resnet-v2. Applied Intelligence, 18431\u201318449","DOI":"10.1007\/s10489-023-04460-4"},{"key":"19654_CR37","doi-asserted-by":"publisher","first-page":"121685","DOI":"10.1109\/ACCESS.2019.2936215","volume":"7","author":"C Ma","year":"2019","unstructured":"Ma C, Mu X, Sha D (2019) Multi-layers feature fusion of convolutional neural network for scene classification of remote sensing. IEEE Access 7:121685\u2013121694","journal-title":"IEEE Access"},{"key":"19654_CR38","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1016\/j.neucom.2016.11.023","volume":"225","author":"P Tang","year":"2017","unstructured":"Tang P, Wang H, Kwong S (2017) G-ms2f: Googlenet based multi-stage feature fusion of deep cnn for scene recognition. Neurocomputing 225:188\u2013197","journal-title":"Neurocomputing"},{"key":"19654_CR39","unstructured":"Wang Y, Huang W, Sun F, Xu T, Rong Y, Huang J (2019) Deep multimodal fusion by channel exchanging. Adv Neural Inf Process Syst , 4835\u20134845"},{"key":"19654_CR40","unstructured":"Lee J, Kim S, Lee K (2018) Listen to dance: Music-driven choreography generation using autoregressive encoder-decoder network. arXiv:1811.00818"},{"key":"19654_CR41","doi-asserted-by":"crossref","unstructured":"Brousmiche M, Rouat J, Dupont S (2019) Audio-visual fusion and conditioning with neural networks for event recognition. 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP), 1\u20136","DOI":"10.1109\/MLSP.2019.8918712"},{"key":"19654_CR42","unstructured":"Zhao T, Eskenazi M (2019) Multimodal dialogue generation with hierarchical latent variables. Proceedings of the AAAI Conference on Artificial Intelligence, 6902\u20136909"},{"key":"19654_CR43","doi-asserted-by":"crossref","unstructured":"Nie W, Ren M, Nie J, Zhao S (2021) C-gcn: Correlation based graph convolutional network for audio-video emotion recognition. IEEE Trans Multimedia, 3793\u20133804","DOI":"10.1109\/TMM.2020.3032037"},{"key":"19654_CR44","doi-asserted-by":"crossref","unstructured":"Wu B, Lang B (2023) Msgcn: a multiscale spatio graph convolution network for 3d point clouds. Multimed Tools Appl, 1\u201320","DOI":"10.1007\/s11042-023-14639-z"},{"key":"19654_CR45","doi-asserted-by":"crossref","unstructured":"Duhme M, Memmesheimer R, Paulus D (2021) Fusion-gcn: Multimodal action recognition using graph convolutional networks. DAGM German Conference on Pattern Recognition, 265\u2013281","DOI":"10.1007\/978-3-030-92659-5_17"},{"key":"19654_CR46","doi-asserted-by":"crossref","unstructured":"Yuan Y, Xiong Z, Wang Q (2019) Acm: Adaptive cross-modal graph convolutional neural networks for rgb-d scene recognition. Proceedings of the AAAI conference on artificial intelligence, 9176\u20139184","DOI":"10.1609\/aaai.v33i01.33019176"},{"key":"19654_CR47","doi-asserted-by":"crossref","unstructured":"Li Y, Zhang J, Cheng Y, Huang K, Tan T (2018) Df 2 net: Discriminative feature learning and fusion network for rgb-d indoor scene classification. Proceedings of the AAAI Conference on Artificial Intelligence 32(1)","DOI":"10.1609\/aaai.v32i1.12292"},{"key":"19654_CR48","doi-asserted-by":"crossref","unstructured":"Song X, Chen C, Jiang S (2017) Rgb-d scene recognition with object-to-object relation. Proceedings of the 25th ACM Int Conf Multimed, 600\u2013608","DOI":"10.1145\/3123266.3123300"},{"key":"19654_CR49","doi-asserted-by":"crossref","unstructured":"Zhu Q, Deng H (2023) Spatial adaptive graph convolutional network for skeleton-based action recognition. Appl Intell, 17796\u201317808","DOI":"10.1007\/s10489-022-04442-y"},{"key":"19654_CR50","doi-asserted-by":"crossref","unstructured":"Shi L, Zhang Y, Cheng J, Lu H (2020) Skeleton-based action recognition with multi-stream adaptive graph convolutional networks. IEEE Trans Image Process, 9532\u20139545","DOI":"10.1109\/TIP.2020.3028207"},{"key":"19654_CR51","doi-asserted-by":"crossref","unstructured":"Zhang L, Yuan F, Xia X (2023) Edge-reinforced attention network for smoke semantic segmentation. Multimed Tools Appl, 1\u201326","DOI":"10.1007\/s11042-023-14879-z"},{"key":"19654_CR52","doi-asserted-by":"crossref","unstructured":"Potluri T, K VKK (2023) An automated online proctoring system using attentive-net to assess student mischievous behavior. Multimed Tools Appl, 1\u201330","DOI":"10.1007\/s11042-023-14604-w"},{"key":"19654_CR53","doi-asserted-by":"crossref","unstructured":"Ye M, You Q, Ma F (2022) Qualifier: Question-guided self-attentive multimodal fusion network for audio visual scene-aware dialog. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), 248\u2013256","DOI":"10.1109\/WACV51458.2022.00256"},{"key":"19654_CR54","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-J (2002) Bleu: a method for automatic evaluation of machine translation. Proceedings of the 40th annual meeting of the Association for Computational Linguistics (ACL), 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"key":"19654_CR55","doi-asserted-by":"crossref","unstructured":"Brousmiche M, Rouat J, Dupont S (2022) Multimodal attentive fusion network for audio-visual event recognition. Information Fusion, 52\u201359","DOI":"10.1016\/j.inffus.2022.03.001"},{"key":"19654_CR56","doi-asserted-by":"crossref","unstructured":"Tian Y, Shi J, Li B, Duan Z, Xu C (2018) Audio-visual event localization in unconstrained videos. Proceedings of the European conference on computer vision (ECCV), 247\u2013263","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"19654_CR57","doi-asserted-by":"crossref","unstructured":"Li J, Wang X, Lv G, Zeng Z (2022) Graphmft: A graph attention based multimodal fusion technique for emotion recognition in conversation. arXiv:2208.00339","DOI":"10.1016\/j.neucom.2023.126427"},{"key":"19654_CR58","doi-asserted-by":"crossref","unstructured":"Hu J, Liu Y, Zhao J, Jin Q (2021) Mmgcn: Multimodal fusion via deep graph convolution network for emotion recognition in conversation. arXiv:2107.06779","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"19654_CR59","doi-asserted-by":"crossref","unstructured":"Wei Y, Wang X, Nie L, He X, Hong R, Chua T-S (2019) Mmgcn: Multi-modal graph convolution network for personalized recommendation of micro-video. Proceedings of the 27th ACM Int Conf Multimed, 1437\u20131445","DOI":"10.1145\/3343031.3351034"},{"key":"19654_CR60","doi-asserted-by":"crossref","unstructured":"Zhang Y, Wang J, Liu Y, Rong L, Zheng Q, Song D, Tiwari P, Qin J (2023) A multitask learning model for multimodal sarcasm, sentiment and emotion recognition in conversations. Information Fusion, 282\u2013301","DOI":"10.1016\/j.inffus.2023.01.005"},{"key":"19654_CR61","doi-asserted-by":"crossref","unstructured":"Liang B, Lou C, Li X, Yang M, Gui L, He Y, Pei W, Xu R (2022) Multi-modal sarcasm detection via cross-modal graph convolutional network. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 1767\u20131777","DOI":"10.18653\/v1\/2022.acl-long.124"},{"key":"19654_CR62","doi-asserted-by":"crossref","unstructured":"Chauhan DS, Dhanush S, Ekbal A, Bhattacharyya P (2020) Sentiment and emotion help sarcasm? a multi-task learning framework for multi-modal sarcasm, sentiment and emotion analysis. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), 4351\u20134360","DOI":"10.18653\/v1\/2020.acl-main.401"},{"key":"19654_CR63","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"key":"19654_CR64","unstructured":"Soomro K, Zamir AR, Shah M (2012) Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402"},{"key":"19654_CR65","doi-asserted-by":"crossref","unstructured":"Wu P, Liu J, Shi Y, Sun Y, Shao F, Wu Z, Yang Z (2020) Not only look, but also listen: Learning multimodal violence detection under weak supervision. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, 23\u201328 August 2020, Proceedings, Part XXX 16, Springer pp 322\u2013339","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"19654_CR66","doi-asserted-by":"crossref","unstructured":"Wang S, Mesaros A, Heittola T, Virtanen T (2021) A curated dataset of urban scenes for audio-visual scene analysis. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 626\u2013630 IEEE","DOI":"10.1109\/ICASSP39728.2021.9415085"},{"key":"19654_CR67","first-page":"1","volume":"72","author":"L Zhou","year":"2023","unstructured":"Zhou L, Zhou Y, Qi X, Hu J, Lam TL, Xu Y (2023) Attentional graph convolutional network for structure-aware audiovisual scene classification. IEEE Trans Instrum Meas 72:1\u201315","journal-title":"IEEE Trans Instrum Meas"},{"key":"19654_CR68","doi-asserted-by":"crossref","unstructured":"Piergiovanni A, Angelova A, Ryoo MS (2020) Evolving losses for unsupervised video representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pp 133\u2013142","DOI":"10.1109\/CVPR42600.2020.00021"},{"key":"19654_CR69","first-page":"9758","volume":"33","author":"H Alwassel","year":"2020","unstructured":"Alwassel H, Mahajan D, Korbar B, Torresani L, Ghanem B, Tran D (2020) Self-supervised learning by cross-modal audio-video clustering. Adv Neural Inf Process Syst 33:9758\u20139770","journal-title":"Adv Neural Inf Process Syst"},{"key":"19654_CR70","unstructured":"Patrick M, Asano Y, Kuznetsova P, Fong R, Henriques JF, Zweig G, Vedaldi A (2020) Multi-modal self-supervision from generalized data transformations"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19654-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-19654-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19654-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T11:15:59Z","timestamp":1747998959000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-19654-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,18]]},"references-count":70,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["19654"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-19654-2","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,18]]},"assertion":[{"value":"21 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 April 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 June 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 June 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"(check journal-specific guidelines for which heading to use): The researchers claim no conflicts of interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest\/Competing interests"}},{"value":"Not applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}}]}}