iBet uBet web content aggregator. Adding the entire web to your favor.
iBet uBet web content aggregator. Adding the entire web to your favor.



Link to original content: https://api.crossref.org/works/10.1007/S11042-023-17945-8
{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T00:23:19Z","timestamp":1717546999093},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"21","license":[{"start":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T00:00:00Z","timestamp":1703808000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T00:00:00Z","timestamp":1703808000000},"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"],"DOI":"10.1007\/s11042-023-17945-8","type":"journal-article","created":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T05:02:45Z","timestamp":1703826165000},"page":"59577-59595","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Integrating multimodal features by a two-way co-attention mechanism for visual question answering"],"prefix":"10.1007","volume":"83","author":[{"given":"Himanshu","family":"Sharma","sequence":"first","affiliation":[]},{"given":"Swati","family":"Srivastava","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,29]]},"reference":[{"key":"17945_CR1","volume":"23","author":"C Zhang","year":"2021","unstructured":"Zhang C, Lu Y (2021) Study on artificial intelligence: the state of the art and future prospects. J Ind Inf Integr 23:100224","journal-title":"J Ind Inf Integr"},{"issue":"1\u20134","key":"17945_CR2","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1080\/13682199.2022.2153489","volume":"69","author":"H Sharma","year":"2021","unstructured":"Sharma H, Srivastava S (2021) Visual question-answering model based on the fusion of multimodal features by a two-way co-attention mechanism. Imaging Sci J 69(1\u20134):177\u2013189","journal-title":"Imaging Sci J"},{"key":"17945_CR3","doi-asserted-by":"crossref","unstructured":"Bhatt D, Patel C, Talsania H, Patel J, Vaghela R, Pandya S, ..., Ghayvat H (2021) CNN variants for computer vision: history, architecture, application, challenges, and future scope. Electronics 10(20):2470","DOI":"10.3390\/electronics10202470"},{"key":"17945_CR4","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28, Montreal Convention Center, Montreal, Canada, December 7\u201310"},{"key":"17945_CR5","unstructured":"Schwartz I, Schwing A, Hazan T (2017) High-order attention models for visual question answering. Advances in Neural Information Processing Systems, 30. Long Beach, California, USA, December 4\u20139, 3667\u20133677"},{"key":"17945_CR6","volume":"96","author":"Y Wu","year":"2021","unstructured":"Wu Y, Ma Y, Wan S (2021) Multi-scale relation reasoning for multi-modal visual question answering. Signal Process: Image Commun 96:116319","journal-title":"Signal Process: Image Commun"},{"key":"17945_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.inffus.2021.02.022","volume":"73","author":"S Zhang","year":"2021","unstructured":"Zhang S, Chen M, Chen J, Zou F, Li YF, Lu P (2021) Multimodal feature-wise co-attention method for visual question answering. Information Fusion 73:1\u201310","journal-title":"Information Fusion"},{"key":"17945_CR8","doi-asserted-by":"crossref","unstructured":"Dey R, Salem FM (2017) Gate-variants of gated recurrent unit (GRU) neural networks. In: 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS). IEEE, pp 1597\u20131600","DOI":"10.1109\/MWSCAS.2017.8053243"},{"key":"17945_CR9","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.neucom.2021.10.016","volume":"467","author":"H Zhan","year":"2022","unstructured":"Zhan H, Xiong P, Wang X, Xin WANG, Yang L (2022) Visual question answering by pattern matching and reasoning. Neurocomputing 467:323\u2013336","journal-title":"Neurocomputing"},{"key":"17945_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108153","volume":"120","author":"W Zheng","year":"2021","unstructured":"Zheng W, Yin L, Chen X, Ma Z, Liu S, Yang B (2021) Knowledge base graph embedding module design for visual question answering model. Pattern Recogn 120:108153","journal-title":"Pattern Recogn"},{"key":"17945_CR11","doi-asserted-by":"publisher","first-page":"6730","DOI":"10.1109\/TIP.2021.3097180","volume":"30","author":"W Guo","year":"2021","unstructured":"Guo W, Zhang Y, Yang J, Yuan X (2021) Re-attention for visual question answering. IEEE Trans Image Process 30:6730\u20136743","journal-title":"IEEE Trans Image Process"},{"key":"17945_CR12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2020.3040221","volume":"60","author":"X Zheng","year":"2021","unstructured":"Zheng X, Wang B, Du X, Lu X (2021) Mutual attention inception network for remote sensing visual question answering. IEEE Trans Geosci Remote Sens 60:1\u201314","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"17945_CR13","doi-asserted-by":"crossref","unstructured":"Yang Z, He X, Gao J, Deng L, Smola A (2016) Stacked attention networks for image question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, Nevada, June 26-July 1, 21\u201329","DOI":"10.1109\/CVPR.2016.10"},{"key":"17945_CR14","unstructured":"Ilievski I, Yan S, Feng J (2016) A focused dynamic attention model for visual question answering. arXiv preprint arXiv:1604.01485"},{"key":"17945_CR15","unstructured":"Lu J, Yang J, Batra D, Parikh D (2016) Hierarchical question-image co-attention for visual question answering. Advances in neural information processing systems, 29, Barcelona, Spain, December 5\u201310, 289\u2013297"},{"issue":"11","key":"17945_CR16","doi-asserted-by":"publisher","first-page":"16247","DOI":"10.1007\/s11042-020-08790-0","volume":"80","author":"X Zhu","year":"2021","unstructured":"Zhu X, Mao Z, Chen Z, Li Y, Wang Z, Wang B (2021) Object-difference drived graph convolutional networks for visual question answering. Multimed Tools Appl 80(11):16247\u201316265","journal-title":"Multimed Tools Appl"},{"key":"17945_CR17","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/j.neucom.2018.11.102","volume":"391","author":"L Gao","year":"2020","unstructured":"Gao L, Cao L, Xu X, Shao J, Song J (2020) Question-led object attention for visual question answering. Neurocomputing 391:227\u2013233","journal-title":"Neurocomputing"},{"key":"17945_CR18","doi-asserted-by":"crossref","unstructured":"Singh A, Natarajan V, Shah M, Jiang Y, Chen X, Batra D, ..., Rohrbach M (2019) Towards vqa models that can read. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, June 16\u201320, 8317\u20138326","DOI":"10.1109\/CVPR.2019.00851"},{"key":"17945_CR19","doi-asserted-by":"crossref","unstructured":"Cadene R, Ben-Younes H, Cord M, Thome N (2019) Murel: multimodal relational reasoning for visual question answering. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, Long Beach, CA, June 16\u201320, 1989\u20131998","DOI":"10.1109\/CVPR.2019.00209"},{"key":"17945_CR20","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.inffus.2019.08.009","volume":"55","author":"W Zhang","year":"2020","unstructured":"Zhang W, Yu J, Hu H, Hu H, Qin Z (2020) Multimodal feature fusion by relational reasoning and attention for visual question answering. Information Fusion 55:116\u2013126","journal-title":"Information Fusion"},{"issue":"1","key":"17945_CR21","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/s11063-021-10655-y","volume":"54","author":"H Sharma","year":"2022","unstructured":"Sharma H, Jalal AS (2022) An improved attention and hybrid optimization technique for visual question answering. Neural Process Lett 54(1):709\u2013730","journal-title":"Neural Process Lett"},{"key":"17945_CR22","unstructured":"Zhang X, Wu C, Zhao Z, Lin W, Zhang Y, Wang Y, Xie W (2023) PMC-VQA: visual instruction tuning for medical visual question answering. arXiv preprint arXiv:2305.10415"},{"key":"17945_CR23","doi-asserted-by":"crossref","unstructured":"Jiang H, Misra I, Rohrbach M, Learned-Miller E, Chen X (2020) In defense of grid features for visual question answering. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 10267\u201310276","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"17945_CR24","doi-asserted-by":"crossref","unstructured":"Chen L, Yan X, Xiao J, Zhang H, Pu S, Zhuang Y (2020) Counterfactual samples synthesizing for robust visual question answering. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 10800\u201310809","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"17945_CR25","doi-asserted-by":"crossref","unstructured":"Sharma H,\u00a0 Jalal AS (2022) Image captioning improved visual question answering. Multimedia tools and applications 81(24):34775\u201334796","DOI":"10.1007\/s11042-021-11276-2"},{"key":"17945_CR26","doi-asserted-by":"crossref","unstructured":"Yu Z, Yu J, Cui Y, Tao D, Tian Q (2019) Deep modular co-attention networks for visual question answering. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 6281\u20136290","DOI":"10.1109\/CVPR.2019.00644"},{"key":"17945_CR27","doi-asserted-by":"crossref","unstructured":"Li L, Gan Z, Cheng Y, Liu J (2019) Relation-aware graph attention network for visual question answering. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp 10313\u201310322","DOI":"10.1109\/ICCV.2019.01041"},{"key":"17945_CR28","doi-asserted-by":"crossref","unstructured":"Krishna R, Zhu Y, Groth O, Johnson J, Hata K, Kravitz J, ..., Fei-Fei L (2017) Visual genome: connecting language and vision using crowdsourced dense image annotations. Int J Comput Vis 123(1):32\u201373","DOI":"10.1007\/s11263-016-0981-7"},{"key":"17945_CR29","doi-asserted-by":"crossref","unstructured":"Teney D, Anderson P, He X, Van Den Hengel A (2018) Tips and tricks for visual question answering: learnings from the 2017 challenge. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, Utah, June 18\u201322, 4223\u20134232","DOI":"10.1109\/CVPR.2018.00444"},{"key":"17945_CR30","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), association for computational linguistics, Doha, Qatar. 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"17945_CR31","doi-asserted-by":"crossref","unstructured":"Yang Z, He X, Gao J, Deng L, Smola A (2016) Stacked attention networks for image question answering. In: CVPR, pp 21\u201329","DOI":"10.1109\/CVPR.2016.10"},{"key":"17945_CR32","unstructured":"Lu J, Yang J, Batra D, Parikh D (2016) Hierarchical question-image co-attention for visual question answering. In: NIPS. pp 289\u2013297"},{"key":"17945_CR33","unstructured":"Kazemi V, Elqursh A (2017) Show, ask, attend, and answer: a strong baseline for visual question answering, arXiv:1704.03162v2"},{"key":"17945_CR34","doi-asserted-by":"crossref","unstructured":"Nguyen D, Okatani T (2018) Improved fusion of visual and language representations by dense symmetric co-attention for visual question answering. In: CVPR. pp 6087\u20136096","DOI":"10.1109\/CVPR.2018.00637"},{"key":"17945_CR35","unstructured":"Ramanan D, Pirsiavash H, Fowlkes C (2009) Bilinear classifiers for visual recognition. In: NIPS, pp 1482\u20131490"},{"issue":"12","key":"17945_CR36","doi-asserted-by":"publisher","first-page":"5947","DOI":"10.1109\/TNNLS.2018.2817340","volume":"29","author":"Z Yu","year":"2018","unstructured":"Yu Z, Yu J, Xiang C, Fan J, Tao D (2018) Beyond bilinear: generalized multimodal factorized high-order pooling for visual question answering. IEEE Trans Neural Netw Learn Syst 29(12):5947\u20135959","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"17945_CR37","unstructured":"O.K. Kim J., W. Lim, Hadamard product for low-rank bilinear pooling, ICLR, 2017."},{"key":"17945_CR38","doi-asserted-by":"publisher","unstructured":"Antol S, Agrawal A, Lu J, Mitchell M, Batra D, Zitnick CL, Parikh D (2015) VQA:visual question answering. In: Proc. IEEE Int. Conf. Computer Vision (ICCV). pp 2425\u20132433, https:\/\/doi.org\/10.1109\/ICCV.2015.279","DOI":"10.1109\/ICCV.2015.279"},{"key":"17945_CR39","doi-asserted-by":"publisher","unstructured":"Goyal Y, Khot T, Summers-Stay D, Batra D, Parikh D (2017) Making the v in VQA matter: elevating the role of image understanding in visual question answering. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR). pp 6325\u20136334. https:\/\/doi.org\/10.1109\/CVPR.2017.670","DOI":"10.1109\/CVPR.2017.670"},{"key":"17945_CR40","doi-asserted-by":"publisher","unstructured":"Lin T, Maire M, Belongie SJ, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft COCO: common objects in context. In: Fleet DJ, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision - ECCV 2014 - 13th European conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part V, in: Lecture Notes in Computer Science. Springer, vol. 8693, pp 740\u2013755. https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"17945_CR41","doi-asserted-by":"crossref","unstructured":"Hariharan B, Johnson J, Maaten L, Li F-F (2017) Clevr: a diagnostic dataset for compositional language and elementary visual reasoning. In: CVPR, pp 1988\u20131997","DOI":"10.1109\/CVPR.2017.215"},{"key":"17945_CR42","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"issue":"1","key":"17945_CR43","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2020.3004830","volume":"44","author":"L Peng","year":"2020","unstructured":"Peng L, Yang Y, Wang Z, Huang Z, Shen HT (2020) Mra-net: improving vqa via multi-modal relation attention network. IEEE Trans Pattern Anal Mach Intell 44(1):318\u2013329","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"17945_CR44","doi-asserted-by":"crossref","unstructured":"Zhou Y, Ren T, Zhu C, Sun X, Liu J, Ding X, ..., Ji R (2021) TRAR: routing the attention spans in transformer for visual question answering. In: Proceedings of the IEEE\/CVF international conference on computer vision, June 19\u201325, 2074\u20132084","DOI":"10.1109\/ICCV48922.2021.00208"},{"key":"17945_CR45","doi-asserted-by":"crossref","unstructured":"Nam H, Ha JW, Kim J (2017) Dual attention networks for multimodal reasoning and matching. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, Hawaii, July 21\u201326, 299\u2013307","DOI":"10.1109\/CVPR.2017.232"},{"key":"17945_CR46","unstructured":"Kazemi V, Elqursh A (2017) Show, ask, attend, and answer: a strong baseline for visual question answering. arXiv preprint arXiv:1704.03162"},{"key":"17945_CR47","doi-asserted-by":"crossref","unstructured":"Yu D, Fu J, Mei T, Rui Y (2017) Multi-level attention networks for visual question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, Hawaii, July 21\u201326, 4709\u20134717","DOI":"10.1109\/CVPR.2017.446"},{"key":"17945_CR48","doi-asserted-by":"crossref","unstructured":"Wang P, Wu Q, Shen C, van den Hengel A (2017) The vqa-machine: learning how to use existing vision algorithms to answer new questions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, Hawaii, July 21\u201326, 1173\u20131182","DOI":"10.1109\/CVPR.2017.416"},{"key":"17945_CR49","doi-asserted-by":"crossref","unstructured":"Nguyen DK, Okatani T (2018) Improved fusion of visual and language representations by dense symmetric co-attention for visual question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, Utah, June 18\u201322, 6087\u20136096","DOI":"10.1109\/CVPR.2018.00637"},{"issue":"2s","key":"17945_CR50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3316767","volume":"15","author":"D Yu","year":"2019","unstructured":"Yu D, Fu J, Tian X, Mei T (2019) Multi-source multi-level attention networks for visual question answering. ACM Trans Multimed Comput Commun Appl (TOMM) 15(2s):1\u201320","journal-title":"ACM Trans Multimed Comput Commun Appl (TOMM)"},{"key":"17945_CR51","doi-asserted-by":"crossref","unstructured":"Liu Y, Zhang X, Zhao Z, Zhang B, Cheng L, Li Z (2020) ALSA: adversarial learning of supervised attentions for visual question answering.\u00a0IEEE Trans Cybern\u00a052(6):4520\u20134533","DOI":"10.1109\/TCYB.2020.3029423"},{"key":"17945_CR52","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106339","volume":"207","author":"Y Liu","year":"2020","unstructured":"Liu Y, Zhang X, Huang F, Zhou Z, Zhao Z, Li Z (2020) Visual question answering via combining inferential attention and semantic space mapping. Knowl-Based Syst 207:106339","journal-title":"Knowl-Based Syst"},{"key":"17945_CR53","doi-asserted-by":"crossref","unstructured":"Peng L, Yang Y, Zhang X, Ji Y, Lu H, Shen HT (2020) Answer again: improving VQA with cascaded-answering model. IEEE\u00a0Trans Knowl Data Eng\u00a034(4):1644\u20131655","DOI":"10.1109\/TKDE.2020.2998805"},{"key":"17945_CR54","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1016\/j.patrec.2020.02.031","volume":"133","author":"W Li","year":"2020","unstructured":"Li W, Sun J, Liu G, Zhao L, Fang X (2020) Visual question answering with attention transfer and a cross-modal gating mechanism. Pattern Recogn Lett 133:334\u2013340","journal-title":"Pattern Recogn Lett"},{"key":"17945_CR55","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104165","volume":"110","author":"H Sharma","year":"2021","unstructured":"Sharma H, Jalal AS (2021) Visual question answering model based on graph neural network and contextual attention. Image Vis Comput 110:104165","journal-title":"Image Vis Comput"},{"key":"17945_CR56","doi-asserted-by":"crossref","unstructured":"Sharma H, Jalal AS (2022) Image captioning improved visual question answering. Multimed Tools Appl 81(24):34775\u201334796","DOI":"10.1007\/s11042-021-11276-2"},{"key":"17945_CR57","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.neunet.2021.02.001","volume":"139","author":"JJ Kim","year":"2021","unstructured":"Kim JJ, Lee DG, Wu J, Jung HG, Lee SW (2021) Visual question answering based on local-scene-aware referring expression generation. Neural Netw 139:158\u2013167","journal-title":"Neural Netw"},{"key":"17945_CR58","unstructured":"Guo D, Xu C, Tao D (2021) Bilinear graph networks for visual question answering. IEEE\u00a0Trans Neural Netw Learn Syst"},{"key":"17945_CR59","doi-asserted-by":"crossref","unstructured":"Yang X, Gao C, Zhang H, Cai J (2021) Auto-parsing network for image captioning and visual question answering. In: Proceedings of the IEEE\/CVF international conference on computer vision, June 19\u201325 (pp. 2197\u20132207)","DOI":"10.1109\/ICCV48922.2021.00220"},{"key":"17945_CR60","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116159","volume":"190","author":"H Sharma","year":"2022","unstructured":"Sharma H, Jalal AS (2022) A framework for visual question answering with the integration of scene-text using PHOCs and fisher vectors. Expert Syst Appl 190:116159","journal-title":"Expert Syst Appl"},{"key":"17945_CR61","doi-asserted-by":"crossref","unstructured":"Sharma H, Jalal AS (2022) Improving visual question answering by combining scene-text information. Multimed Tools Appl 81(9):12177\u201312208","DOI":"10.1007\/s11042-022-12317-0"},{"key":"17945_CR62","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1016\/j.patrec.2021.09.008","volume":"151","author":"S Barra","year":"2021","unstructured":"Barra S, Bisogni C, De Marsico M, Ricciardi S (2021) Visual question answering: which investigated applications? Pattern Recogn Lett 151:325\u2013331","journal-title":"Pattern Recogn Lett"},{"issue":"1","key":"17945_CR63","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1109\/TCSS.2021.3102591","volume":"9","author":"H Gao","year":"2021","unstructured":"Gao H, Xu K, Cao M, Xiao J, Xu Q, Yin Y (2021) The deep features and attention mechanism-based method to dish healthcare under social iot systems: an empirical study with a hand-deep local\u2013global net. IEEE Trans Comput Soc Syst 9(1):336\u2013347","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"17945_CR64","unstructured":"Gao H, Xiao J, Yin Y, Liu T, Shi J (2022) A mutually supervised graph attention network for few-shot segmentation: the perspective of fully utilizing limited samples. IEEE\u00a0Trans Neural Netw Learn Syst"},{"issue":"1s","key":"17945_CR65","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3419842","volume":"17","author":"J Xiao","year":"2021","unstructured":"Xiao J, Xu H, Gao H, Bian M, Li Y (2021) A weakly supervised semantic segmentation network by aggregating seed cues: the multi-object proposal generation perspective. ACM Trans Multimed Comput Commun Appl 17(1s):1\u201319","journal-title":"ACM Trans Multimed Comput Commun Appl"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17945-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-17945-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17945-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T04:02:50Z","timestamp":1717473770000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-17945-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,29]]},"references-count":65,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["17945"],"URL":"http:\/\/dx.doi.org\/10.1007\/s11042-023-17945-8","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,29]]},"assertion":[{"value":"22 May 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 October 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 December 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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}