{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:45:40Z","timestamp":1780501540296,"version":"3.54.1"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"32","license":[{"start":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T00:00:00Z","timestamp":1708905600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T00:00:00Z","timestamp":1708905600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61733013,62073245"],"award-info":[{"award-number":["61733013,62073245"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-18382-x","type":"journal-article","created":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T06:02:10Z","timestamp":1708927330000},"page":"77529-77547","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Joint self-supervised learning of interest point, descriptor, depth, and ego-motion from monocular video"],"prefix":"10.1007","volume":"83","author":[{"given":"Zhongyi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengjiao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qijun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,26]]},"reference":[{"key":"18382_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal S, Snavely N, Seitz SM, Szeliski R (2010) Bundle adjustment in the large. In: European conference on computer vision, Springer, pp 29\u201342","DOI":"10.1007\/978-3-642-15552-9_3"},{"key":"18382_CR2","doi-asserted-by":"crossref","unstructured":"Cadena C, Carlone L, Carrillo H, Latif Y, Scaramuzza D, Neira J, Reid I, Leonard JJ (2016) Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age. IEEE Trans Robot 32(6):1309\u20131332","DOI":"10.1109\/TRO.2016.2624754"},{"issue":"2","key":"18382_CR3","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91\u2013110","journal-title":"Int J Comput Vis"},{"key":"18382_CR4","doi-asserted-by":"crossref","unstructured":"Bian J, Lin W.-Y, Matsushita Y, Yeung S-K, Nguyen T-D, Cheng M-M (2017) Gms: Grid-based motion statistics for fast, ultra-robust feature correspondence. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4181\u20134190","DOI":"10.1109\/CVPR.2017.302"},{"key":"18382_CR5","doi-asserted-by":"crossref","unstructured":"Hartley R, Zisserman A (2003) Multiple View Geometry in Computer Vision. Cambridge university press, ???","DOI":"10.1017\/CBO9780511811685"},{"key":"18382_CR6","doi-asserted-by":"crossref","unstructured":"Sarlin P-E, Cadena C, Siegwart R, Dymczyk M (2019) From coarse to fine: Robust hierarchical localization at large scale. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12716\u201312725","DOI":"10.1109\/CVPR.2019.01300"},{"key":"18382_CR7","unstructured":"ZhaoC TangY (2021) SunQ. VasilakosA.V Deep direct visual odometry. IEEE Trans Intell Transp Syst"},{"key":"18382_CR8","doi-asserted-by":"crossref","unstructured":"Tateno K, Tombari F, Laina I, Navab N (2017) Cnn-slam: Real-time dense monocular slam with learned depth prediction. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6243\u20136252","DOI":"10.1109\/CVPR.2017.695"},{"key":"18382_CR9","unstructured":"Vijayanarasimhan S, Ricco S, Schmid C, Sukthankar R, Fragkiadaki K (2017) Sfm-net: Learning of structure and motion from video. arXiv preprint arXiv:1704.07804"},{"key":"18382_CR10","doi-asserted-by":"crossref","unstructured":"Wang S Clark R Wen H, Trigoni N (2018) End-to-end, sequence-to-sequence probabilistic visual odometry through deep neural networks. Int J Rob Res 37(4\u20135):513\u2013542","DOI":"10.1177\/0278364917734298"},{"key":"18382_CR11","doi-asserted-by":"crossref","unstructured":"DeTone D, Malisiewicz T, Rabinovich A (2018) Superpoint: Self-supervised interest point detection and description. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 224\u2013236","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"18382_CR12","unstructured":"Christiansen PH, Kragh MF, Brodskiy Y, Karstoft H (2019) Unsuperpoint: End-to-end unsupervised interest point detector and descriptor. arXiv preprint arXiv:1907.04011"},{"key":"18382_CR13","unstructured":"Revaud J, Weinzaepfel P, De\u00a0Souza C, Pion N, Csurka G, Cabon Y, Humenberger M (2019) R2d2: repeatable and reliable detector and descriptor. arXiv preprint arXiv:1906.06195"},{"key":"18382_CR14","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"18382_CR15","doi-asserted-by":"crossref","unstructured":"Zhou T, Brown M, Snavely N, Lowe DG (2017) Unsupervised learning of depth and ego-motion from video. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1851\u20131858","DOI":"10.1109\/CVPR.2017.700"},{"key":"18382_CR16","doi-asserted-by":"crossref","unstructured":"Yin Z, Shi J (2018) Geonet: Unsupervised learning of dense depth, optical flow and camera pose. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1983\u20131992","DOI":"10.1109\/CVPR.2018.00212"},{"key":"18382_CR17","doi-asserted-by":"crossref","unstructured":"Zou Y, Luo Z, Huang J-B (2018) Df-net: Unsupervised joint learning of depth and flow using cross-task consistency. In: Proceedings of the European conference on computer vision (ECCV), pp 36\u201353","DOI":"10.1007\/978-3-030-01228-1_3"},{"key":"18382_CR18","doi-asserted-by":"crossref","unstructured":"Ranjan A, Jampani V, Balles L, Kim K, Sun D, Wulff J, Black MJ (2019) Competitive collaboration: Joint unsupervised learning of depth, camera motion, optical flow and motion segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12240\u201312249","DOI":"10.1109\/CVPR.2019.01252"},{"key":"18382_CR19","doi-asserted-by":"crossref","unstructured":"Mahjourian R, Wicke M, Angelova A (2018) Unsupervised learning of depth and ego-motion from monocular video using 3d geometric constraints. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5667\u20135675","DOI":"10.1109\/CVPR.2018.00594"},{"key":"18382_CR20","doi-asserted-by":"crossref","unstructured":"Lowe DG (1999) Object recognition from local scale-invariant features. In: Proceedings of the seventh IEEE international conference on computer vision, Ieee, vol 2, pp 1150\u20131157","DOI":"10.1109\/ICCV.1999.790410"},{"key":"18382_CR21","doi-asserted-by":"crossref","unstructured":"Rublee E, Rabaud V, Konolige K, Bradski G (2011) Orb: An efficient alternative to sift or surf. In: 2011 International conference on computer vision, Ieee, pp 2564\u20132571","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"18382_CR22","doi-asserted-by":"crossref","unstructured":"Yi KM, Trulls E, Lepetit V, Fua P (2016) Lift: Learned invariant feature transform. In: European conference on computer vision, Springer, pp 467\u2013483","DOI":"10.1007\/978-3-319-46466-4_28"},{"key":"18382_CR23","unstructured":"Ono Y, Trulls E, Fua P, Yi KM (2018) Lf-net: Learning local features from images. Adv Neural Inf Process Syst 31"},{"key":"18382_CR24","unstructured":"Tang J, Kim H, Guizilini V, Pillai S, Ambrus R (2020) Neural outlier rejection for self-supervised keypoint learning. In: International conference on learning representations"},{"key":"18382_CR25","doi-asserted-by":"crossref","unstructured":"Sarlin P-E, DeTone D, Malisiewicz T, Rabinovich A (2020) Superglue: Learning feature matching with graph neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4938\u20134947","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"18382_CR26","unstructured":"Eigen D, Puhrsch C, Fergus R (2014) Depth map prediction from a single image using a multi-scale deep network. Adv Neural Inf Process Syst 27"},{"issue":"10","key":"18382_CR27","first-page":"2024","volume":"38","author":"ShenC LiuF","year":"2015","unstructured":"LiuF ShenC (2015) LinG, ReidI Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans Pattern Anal Mach Intell 38(10):2024\u20132039","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"18382_CR28","unstructured":"Tang C, Tan P (2018) Ba-net: Dense bundle adjustment network. arXiv preprint arXiv:1806.04807"},{"key":"18382_CR29","doi-asserted-by":"crossref","unstructured":"Yin W, Liu Y, Shen C, Yan Y (2019) Enforcing geometric constraints of virtual normal for depth prediction. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 5684\u20135693","DOI":"10.1109\/ICCV.2019.00578"},{"key":"18382_CR30","doi-asserted-by":"crossref","unstructured":"Garg R, Bg VK, Carneiro G, Reid I (2016) Unsupervised cnn for single view depth estimation: Geometry to the rescue. In: European conference on computer vision, Springer, pp 740\u2013756","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"18382_CR31","doi-asserted-by":"crossref","unstructured":"Godard C, Mac\u00a0Aodha O, Brostow GJ (2017) Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 270\u2013279","DOI":"10.1109\/CVPR.2017.699"},{"key":"18382_CR32","doi-asserted-by":"crossref","unstructured":"Zhan H, Garg R, Weerasekera CS, Li K, Agarwal H, Reid I (2018) Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 340\u2013349","DOI":"10.1109\/CVPR.2018.00043"},{"key":"18382_CR33","unstructured":"Bian J, Li Z, Wang N, Zhan H, Shen C, Cheng M-M, Reid I (2019) Unsupervised scale-consistent depth and ego-motion learning from monocular video. Adv Neural Inf Process Syst 32"},{"key":"18382_CR34","doi-asserted-by":"crossref","unstructured":"Wang S, Clark R, Wen H, Trigoni N (2017) Deepvo: Towards end-to-end visual odometry with deep recurrent convolutional neural networks. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp 2043\u20132050","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"18382_CR35","unstructured":"Ambrus R, Guizilini V, Li J, Gaidon SPA (2020) Two stream networks for self-supervised ego-motion estimation. In: Conference on robot learning, PMLR, pp 1052\u20131061"},{"key":"18382_CR36","doi-asserted-by":"crossref","unstructured":"Zhan H, Weerasekera CS, Bian J-W, Reid I (2020) Visual odometry revisited: What should be learnt? In: 2020 IEEE International conference on robotics and automation (ICRA), IEEE, pp 4203\u20134210","DOI":"10.1109\/ICRA40945.2020.9197374"},{"key":"18382_CR37","doi-asserted-by":"crossref","unstructured":"Zhao W, Liu S, Shu Y, Liu Y-J (2020) Towards better generalization: Joint depth-pose learning without posenet. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9151\u20139161","DOI":"10.1109\/CVPR42600.2020.00917"},{"key":"18382_CR38","unstructured":"Jaderberg M, Simonyan K, Zisserman A et al (2015) Spatial transformer networks. Adv Neural Inf Process Syst 28"},{"key":"18382_CR39","doi-asserted-by":"crossref","unstructured":"Bay H, Tuytelaars T, Gool LV (2006) Surf: Speeded up robust features. In: European conference on computer vision, Springer, pp 404\u2013417","DOI":"10.1007\/11744023_32"},{"key":"18382_CR40","doi-asserted-by":"crossref","unstructured":"Leutenegger S, Chli M, Siegwart RY (2011) Brisk: Binary robust invariant scalable keypoints. In: 2011 International conference on computer vision, Ieee, pp 2548\u20132555","DOI":"10.1109\/ICCV.2011.6126542"},{"key":"18382_CR41","doi-asserted-by":"crossref","unstructured":"Baker S, Matthews I (2004) Lucas-kanade 20 years on: A unifying framework. Int J Comput Vis 56(3): 221\u2013255","DOI":"10.1023\/B:VISI.0000011205.11775.fd"},{"key":"18382_CR42","doi-asserted-by":"crossref","unstructured":"Heise P, Klose S, Jensen B, Knoll A (2013) Pm-huber: Patchmatch with huber regularization for stereo matching. In: Proceedings of the IEEE international conference on computer vision, pp 2360\u20132367","DOI":"10.1109\/ICCV.2013.293"},{"key":"18382_CR43","doi-asserted-by":"crossref","unstructured":"Wang G, Zhang C Wang H, Wang J, Wang Y, Wang X (2020) Unsupervised learning of depth, optical flow and pose with occlusion from 3d geometry. IEEE Trans Intell Transp Syst 23(1):308\u2013320","DOI":"10.1109\/TITS.2020.3010418"},{"key":"18382_CR44","doi-asserted-by":"crossref","unstructured":"Yang Z, Wang P, Xu W, Zhao L, Nevatia R (2017) Unsupervised learning of geometry with edge-aware depth-normal consistency. arXiv preprint arXiv:1711.03665","DOI":"10.1609\/aaai.v32i1.12257"},{"key":"18382_CR45","doi-asserted-by":"crossref","unstructured":"Wang C, Buenaposada JM, Zhu R, Lucey S (2018) Learning depth from monocular videos using direct methods. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2022\u20132030","DOI":"10.1109\/CVPR.2018.00216"},{"key":"18382_CR46","doi-asserted-by":"crossref","unstructured":"Gordon A, Li H, Jonschkowski R, Angelova A (2019) Depth from videos in the wild: Unsupervised monocular depth learning from unknown cameras. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 8977\u20138986","DOI":"10.1109\/ICCV.2019.00907"},{"key":"18382_CR47","doi-asserted-by":"crossref","unstructured":"Mur-Artal R, Tard\u00f3s JD (2017) Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras. IEEE Trans Robot 33(5): 1255\u20131262","DOI":"10.1109\/TRO.2017.2705103"},{"key":"18382_CR48","unstructured":"Wang W, Hu Y, Scherer S (2020) Tartanvo: A generalizable learning-based vo. In: Conference on robot learning (CoRL)"},{"key":"18382_CR49","doi-asserted-by":"crossref","unstructured":"Balntas V, Lenc K, Vedaldi A, Mikolajczyk K (2017) Hpatches: A benchmark and evaluation of handcrafted and learned local descriptors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5173\u20135182","DOI":"10.1109\/CVPR.2017.410"},{"key":"18382_CR50","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE Conference on computer vision and pattern recognition, pp 3354\u20133361","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"18382_CR51","doi-asserted-by":"crossref","unstructured":"Gao H, Fang D, Xiao J, Hussain W, Kim JY (2023) Camrl: A joint method of channel attention and multidimensional regression loss for 3d object detection in automated vehicles. IEEE Trans Intell Transp Syst 24(8): 8831\u20138845","DOI":"10.1109\/TITS.2022.3219474"},{"key":"18382_CR52","doi-asserted-by":"crossref","unstructured":"Luiten J, Osep A, Dendorfer P, Torr P, Geiger A, Leal-Taix\u00e9 L, Leibe B (2021) Hota: A higher order metric for evaluating multi-object tracking. Int J Comput Vis 129(2):548\u2013578","DOI":"10.1007\/s11263-020-01375-2"},{"key":"18382_CR53","doi-asserted-by":"crossref","unstructured":"Yuan W, Gu X, Dai Z, Zhu S, Tan P (2022) Neural window fully-connected crfs for monocular depth estimation. In: 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 3906\u20133915","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"18382_CR54","doi-asserted-by":"crossref","unstructured":"Qiao S, Zhu Y, Adam H, Yuille A, Chen L-C (2021) Vip-deeplab: Learning visual perception with depth-aware video panoptic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3997\u20134008","DOI":"10.1109\/CVPR46437.2021.00399"},{"key":"18382_CR55","doi-asserted-by":"crossref","unstructured":"Aich S, Vianney JMU, Islam MA, Liu MKB (2021) Bidirectional attention network for monocular depth estimation. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp 11746\u201311752","DOI":"10.1109\/ICRA48506.2021.9560885"},{"key":"18382_CR56","doi-asserted-by":"crossref","unstructured":"Song X, Li W, Zhou D, Dai Y, Fang J, Li H, Zhang L (2021) Mlda-net: Multi-level dual attention-based network for self-supervised monocular depth estimation. IEEE Trans Image Process 30:4691\u20134705","DOI":"10.1109\/TIP.2021.3074306"},{"key":"18382_CR57","doi-asserted-by":"crossref","unstructured":"Ganeshan A, Vallet A, Kudo Y, Maeda S-i, Kerola T, Ambrus R, Park D, Gaidon A (2021) Warp-refine propagation: Semi-supervised auto-labeling via cycle-consistency. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 15499\u201315509","DOI":"10.1109\/ICCV48922.2021.01521"},{"key":"18382_CR58","doi-asserted-by":"crossref","unstructured":"Cai Y, Dai L, Wang H, Li Z (2021) Multi-target pan-class intrinsic relevance driven model for improving semantic segmentation in autonomous driving. IEEE Trans Image Process 30:9069\u20139084","DOI":"10.1109\/TIP.2021.3122293"},{"key":"18382_CR59","doi-asserted-by":"crossref","unstructured":"Liu H, Lu T, Xu Y, Liu J, Li W, Chen L (2022) Camliflow: Bidirectional camera-lidar fusion for joint optical flow and scene flow estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5791\u20135801","DOI":"10.1109\/CVPR52688.2022.00570"},{"key":"18382_CR60","doi-asserted-by":"crossref","unstructured":"Jeong J, Lin JM, Porikli F, Kwak N (2022) Imposing consistency for optical flow estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3181\u20133191","DOI":"10.1109\/CVPR52688.2022.00318"},{"key":"18382_CR61","doi-asserted-by":"crossref","unstructured":"Luo A, Yang F, Luo K, Li X, Fan H, Liu S (2022) Learning optical flow with adaptive graph reasoning. In: Proceedings of the AAAI conference on artificial intelligence (AAAI)","DOI":"10.1609\/aaai.v36i2.20083"},{"key":"18382_CR62","doi-asserted-by":"crossref","unstructured":"Dellenbach P, Deschaud J-E, Jacquet B, Goulette F (2022) Ct-icp: Real-time elastic lidar odometry with loop closure. In: 2022 International conference on robotics and automation (ICRA), IEEE, pp 5580\u20135586","DOI":"10.1109\/ICRA46639.2022.9811849"},{"key":"18382_CR63","doi-asserted-by":"crossref","unstructured":"Yoon DJ, Zhang H, Gridseth M, Thomas H, Barfoot TD (2021) Unsupervised learning of lidar features for use ina probabilistic trajectory estimator. IEEE Robot Autom Lett 6(2):2130\u20132138","DOI":"10.1109\/LRA.2021.3060407"},{"key":"18382_CR64","doi-asserted-by":"crossref","unstructured":"Chou C-C, Chou C-F (2022) Efficient and accurate tightly-coupled visual-lidar slam. IEEE Trans Intell Transp Syst 23(9):14509\u201314523","DOI":"10.1109\/TITS.2021.3130089"},{"key":"18382_CR65","doi-asserted-by":"crossref","unstructured":"Mayer N, Ilg E, Hausser P, Fischer P, Cremers D, Dosovitskiy A, Brox T (2016) A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4040\u20134048","DOI":"10.1109\/CVPR.2016.438"},{"key":"18382_CR66","unstructured":"Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer A (2017)Automatic differentiation in pytorch"},{"key":"18382_CR67","unstructured":"Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"key":"18382_CR68","doi-asserted-by":"crossref","unstructured":"Chen Y, Schmid C, Sminchisescu C (2019) Self-supervised learning with geometric constraints in monocular video: Connecting flow, depth, and camera. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7063\u20137072","DOI":"10.1109\/ICCV.2019.00716"},{"key":"18382_CR69","unstructured":"Grupp M (2017) evo: Python package for the evaluation of odometry and slam"},{"key":"18382_CR70","doi-asserted-by":"crossref","unstructured":"Triggs B, McLauchlan PF, Hartley RI, Fitzgibbon AW (1999) Bundle adjustment \u2014 a modern synthesis. In: international workshop on vision algorithms, Springer, pp 298\u2013372","DOI":"10.1007\/3-540-44480-7_21"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18382-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-18382-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18382-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T04:23:07Z","timestamp":1725423787000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-18382-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,26]]},"references-count":70,"journal-issue":{"issue":"32","published-online":{"date-parts":[[2024,9]]}},"alternative-id":["18382"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-18382-x","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,26]]},"assertion":[{"value":"31 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 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":"All authors declare that there are no conflicts of interest in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interests"}}]}}