{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:53:36Z","timestamp":1781110416489,"version":"3.54.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,2,25]],"date-time":"2022-02-25T00:00:00Z","timestamp":1645747200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,2,25]],"date-time":"2022-02-25T00:00:00Z","timestamp":1645747200000},"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":[[2023,2]]},"DOI":"10.1007\/s11042-022-12178-7","type":"journal-article","created":{"date-parts":[[2022,2,25]],"date-time":"2022-02-25T14:02:37Z","timestamp":1645797757000},"page":"5343-5367","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":84,"title":["Multi-modal active learning with deep reinforcement learning for target feature extraction in multi-media image processing applications"],"prefix":"10.1007","volume":"82","author":[{"given":"Gaurav","family":"Dhiman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A. Vignesh","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R.","family":"Nirmalan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S.","family":"Sujitha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"K.","family":"Srihari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"N.","family":"Yuvaraj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"P.","family":"Arulprakash","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R. Arshath","family":"Raja","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,2,25]]},"reference":[{"key":"12178_CR1","unstructured":"20BN-something-something Dataset:https:\/\/20bn.com\/datasets\/something-something"},{"issue":"1\u20132","key":"12178_CR2","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/0165-5817(96)81312-X","volume":"50","author":"M Abdel-Mottaleb","year":"1996","unstructured":"Abdel-Mottaleb M, Wu HL, Dimitrova N (1996) Aspects of multimedia retrieval. Philips J Res 50(1\u20132):227\u2013251","journal-title":"Philips J Res"},{"key":"12178_CR3","unstructured":"Abu-El-Haija S, Kothari N, Lee J, Natsev P, Toderici G, Varadarajan B, Vijayanarasimhan S (2016) Youtube-8m: A large-scale video classification benchmark. arXiv preprint arXiv:1609.08675"},{"key":"12178_CR4","unstructured":"ActivityNet C dataset: https:\/\/paperswithcode.com\/sota\/dense-video-captioning-on-activitynet"},{"key":"12178_CR5","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.media.2019.02.007","volume":"53","author":"A Alansary","year":"2019","unstructured":"Alansary A, Oktay O, Li Y, Le Folgoc L, Hou B, Vaillant G, Rueckert D (2019) Evaluating reinforcement learning agents for anatomical landmark detection. Med Image Anal 53:156\u2013164","journal-title":"Med Image Anal"},{"key":"12178_CR6","first-page":"15","volume":"1","author":"I Chatterjee","year":"2021","unstructured":"Chatterjee I (2021) Artificial intelligence and patentability: review and discussions. Int J Mod Res 1:15\u201321","journal-title":"Int J Mod Res"},{"key":"12178_CR7","unstructured":"DALY dataset: http:\/\/thoth.inrialpes.fr\/daly\/"},{"issue":"5","key":"12178_CR8","doi-asserted-by":"publisher","first-page":"4185","DOI":"10.1007\/s11042-019-07935-0","volume":"79","author":"S Duraimurugan","year":"2020","unstructured":"Duraimurugan S, Jayarin PJ (2020) Maximizing the quality of service in distributed multimedia streaming in heterogeneous wireless network. Multimed Tools Appl 79(5):4185\u20134198","journal-title":"Multimed Tools Appl"},{"key":"12178_CR9","doi-asserted-by":"crossref","unstructured":"Goyal R, Kahou SE, Michalski V, Materzynska J, Westphal S, Kim H, Hoppe F (2017) The\u201d Something Something\u201d video database for learning and evaluating visual common sense. In: ICCV, vol 1, no 4, p 5","DOI":"10.1109\/ICCV.2017.622"},{"key":"12178_CR10","doi-asserted-by":"publisher","unstructured":"Hashemzehi R, Mahdavi SJS, Kheirabadi M, Kamel SR (2020) Detection of brain tumors from MRI images base on deep learning using hybrid model CNN and NADE. Biocybern Biomed Eng. https:\/\/doi.org\/10.1016\/j.bbe.2020.06.001","DOI":"10.1016\/j.bbe.2020.06.001"},{"key":"12178_CR11","doi-asserted-by":"publisher","unstructured":"He S, Wu J, Lian C, Gach HM, Mutic S, Bosch W, Li H (2020) An adaptive low-rank modeling-based active learning method for medical image annotation. IRBM. In Press, Corrected Proof. https:\/\/doi.org\/10.1016\/j.irbm.2020.06.001","DOI":"10.1016\/j.irbm.2020.06.001"},{"key":"12178_CR12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2918284","author":"G Huang","year":"2019","unstructured":"Huang G, Liu Z, Pleiss G, Van Der Maaten L, Weinberger K (2019) Convolutional networks with dense connectivity. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2019.2918284","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"12178_CR13","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.patrec.2020.03.034","volume":"135","author":"H Ide","year":"2020","unstructured":"Ide H, Kobayashi T, Watanabe K, Kurita T (2020) Robust pruning for efficient CNNs. Pattern Recognit Lett 135:90\u201398","journal-title":"Pattern Recognit Lett"},{"key":"12178_CR14","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014)Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp 1725-1732","DOI":"10.1109\/CVPR.2014.223"},{"key":"12178_CR15","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.patcog.2017.05.020","volume":"71","author":"X Ke","year":"2017","unstructured":"Ke X, Zhou M, Niu Y, Guo W (2017) Data equilibrium based automatic image annotation by fusing deep model and semantic propagation. Pattern Recogn 71:60\u201377","journal-title":"Pattern Recogn"},{"key":"12178_CR16","doi-asserted-by":"publisher","first-page":"4560","DOI":"10.1109\/ACCESS.2018.2791427","volume":"6","author":"T Khalil","year":"2018","unstructured":"Khalil T, Akram MU, Raja H, Jameel A, Basit I (2018) Detection of glaucoma using cup to disc ratio from spectral domain optical coherence tomography images. IEEE Access 6:4560\u20134576","journal-title":"IEEE Access"},{"key":"12178_CR17","doi-asserted-by":"crossref","unstructured":"Kiran R, Kumar P, Bhasker B (2020) OSLCFit (Organic Simultaneous LSTM and CNN Fit): A novel deep learning based solution for sentiment polarity classification of reviews. Expert Syst Appl 113488","DOI":"10.1016\/j.eswa.2020.113488"},{"key":"12178_CR18","first-page":"65","volume":"17","author":"SM Koriem","year":"2004","unstructured":"Koriem SM (2004) Modeling concurrent, sequential, storage, retrieval, and scheduling activities of multimedia systems. J King Saud Univ - Comput Inf Sci 17:65\u2013103","journal-title":"J King Saud Univ - Comput Inf Sci"},{"key":"12178_CR19","doi-asserted-by":"crossref","unstructured":"Krishna R, Hata K, Ren F, Fei-Fei L, Niebles C (2017) J. Dense-captioning events in videos. In: Proceedings of the IEEE international conference on computer vision, pp 706-715","DOI":"10.1109\/ICCV.2017.83"},{"key":"12178_CR20","first-page":"1","volume":"1","author":"R Kumar","year":"2021","unstructured":"Kumar R, Dhiman G (2021) A comparative study of fuzzy optimization through fuzzy number. Int J Mod Res 1:1\u201314","journal-title":"Int J Mod Res"},{"key":"12178_CR21","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/j.ascom.2018.10.008","volume":"25","author":"E Kuminski","year":"2018","unstructured":"Kuminski E, Shamir L (2018) A hybrid approach to machine learning annotation of large galaxy image databases. Astron Comput 25:257\u2013269","journal-title":"Astron Comput"},{"issue":"2","key":"12178_CR22","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1016\/j.bbe.2020.03.005","volume":"40","author":"H Li","year":"2020","unstructured":"Li H, Zhang B, Zhang Y, Liu W, Mao Y, Huang J, Wei L (2020) A semi-automated annotation algorithm based on weakly supervised learning for medical images. Biocybernet Biomed Eng 40(2):787\u2013802","journal-title":"Biocybernet Biomed Eng"},{"key":"12178_CR23","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1016\/j.patrec.2019.05.011","volume":"125","author":"C Luo","year":"2019","unstructured":"Luo C, Yu L, Yang E, Zhou H, Ren P (2019) A benchmark image dataset for industrial tools. Pattern Recognit Lett 125:341\u2013348","journal-title":"Pattern Recognit Lett"},{"key":"12178_CR24","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.cviu.2017.05.007","volume":"161","author":"D Mishkin","year":"2017","unstructured":"Mishkin D, Sergievskiy N, Matas J (2017) Systematic evaluation of convolution neural network advances on the imagenet. Comput Vis Image Underst 161:11\u201319","journal-title":"Comput Vis Image Underst"},{"key":"12178_CR25","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/j.patrec.2020.04.031","volume":"135","author":"SR Mishra","year":"2020","unstructured":"Mishra SR, Mishra TK, Sanyal G, Sarkar A, Satapathy SC (2020) Real time human action recognition using triggered frame extraction and a typical CNN heuristic. Pattern Recognit Lett 135:329\u2013336","journal-title":"Pattern Recognit Lett"},{"key":"12178_CR26","doi-asserted-by":"crossref","unstructured":"Mo K, Zhu S, Chang AX, Yi L, Tripathi S, Guibas LJ, Su H (2019) Partnet: A large-scale benchmark for fine-grained and hierarchical part-level 3d object understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 909-918","DOI":"10.1109\/CVPR.2019.00100"},{"key":"12178_CR27","unstructured":"MPII-Cooking dataset: https:\/\/pgram.com\/dataset\/mpii-cooking-activities-dataset\/"},{"key":"12178_CR28","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.inffus.2017.01.003","volume":"37","author":"L Piras","year":"2017","unstructured":"Piras L, Giacinto G (2017) Information fusion in content based image retrieval: A comprehensive overview. Inf Fusion 37:50\u201360","journal-title":"Inf Fusion"},{"issue":"2","key":"12178_CR29","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1016\/j.patcog.2006.04.042","volume":"40","author":"X Qi","year":"2007","unstructured":"Qi X, Han Y (2007) Incorporating multiple SVMs for automatic image annotation. Pattern Recogn 40(2):728\u2013741","journal-title":"Pattern Recogn"},{"key":"12178_CR30","doi-asserted-by":"publisher","first-page":"101093","DOI":"10.1016\/j.ecoinf.2020.101093","volume":"58","author":"J Qin","year":"2020","unstructured":"Qin J, Pan W, Xiang X, Tan Y, Hou G (2020) A biological image classification method based on improved CNN. Eco Inform 58:101093","journal-title":"Eco Inform"},{"key":"12178_CR31","doi-asserted-by":"crossref","unstructured":"Real E, Shlens J, Mazzocchi S, Pan X, Vanhoucke V (2017) Youtube-boundingboxes: A large high-precision human-annotated data set for object detection in video. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5296-5305","DOI":"10.1109\/CVPR.2017.789"},{"key":"12178_CR32","doi-asserted-by":"crossref","unstructured":"Rohrbach M, Amin S, Andriluka M, Schiele B (2012) A database for fine grained activity detection of cooking activities. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 1194-1201","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"12178_CR33","doi-asserted-by":"publisher","first-page":"132306","DOI":"10.1016\/j.physd.2019.132306","volume":"404","author":"A Sherstinsky","year":"2020","unstructured":"Sherstinsky A (2020) Fundamentals of recurrent neural network (rnn) and long short-term memory (lstm) network. Physica D 404:132306","journal-title":"Physica D"},{"key":"12178_CR34","unstructured":"Sports-1M dataset: https:\/\/github.com\/gtoderici\/sports-1m-dataset\/blob\/wiki\/ProjectHome.md"},{"key":"12178_CR35","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1016\/j.jvcir.2018.12.028","volume":"58","author":"F Tian","year":"2019","unstructured":"Tian F, Wang Q, Li X, Sun N (2019) Heterogeneous multimedia cooperative annotation based on multimodal correlation learning. J Vis Commun Image Represent 58:544\u2013553","journal-title":"J Vis Commun Image Represent"},{"key":"12178_CR36","unstructured":"Tran D, Bolonkin M, Paluri M, Torresani L (2016) VideoMCC: a New benchmark for video comprehension. arXiv preprint arXiv:1606.07373"},{"key":"12178_CR37","first-page":"22","volume":"1","author":"PK Vaishnav","year":"2021","unstructured":"Vaishnav PK, Sharma S, Sharma P (2021) Analytical review analysis for screening COVID-19. Int J Mod Res 1:22\u201329","journal-title":"Int J Mod Res"},{"key":"12178_CR38","unstructured":"VideoMCC dataset: https:\/\/archive.org\/details\/vicomdataset"},{"key":"12178_CR39","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.jvcir.2017.07.004","volume":"49","author":"R Wang","year":"2017","unstructured":"Wang R, Xie Y, Yang J, Xue L, Hu M, Zhang Q (2017) Large scale automatic image annotation based on convolutional neural network. J Vis Commun Image Represent 49:213\u2013224","journal-title":"J Vis Commun Image Represent"},{"key":"12178_CR40","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.image.2018.09.013","volume":"70","author":"R Wang","year":"2019","unstructured":"Wang R, Xu J, Han TX (2019) Object instance detection with pruned Alexnet and extended training data. Sig Process Image Commun 70:145\u2013156","journal-title":"Sig Process Image Commun"},{"key":"12178_CR41","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.neucom.2019.11.062","volume":"382","author":"C Wang","year":"2020","unstructured":"Wang C, Song L, Wang G, Zhang Q, Wang X (2020)Multi-scale multi-patch person re-identification with exclusivity regularized softmax. Neurocomputing 382:64\u201370","journal-title":"Neurocomputing"},{"key":"12178_CR42","unstructured":"Weinzaepfel P, Martin X, Schmid C (2016) Human action localization with sparse spatial supervision. arXiv preprint arXiv:1605.05197"},{"issue":"1","key":"12178_CR43","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.ejor.2017.07.052","volume":"265","author":"Y Xie","year":"2018","unstructured":"Xie Y, Zhou S, Xiao Y, Kulturel-Konak S, Konak A (2018) A \u03b2-accurate linearization method of Euclidean distance for the facility layout problem with heterogeneous distance metrics. Eur J Oper Res 265(1):26\u201338","journal-title":"Eur J Oper Res"},{"key":"12178_CR44","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1016\/j.ins.2018.03.051","volume":"451","author":"Z Xue","year":"2018","unstructured":"Xue Z, Li G, Huang Q (2018) Joint multi-view representation and image annotation via optimal predictive subspace learning. Inf Sci 451:180\u2013194","journal-title":"Inf Sci"},{"key":"12178_CR45","unstructured":"Youtube-8M dataset: http:\/\/research.google.com\/youtube8m\/"},{"key":"12178_CR46","unstructured":"Youtube BoundingBoxes dataset: https:\/\/research.google.com\/youtube-bb\/"},{"issue":"3","key":"12178_CR47","doi-asserted-by":"publisher","first-page":"615","DOI":"10.2298\/CSIS180105025Z","volume":"15","author":"B Zafar","year":"2018","unstructured":"Zafar B, Ashraf R, Ali N, Ahmed M, Jabbar S, Naseer K, Jeon G (2018) Intelligent image classification-based on spatial weighted histograms of concentric circles. Comput Sci Inf Syst 15(3):615\u2013633","journal-title":"Comput Sci Inf Syst"},{"key":"12178_CR48","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.knosys.2014.12.014","volume":"76","author":"M Zhao","year":"2015","unstructured":"Zhao M, Chow TW, Zhang Z, Li B (2015) Automatic image annotation via compact graph based semi-supervised learning. Knowl Based Syst 76:148\u2013165","journal-title":"Knowl Based Syst"},{"issue":"2","key":"12178_CR49","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1080\/10095020.2018.1441754","volume":"21","author":"W Zhao","year":"2018","unstructured":"Zhao W, Yan L, Zhang Y (2018)Geometric-constrained multi-view image matching method based on semi-global optimization. Geo Spat Inf Sci 21(2):115\u2013126","journal-title":"Geo Spat Inf Sci"},{"key":"12178_CR50","doi-asserted-by":"publisher","first-page":"111853","DOI":"10.1016\/j.enconman.2019.111853","volume":"197","author":"Z Zhen","year":"2019","unstructured":"Zhen Z, Xuan Z, Wang F, Sun R, Dui\u0107 N, Jin T (2019) Image phase shift invariance based multi-transform-fusion method for cloud motion displacement calculation using sky images. Energy Conv Manag 197:111853","journal-title":"Energy Conv Manag"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12178-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-12178-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12178-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T08:20:01Z","timestamp":1674634801000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-12178-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,25]]},"references-count":50,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["12178"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-12178-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,25]]},"assertion":[{"value":"5 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 November 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}