{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:27Z","timestamp":1760245047668,"version":"3.41.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2017,9,18]],"date-time":"2017-09-18T00:00:00Z","timestamp":1505692800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1007\/s10489-017-1033-x","type":"journal-article","created":{"date-parts":[[2017,9,18]],"date-time":"2017-09-18T03:05:48Z","timestamp":1505703948000},"page":"2047-2066","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Multi-label semantic concept detection in videos using fusion of asymmetrically trained deep convolutional neural networks and foreground driven concept co-occurrence matrix"],"prefix":"10.1007","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3983-6118","authenticated-orcid":false,"given":"Nitin J.","family":"Janwe","sequence":"first","affiliation":[]},{"given":"Kishor K.","family":"Bhoyar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,9,18]]},"reference":[{"issue":"2","key":"1033_CR1","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1109\/TPAMI.2015.2469281","volume":"38","author":"L Feng","year":"2016","unstructured":"Feng L, Bhanu B (2016) Semantic concept co-occurrence patterns for image annotation and retrieval. IEEE Trans Pattern Anal Mach Intell 38(2):785\u2013799","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1033_CR2","doi-asserted-by":"publisher","unstructured":"Kuo CH, Chou YH, Chang PC (2016) Using deep convolutional neural networks for image retrieval. Soc Imag Sci Technol. https:\/\/doi.org\/10.2352\/ISSN.2470-1173.2016.2.VIPC-231","DOI":"10.2352\/ISSN.2470-1173.2016.2.VIPC-231"},{"key":"1033_CR3","doi-asserted-by":"crossref","unstructured":"Podlesnaya A, Podlesnyy S (2016) Deep learning based semantic video indexing and retrieval. arXiv: 1601.07754 [cs.IR]","DOI":"10.1007\/978-3-319-56991-8_27"},{"key":"1033_CR4","doi-asserted-by":"crossref","unstructured":"McCormac J, Handa A, Davison A, Leutenegger S (2016) SemanticFusion: dense 3D semantic mapping with convolutional neural networks. arXiv: 1609.05130v2 [cs.CV]","DOI":"10.1109\/ICRA.2017.7989538"},{"key":"1033_CR5","doi-asserted-by":"crossref","unstructured":"Kikuchi K, Ueki K, Ogawa T, Kobayashi T (2016) Video semantic indexing using object detection-derived features. In: Proc. 24th European signal processing conference (EUSIPCO). Budapest, pp 1288\u20131292","DOI":"10.1109\/EUSIPCO.2016.7760456"},{"issue":"1","key":"1033_CR6","first-page":"187","volume":"4","author":"G Awad","year":"2016","unstructured":"Awad G, Snoek CGM, Smeaton AF, Qu\u00e9not G (2016) TRECVid semantic indexing of video: a 6-year retrospective. ITE Trans Med Technol Appl (MTA) 4(1):187\u2013208","journal-title":"ITE Trans Med Technol Appl (MTA)"},{"key":"1033_CR7","doi-asserted-by":"crossref","unstructured":"Janwe NJ, Bhoyar KK (2016) Neural network based multi-label semantic video concept detection using novel mixed-hybrid-fusion approach. In: Proceedings of the 2nd international conference on communication and information processing, ICCIP 2016. ACM, Singapore, pp 129\u2013133","DOI":"10.1145\/3018009.3018052"},{"key":"1033_CR8","doi-asserted-by":"publisher","unstructured":"Vedaldi A, Lenc K (2015) MatConvNet: convolutional neural networks for MATLAB. In: Proc. of the int. conf. on multimedia. ACM, pp 689-692. https:\/\/doi.org\/10.1145\/2733373.2807412","DOI":"10.1145\/2733373.2807412"},{"key":"1033_CR9","doi-asserted-by":"publisher","unstructured":"Modiri S, Amir A, Zamir R, Shah M (2014) Video classification using semantic concept co-occurrences. https:\/\/doi.org\/10.1109\/CVPR.2014.324","DOI":"10.1109\/CVPR.2014.324"},{"key":"1033_CR10","unstructured":"Li X, Zhao F, Guo Y (2014) Multi-label image classification with a probabilistic label enhancement model. In: UAI\u201914 Proceedings of the thirtieth conference on uncertainty in artificial intelligence, pp 430-439"},{"key":"1033_CR11","unstructured":"Donahue J, Jia Y, Vinyals O, Hoffman J, Zhang N, Tzeng E, Darrell T (2014) Decaf: a deep convolutional activation feature for generic visual recognition. In: Proceedings of the international conference on machine learning, ICML. Beijing, pp 647\u2013 655"},{"key":"1033_CR12","unstructured":"Zeiler MD, Fergus R (2013) Visualizing and understanding convolutional networks. arXiv: 1311.2901 [cs.CV]"},{"key":"1033_CR13","doi-asserted-by":"publisher","first-page":"77","DOI":"10.6138\/JIT.2017.18.2.20160815","volume":"64","author":"S Memar","year":"2013","unstructured":"Memar S, Suriani AL (2013) An integrated semantic-based approach in concept based video retrieval. Multimed Tools Appl 64:77\u201395. 10.1007\/s11042-011-0848-4","journal-title":"Multimed Tools Appl"},{"key":"1033_CR14","doi-asserted-by":"crossref","unstructured":"Oquab M, Bottou L, Laptev I, Sivic J (2013) Learning and transferring mid-level image representations using convolutional neural networks. Technical Report HAL-00911179, INRIA","DOI":"10.1109\/CVPR.2014.222"},{"issue":"5","key":"1033_CR15","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1109\/TMM.2010.2051360","volume":"12","author":"H Ma","year":"2010","unstructured":"Ma H, Zhu J, Lyu MRT, King I (2010) Bridging the semantic gap between image contents and tags. IEEE Trans Multimed 12(5):462\u2013473","journal-title":"IEEE Trans Multimed"},{"key":"1033_CR16","unstructured":"Jia D, Berg A, Fei-Fei L (2011) Hierarchical semantic indexing for large scale image retrieval. In: Proceedings of the 2011 IEEE conference on computer vision and pattern recognition, CVPR 2011. Colorado Springs, pp 785\u2013792"},{"key":"1033_CR17","doi-asserted-by":"crossref","unstructured":"Farhadi A, Endres I, Hoiem D, Forsyth D (2009) Describing objects by their attributes. In: 2009 IEEE Computer society conference on computer vision and pattern recognition workshops, CVPR Workshops. Miami, pp 1778\u20131785","DOI":"10.1109\/CVPR.2009.5206772"},{"issue":"1","key":"1033_CR18","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/34.910878","volume":"23","author":"A Bobick","year":"2001","unstructured":"Bobick A, Davis J (2001) The recognition of human movement using temporal templates. IEEE Trans Pattern Anal Mach Intell 23(1):257\u2013267","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1033_CR19","doi-asserted-by":"crossref","unstructured":"Davis JW, Bobick AF (1997) The representation and recognition of action using temporal templates. In: Proc. IEEE International conference on computer vision and pattern recognition, pp 928\u2013934","DOI":"10.1109\/CVPR.1997.609439"},{"issue":"9","key":"1033_CR20","doi-asserted-by":"crossref","first-page":"1530","DOI":"10.1109\/TPAMI.2006.194","volume":"28","author":"ML Zelnik","year":"2006","unstructured":"Zelnik ML, Irani M (2006) Statistical analysis of dynamic actions. IEEE Trans Pattern Anal Mach Intell 28(9):1530\u20131535","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1033_CR21","unstructured":"Dong X, Chang SF (2007) Visual event recognition in news video using kernel methods with multi-level temporal alignment. In: Proc. IEEE international conference on computer vision and pattern recognition. Minneapolis"},{"key":"1033_CR22","doi-asserted-by":"crossref","unstructured":"Zhou X, Zhuang X, Yan S, Chang SF, Hasegawa-Johnson M, Huang TS (2008) Sift-bag kernel for video event analysis. In: Proc. ACM international conference on multimedia. Vancouver, pp 229\u2013238","DOI":"10.1145\/1459359.1459391"},{"key":"1033_CR23","unstructured":"Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. In: ANIPS, pp 1\u20138"},{"issue":"5","key":"1033_CR24","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"L LeCun","year":"1998","unstructured":"LeCun L, Bottou Y, Bengio, Haffner P (1998) Gradient based learning applied to document recognition. Proc IEEE 86(5):2278\u20132324","journal-title":"Proc IEEE"},{"key":"1033_CR25","unstructured":"Dean G, Corrado R, Monga K, Chen M, Devin Q, Le M, Mao M, Ranzato A, Senior P, Tucker K, Yang, Ng A (2012) Large scale distributed deep networks. In: NIPS, pp 1\u20139"},{"issue":"6088","key":"1033_CR26","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"D Rumelhart","year":"1986","unstructured":"Rumelhart D, Hinton G, Williams R (1986) Learning representations by back-propagating errors. Nature 323(6088):533\u2013536","journal-title":"Nature"},{"key":"1033_CR27","unstructured":"Torralba A, Murphy KP, Freeman WT (2004) Contextual models for object detection using boosted random fields. In: Proc. Adv. neural inf. process. syst., pp 1401\u20131408"},{"key":"1033_CR28","doi-asserted-by":"crossref","unstructured":"Rabinovich A, Vedaldi A, Galleguillos C, Wiewiora E, Belongie S (2007) Objects in context. In: Proc. 11th IEEE int. conf. comput. vis., pp 1\u20138","DOI":"10.1109\/ICCV.2007.4408986"},{"key":"1033_CR29","doi-asserted-by":"crossref","unstructured":"Galleguillos C, Rabinovich A, Belongie S (2008) Object categorization using co-occurrence, location and appearance. In: Proc. IEEE Conf. comput. vis. pattern recog., pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587799"},{"key":"1033_CR30","doi-asserted-by":"crossref","unstructured":"Hwang S, Grauman K (2010) Reading between the lines: object localization using implicit cues from image tags. In: Proc. IEEE Conf. comput. vis. pattern recog., pp 1145\u20131158","DOI":"10.1109\/CVPR.2010.5540043"},{"issue":"2","key":"1033_CR31","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1023\/A:1023052124951","volume":"53","author":"A Torralba","year":"2003","unstructured":"Torralba A (2003) Contextual priming for object detection. Int J Comput Vis 53(2):169\u2013191","journal-title":"Int J Comput Vis"},{"key":"1033_CR32","doi-asserted-by":"crossref","unstructured":"Divvala S, Hoiem D, Hays J, Efros A, Hebert M (2009) An empirical study of context in object detection. In: Proc. IEEE Conf. comput. vis. pattern recog., pp 1271\u20131278","DOI":"10.1109\/CVPR.2009.5206532"},{"key":"1033_CR33","doi-asserted-by":"crossref","unstructured":"Feng L, Bhanu B (2012) Semantic-visual concept relatedness and co-occurrences for image retrieval. In: ICIP, pp 2429\u20132432","DOI":"10.1109\/ICIP.2012.6467388"},{"key":"1033_CR34","doi-asserted-by":"crossref","first-page":"2274","DOI":"10.1016\/j.patcog.2010.07.015","volume":"44","author":"J Wang","year":"2011","unstructured":"Wang J, Zhao Y, Wu X, Hua XS (2011) A transductive multi-label learning approach for video concept detection. Pattern Recogn 44:2274\u20132286","journal-title":"Pattern Recogn"},{"key":"1033_CR35","unstructured":"Zha ZJ, Liu Y, Mei T, Hua XS (2007) Video concept detection using support vector machines - trecvid 2007 evaluations. Technical report Microsoft Research Lab \u2013 Asia"},{"issue":"7","key":"1033_CR36","doi-asserted-by":"crossref","first-page":"1378","DOI":"10.1109\/TMM.2016.2559947","volume":"18","author":"M Mazloom","year":"2016","unstructured":"Mazloom M, Li X, Snoek CGM (2016) TagBook: a semantic video representation without supervision for event detection. IEEE Trans Multimed 18(7):1378\u20131388","journal-title":"IEEE Trans Multimed"},{"key":"1033_CR37","doi-asserted-by":"crossref","unstructured":"Markatopoulou F, Mezaris V, Patras I (2015) Cascade of classifiers based on binary, non-binary and deep convolutional network descriptors for video concept detection. In: Proc. IEEE Int. conf. on image processing. Quebec City, pp 1786\u20131790","DOI":"10.1109\/ICIP.2015.7351108"},{"key":"1033_CR38","doi-asserted-by":"crossref","unstructured":"Markatopoulou F, Mezaris V, Patras I (2016) Deep multi-task learning with label correlation constraint for video concept detection. In: Proc. of the ACM multimedia conference. Amsterdam, pp 501\u2013505","DOI":"10.1145\/2964284.2967271"},{"key":"1033_CR39","unstructured":"Sun Y, Sudo K, Taniguchi Y (2014) TRECVid 2013 semantic video concept detection by NTT-MD-DUT. In: Proc. of Trecvid 2014"},{"key":"1033_CR40","doi-asserted-by":"publisher","unstructured":"Chen X, Chen S, Wu Y (2017) Coverless information hiding method based on the Chinese character encoding. J Int Technol 18(2):91\u201398. https:\/\/doi.org\/10.6138\/JIT.2017.18.2.20160815","DOI":"10.6138\/JIT.2017.18.2.20160815"},{"key":"1033_CR41","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1016\/j.neucom.2017.01.064","volume":"238","author":"Q Tian","year":"2017","unstructured":"Tian Q, Chen S (2017) Cross-heterogeneous-database age estimation through correlation representation learning. J Neurocomput 238:286\u2013295","journal-title":"J Neurocomput"},{"key":"1033_CR42","doi-asserted-by":"publisher","unstructured":"Xue Y, Jiang J, Zhao B, Ma T (2017) A self-adaptive artificial bee colony algorithm based on global best for global optimization. Soft Comput 1\u201318. https:\/\/doi.org\/10.1007\/s00500-017-2547-1","DOI":"10.1007\/s00500-017-2547-1"},{"issue":"2","key":"1033_CR43","first-page":"209","volume":"18","author":"C Yuan","year":"2017","unstructured":"Yuan C, Xia Z, Sun X (2017) Coverless image steganography based on SIFT and BOF. J Int Technol 18(2):209\u2013 216","journal-title":"J Int Technol"},{"key":"1033_CR44","doi-asserted-by":"publisher","unstructured":"Wei W, Fan X, Song H, Fan X, Yang J (2016) Imperfect information dynamic stackelberg game based resource allocation using hidden Markov for cloud computing. IEEE Trans Services Comput (99) https:\/\/doi.org\/10.1109\/TSC.2016.2528246","DOI":"10.1109\/TSC.2016.2528246"},{"issue":"9","key":"1033_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-015-0957-4","volume":"59","author":"Y Chen","year":"2016","unstructured":"Chen Y, Hao C, Wu W, Wu E (2016) Robust dense reconstruction by range merging based on confidence estimation. Sci Chin Inf Sci 59(9):1\u201311. https:\/\/doi.org\/10.1007\/s11432-015-0957-4","journal-title":"Sci Chin Inf Sci"},{"key":"1033_CR46","unstructured":"NIST: http:\/\/www.nist.gov"},{"key":"1033_CR47","unstructured":"TRECVID: http:\/\/www-nlpir.nist.go"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10489-017-1033-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-017-1033-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-017-1033-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T19:44:38Z","timestamp":1750880678000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10489-017-1033-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9,18]]},"references-count":47,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2018,8]]}},"alternative-id":["1033"],"URL":"https:\/\/doi.org\/10.1007\/s10489-017-1033-x","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2017,9,18]]}}}