{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T23:46:29Z","timestamp":1771458389104,"version":"3.50.1"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2017,2,11]],"date-time":"2017-02-11T00:00:00Z","timestamp":1486771200000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2018,2]]},"DOI":"10.1007\/s00530-017-0535-z","type":"journal-article","created":{"date-parts":[[2017,2,11]],"date-time":"2017-02-11T06:32:58Z","timestamp":1486794778000},"page":"55-72","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Multi-modal video event recognition based on association rules and decision fusion"],"prefix":"10.1007","volume":"24","author":[{"given":"Mennan","family":"G\u00fcder","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nihan Kesim","family":"\u00c7i\u00e7ekli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,2,11]]},"reference":[{"issue":"2","key":"535_CR1","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1007\/s13735-012-0024-2","volume":"2","author":"Yu-Gang Jiang","year":"2013","unstructured":"Jiang, Yu-Gang, et al.: High-level event recognition in unconstrained videos. Int. J. Multimed. Inf. Retr. 2(2), 73\u2013101 (2013)","journal-title":"Int. J. Multimed. Inf. Retr."},{"key":"535_CR2","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.cviu.2007.09.014","volume":"110","author":"H Bay","year":"2008","unstructured":"Bay, H., et al.: \u201cSpeeded-Up robust features (SURF)\u201d. Comput. Vis. Image Underst. 110, 346\u2013359 (2008)","journal-title":"Comput. Vis. Image Underst."},{"key":"535_CR3","doi-asserted-by":"crossref","unstructured":"Rublee, E., et al.: \u201cORB: an efficient alternative to SIFT or SURF\u201d in 2011 IEEE International Conference on Computer Vision, pp.\u00a02564\u20132571 (2011)","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"535_CR4","doi-asserted-by":"crossref","unstructured":"Leutenegger, S., Chli, M., Siegwart, R.Y.: \u201cBRISK: binary robust invariant scalable keypoints\u201d in 2011 IEEE International Conference on Computer Vision, pp.\u00a02548\u20132555 (2011)","DOI":"10.1109\/ICCV.2011.6126542"},{"key":"535_CR5","doi-asserted-by":"crossref","unstructured":"Calonder, M., et al.: \u201cBRIEF: binary robust independent elementary features.\u201d In ECCV (2010)","DOI":"10.1007\/978-3-642-15561-1_56"},{"key":"535_CR6","doi-asserted-by":"crossref","unstructured":"Jia, Y.: \u201cCaffe: an open source convolutional architecture for fast feature embedding.\u201d http:\/\/caffe.berkleyvision.org (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"535_CR7","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: \u201cAction recognition with improved trajectories\u201d. In ICCV 2013. Sydney, Australia. IEEE, pp. 3551\u20133558 (2013)","DOI":"10.1061\/9780784413135"},{"key":"535_CR8","unstructured":"Lan, Z., et al.: \u201cBeyond Gaussian pyramid: multi-skip feature stacking for action recognition.\u201d arXiv preprint arXiv, vol. 1411, pp. 6660 (2014)"},{"issue":"4","key":"535_CR9","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1007\/s00530-012-0294-9","volume":"19","author":"J-B Yeh","year":"2013","unstructured":"Yeh, J.-B., et al.: \u201cMultiple visual concept discovery using concept-based visual word clustering.\u201d Multimed. Syst. 19(4), 381\u2013393 (2013)","journal-title":"Multimed. Syst"},{"key":"535_CR10","unstructured":"Jia, Y., et al.: \u201cVisual concept learning: Combining machine vision and Bayesian generalization on concept hierarchies.\u201d In Advances in Neural Information Processing Systems, pp.\u00a01842\u20131850 (2013)"},{"issue":"1","key":"535_CR11","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1007\/s11042-013-1427-7","volume":"70","author":"A Scherp","year":"2014","unstructured":"Scherp, A., Mezaris, V.: \u201cSurvey on modeling and indexing events in multimedia.\u201d Multimed. Tools Appl. 70(1), 7\u201323 (2014)","journal-title":"Multimed. Tools Appl."},{"key":"535_CR12","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s10994-006-5833-1","volume":"62","author":"M Richardson","year":"2006","unstructured":"Richardson, M., Domingos, P.: Markov logic networks. Mach. Learn. 62, 107\u2013136 (2006)","journal-title":"Mach. Learn."},{"key":"535_CR13","doi-asserted-by":"crossref","unstructured":"Agrawal, R., Imielinkski, T., Swami, A.: Mining association rules between sets of items in large databases. In Proceedings of ACM SIGMOD, pp. 207\u2013216 (1993)","DOI":"10.1145\/170035.170072"},{"issue":"7","key":"535_CR14","first-page":"373","volume":"136","author":"M Naqvi","year":"2011","unstructured":"Naqvi, M., et al.: Mining temporal association rules with incremental standing for segment progressive filter. Commun. Comput. Inf. Sci. 136(7), 373\u2013382 (2011)","journal-title":"Commun. Comput. Inf. Sci."},{"key":"535_CR15","unstructured":"Thomason, J., et al.: \u201cIntegrating language and vision to generate natural language descriptions of videos in the wild,\u201d in Proceedings of the 25th International Conference on Computational Linguistics (COLING) (2014)"},{"key":"535_CR16","unstructured":"Natsev, A. et.al.: IBM Research TRECVID-2010 video copy detection and multimedia event detection system. In Proceedings of NIST TRECVID. Workshop (2010)"},{"key":"535_CR17","unstructured":"Natarajan, P., et al.: \u201cBBN VISER TRECVID 2011 multimedia event detection system.\u201d In Proceedings of NIST TRECVID. Workshop (2011)"},{"issue":"7","key":"535_CR18","doi-asserted-by":"crossref","first-page":"1354","DOI":"10.1109\/TPAMI.2013.212","volume":"36","author":"SS Bucak","year":"2014","unstructured":"Bucak, S.S., Jin, R., Jain, A.K.: Multiple kernel learning for visual object recognition: a review. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1354\u20131369 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"535_CR19","unstructured":"Chen, Q., et al.: \u201cBoosting classification with exclusive context.\u201d In Proc. PASCAL Visual Object Classes Challenge Workshop (2010)"},{"key":"535_CR20","unstructured":"Yang, J., et al.: \u201cGroup-sensitive multiple kernel learning for object categorization.\u201d In Proc. 12th ICCV. Kyoto. Japan (2009)"},{"key":"535_CR21","unstructured":"Vishwanathan, S.V.N., et al.: \u201cMultiple kernel learning and the SMO algorithm.\u201d In Advances in Neural Information Processing Systems, Vancouver, B. C., Canada (2010)"},{"key":"535_CR22","doi-asserted-by":"crossref","unstructured":"Varma, M., Babu, B.R.: \u201cMore generality in efficient multiple kernel learning.\u201d In ICML, pp. 134 (2009)","DOI":"10.1145\/1553374.1553510"},{"key":"535_CR23","doi-asserted-by":"crossref","unstructured":"Jain, A., Vishwanathan, S.V.N., Varma, M.: \u201cSPG-GMKL: Generalized multiple kernel learning with a million kernels.\u201d In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Beijing, China, August (2012)","DOI":"10.1145\/2339530.2339648"},{"key":"535_CR24","doi-asserted-by":"crossref","unstructured":"Tjondronegoro, D., et al.: \u201cMulti-modal summarization of key events and top players in sports tournament videos.\u201d In WACV. Kona. HI (2011)","DOI":"10.1109\/WACV.2011.5711541"},{"key":"535_CR25","doi-asserted-by":"crossref","unstructured":"Nephade, M.R., Huang, T.S.: \u201cDetecting semantic concepts using context and audio\/visual features.\u201d In Proceedings of the IEEE workshop on Detection and Recognition of Events in Video, pp.\u00a092\u201398 (2001)","DOI":"10.1109\/EVENT.2001.938871"},{"key":"535_CR26","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: \u201cImageNet classification with deep convolutional neural networks.\u201d In NIPS (2012)"},{"key":"535_CR27","unstructured":"Srivastava, N., Salakhutdinow, R.: \u201cMultimodal learning with deep boltzman machines.\u201d In NIPS\u201912. 25, pp. 2231\u20132239 (2012)"},{"issue":"5","key":"535_CR28","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P., et al.: \u201cStacked denosing autoencoders: learning useful representation in a deep network with a local denosing criterion.\u201d JMLR 11(5):3371\u20133408 (2010)","journal-title":"JMLR"},{"key":"535_CR29","unstructured":"Deng, J., et al.: \u201cImageNet Large Scale Visual Recognition Competition\u201d In ILSVRC (2012)"},{"key":"535_CR30","unstructured":"Simonyan, K., Zisserman, A.: \u201cTwo-stream convolutional networks for action recognition in videos.\u201d in NIPS (2014)"},{"key":"535_CR31","unstructured":"Jiang, Yu-Gang, et al.: \u201cExploiting feature and class relationships in video categorization with regularized deep neural networks\u201d arXiv abs\/1502.07209 (2015)"},{"key":"535_CR32","unstructured":"Sohn, K., Shang, W., Lee, H.: \u201cImproved multimodal deep learning with variation of information.\u201d in NIPS (2014)"},{"key":"535_CR33","doi-asserted-by":"crossref","unstructured":"Baccouche, M., et al.: \u201cSequential deep learning for human action recognition.\u201d In Human Behavior Understanding (2011)","DOI":"10.1007\/978-3-642-25446-8_4"},{"issue":"1","key":"535_CR34","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: \u201c3D convolutional neural networks for human action recognition.\u201d IEEE Trans. Pattern Anal. Mach. Intell. 35(1):221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"535_CR35","doi-asserted-by":"crossref","unstructured":"Karpathy, A., et al.: \u201cLarge-scale video classification with convolutional neural networks.\u201d In CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"535_CR36","unstructured":"Russakovsky, O., et al.: \u201cImageNet Large Scale Visual Recognition Challenge.\u201d (2014)"},{"key":"535_CR37","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: \u201cLong-term recurrent convolutional networks for visual recognition and description. CoRR abs\/1411.4389 (2014)","DOI":"10.21236\/ADA623249"},{"key":"535_CR38","doi-asserted-by":"crossref","unstructured":"Chatfield, K., et al.: \u201cReturn of the devil in the details: delving deep into convolutional nets.\u201d british machine vision conference, (arXiv ref. cs1405.3531) (2014)","DOI":"10.5244\/C.28.6"},{"key":"535_CR39","doi-asserted-by":"crossref","unstructured":"Girshick, R., et al.: \u201cRich feature hierarchies for accurate object detection and semantic segmentation.\u201d In IEEE Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"2","key":"535_CR40","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1007\/s11042-011-0912-0","volume":"62","author":"K Todorov","year":"2013","unstructured":"Todorov, K. ,et al.: \u201cMultimedia ontology matching by using visual and textual modalities.\u201d Multimed. Tools Appl. 62(2), 401\u2013425 (2013)","journal-title":"Multimed. Tools Appl."},{"issue":"11","key":"535_CR41","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"G Miller","year":"1995","unstructured":"Miller, G.: \u201cWordNet: a lexical database for English.\u201d Commun. ACM. 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"issue":"3","key":"535_CR42","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1109\/MMUL.2006.63","volume":"13","author":"J Smith","year":"2006","unstructured":"Smith, J., Chang, S.: Large-scale concept ontology for multimedia. IEEE Multimed. 13(3), 86\u201391 (2006)","journal-title":"IEEE Multimed."},{"issue":"1","key":"535_CR43","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","volume":"77","author":"B Russell","year":"2008","unstructured":"Russell, B., Torralba, A., Murphy, K., Freeman, W.: \u201cLabelMe: a database and web-based tool for image annotation.\u201d In IJCV 77(1), 157\u2013173 (2008)","journal-title":"In IJCV"},{"issue":"6","key":"535_CR44","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/MC.2010.183","volume":"43","author":"CGM Snoek","year":"2010","unstructured":"Snoek, C.G.M., Smeulders, A.W.M.: Visual-concept search solved? IEEE Comp. 43(6), 76\u201378 (2010)","journal-title":"IEEE Comp."},{"key":"535_CR45","doi-asserted-by":"crossref","unstructured":"van de Sande, K.E.A., Gevers, Th., Snoek, C.G.M.: \u201cEvaluation of Color Descriptors for Object and Scene Recognition.\u201d IEEE Trans on Pattern Analysis and Machine Intelligence (TPAMI) (2010)","DOI":"10.1109\/TPAMI.2009.154"},{"issue":"2","key":"535_CR46","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1007\/s11042-012-0995-2","volume":"69","author":"K Ntalianis","year":"2014","unstructured":"Ntalianis, K.,et al.: \u201cAutomatic annotation of image databases based on implicit crowdsourcing, visual concept modeling and evolution.\u201d Multimed. Tools Appl. 69(2), 397\u2013421 (2014)","journal-title":"Multimed. Tools Appl."},{"key":"535_CR47","volume-title":"\u201cVisual concept detection of web images based on group sparse ensemble learning.\u201d In Multimedia Tools and Applications","author":"Y Sun","year":"2014","unstructured":"Sun, Y., et al.: \u201cVisual concept detection of web images based on group sparse ensemble learning.\u201d In Multimedia Tools and Applications. Springer, Berlin (2014)"},{"key":"535_CR48","doi-asserted-by":"crossref","unstructured":"Natsev, A., et al.: \u201cSemantic concept-based query expansion and re-ranking for multimedia retrieval.\u201d ACM Multimedia. Augsburg, Germany (2007)","DOI":"10.1145\/1291233.1291448"},{"key":"535_CR49","doi-asserted-by":"crossref","unstructured":"Guder, M., Cicekli, N.K.: Dichotomic Decision Cascading for Video Shot Boundary Detection. In International Symposium on Multimedia (ISM) (2013)","DOI":"10.1109\/ISM.2013.43"},{"issue":"3","key":"535_CR50","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1142\/S021946780100027X","volume":"1","author":"R Lienhart","year":"2001","unstructured":"Lienhart, R.: \u201cReliable transition detection in videos: a survey and practitioner\u2019s guide.\u201d In International Journal of Image and Graphics (IJIG). 1(3), 469\u2013486 (2001)","journal-title":"In International Journal of Image and Graphics (IJIG)"},{"key":"535_CR51","unstructured":"Yu-Gang, J., et al.: \u201cConsumer video understanding: a benchmark database and an evaluation of human and machine performance.\u201d In ACM International Conference on Multimedia Retrieval (ICMR). Trento. Italy, (2011)"},{"key":"535_CR52","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: \u201cImageNet: A large-scale hierarchical image database.\u201d In CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"535_CR53","unstructured":"Google Web Search API (Deprecated). https:\/\/developers.google.com\/web-search\/ . 22 Apr. 2015"},{"key":"535_CR54","unstructured":"Bouchard, G., Triggs, B.: \u201cHierarchical part-based visual object categorization.\u201d In CVPR (2005)"},{"key":"535_CR55","first-page":"264","volume":"2","author":"R Fergus","year":"2003","unstructured":"Fergus, R., Perona, P., Zisserman, A.: \u201cObject class recognition by unsupervised scale-invariant learning\u201d. Proc. CVPR 2, 264\u2013271 (2003)","journal-title":"Proc. CVPR"},{"key":"535_CR56","unstructured":"Miksik, O., Mikolajczyk, K.: \u201cEvaluation of local detectors and descriptors for fast feature matching.\u201d Pattern Recognition (ICPR). 2012 21st International Conference, pp.\u00a02681\u20132684 (2012)"},{"key":"535_CR57","doi-asserted-by":"crossref","unstructured":"Heinly, J., Dunn, E., Frahm, J.M.: \u201cComparative evaluation of binary features.\u201d In Computer Vision ECCV (2012)","DOI":"10.1007\/978-3-642-33709-3_54"},{"key":"535_CR58","unstructured":"Sermanet, P., et al.: \u201cOverFeat: integrated recognition, localization and detection using convolutional networks,\u201d http:\/\/arxiv.org\/abs\/1312.6229 , ICLR (2014)"},{"key":"535_CR59","unstructured":"Jolliffe, I.T.: \u201cPrincipal component analysis. In Springer Series in Statistics.\u201d In 2nd ed. Springer. NY, vol. XXIX. 487 p.\u00a028 illus. ISBN 978-0-387-95442-4 (2002)"},{"issue":"5","key":"535_CR60","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1016\/j.cviu.2012.10.010","volume":"117","author":"K Piotr","year":"2013","unstructured":"Piotr, K., Fei, Y., Krystian, M.: \u201cComparison of mid-level feature coding approaches and pooling strategies in visual concept detection.\u201d Comp. Vision Image Underst. 117(5), 479\u2013492 (2013)","journal-title":"Comp. Vision Image Underst."},{"key":"535_CR61","doi-asserted-by":"crossref","unstructured":"Chang, Shih-Fu.: \u201cRobust late fusion with rank minimization.\u201d In Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.\u00a03021\u20133028, June 16\u201321 2012","DOI":"10.1109\/CVPR.2012.6248032"},{"key":"535_CR62","doi-asserted-by":"crossref","unstructured":"Ma, A.J., Yuen, P.C.: \u201cReduced analytic dependency modeling: Robust fusion for visual recognition.\u201d IJCV (2014)","DOI":"10.1007\/s11263-014-0723-7"},{"issue":"9","key":"535_CR63","doi-asserted-by":"crossref","first-page":"2772","DOI":"10.1109\/TIP.2015.2423560","volume":"24","author":"Kuan-Ting Lai","year":"2015","unstructured":"Lai, Kuan-Ting, et al.: \u201cLearning Sample Specific Weights for Late Fusion.\u201d Image Process. IEEE Trans. 24(9), 2772\u20132783 (2015)","journal-title":"Image Process. IEEE Trans."},{"key":"535_CR64","doi-asserted-by":"crossref","unstructured":"Marszaek, M., Laptev, I., Schmid, C.: \u201cActions in Context\u201d, In IEEE Conference on Computer Vision and Pattern Recognition\u201d (2009)","DOI":"10.1109\/CVPR.2009.5206557"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00530-017-0535-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-017-0535-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-017-0535-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T08:05:29Z","timestamp":1749974729000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00530-017-0535-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,11]]},"references-count":64,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,2]]}},"alternative-id":["535"],"URL":"https:\/\/doi.org\/10.1007\/s00530-017-0535-z","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,2,11]]}}}