{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T01:11:40Z","timestamp":1791421900278,"version":"4.3.3"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2014,4,25]],"date-time":"2014-04-25T00:00:00Z","timestamp":1398384000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2015,2]]},"DOI":"10.1007\/s11042-014-1955-9","type":"journal-article","created":{"date-parts":[[2014,4,24]],"date-time":"2014-04-24T07:35:40Z","timestamp":1398324940000},"page":"1397-1421","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["A generic framework for semantic video indexing based on visual concepts\/contexts detection"],"prefix":"10.1007","volume":"74","author":[{"given":"Nizar","family":"Elleuch","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anis","family":"Ben Ammar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adel M.","family":"Alimi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2014,4,25]]},"reference":[{"key":"1955_CR1","unstructured":"Amir A, Berg M, fu Chang S, Iyengar G, yung Lin C, (paul Natsev A, Neti C, Nock H, Naphade M, Hsu W, Smith JR, Tseng B, Wu Y, Zhang D, Watson ITJ (2003) Ibm research trecvid-2003 video retrieval system. In: In NIST TRECVID-2003"},{"key":"1955_CR2","doi-asserted-by":"crossref","first-page":"1818","DOI":"10.1109\/TPAMI.2007.1098","volume":"29","author":"J Amores","year":"2007","unstructured":"Amores J, Sebe N, Radeva P (2007) Context-based object-class recognition and retrieval by generalized correlograms. IEEE Trans Pattern Anal Mach Intell 29:1818\u20131833","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1955_CR3","doi-asserted-by":"crossref","unstructured":"Ayache S, Quenot G (2008) Video Corpus annotation using active learning. In: European Conference on Information Retrieval (ECIR), pp. 187\u2013198. Glasgow, Scotland","DOI":"10.1007\/978-3-540-78646-7_19"},{"key":"1955_CR4","doi-asserted-by":"crossref","unstructured":"Behmo R, Paragios N, Prinet V (2008) Graph commute times for image representation. In: CVPR","DOI":"10.1109\/CVPR.2008.4587840"},{"key":"1955_CR5","doi-asserted-by":"crossref","unstructured":"Bres S, Jolion JM (1999) Detection of interest points for image indexation. In: VISUAL, pp. 427\u2013434","DOI":"10.1007\/3-540-48762-X_53"},{"key":"1955_CR6","doi-asserted-by":"crossref","unstructured":"Crandall D, Felzenszwalb P, Huttenlocher D (2005) Spatial priors for part-based recognition using statistical models. In: Proceedings of the 2005 I.E. Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905) - Volume 1 - Volume 01, CVPR\u201905, pp. 10\u201317. IEEE Computer Society, Washington, DC, USA","DOI":"10.1109\/CVPR.2005.329"},{"key":"1955_CR7","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1955_CR8","doi-asserted-by":"crossref","unstructured":"Elleuch N, Ben Animar A, Alimi AM (2010) A generic system for semantic video indexing by visual concept. In: I\/V Communications and Mobile Network (ISVC), 2010 5th International Symposium on, pp. 1\u20134. IEEE","DOI":"10.1109\/ISVC.2010.5656203"},{"key":"1955_CR9","doi-asserted-by":"crossref","unstructured":"Elleuch N, Zarka M, Ammar AB, Alimi AM (2011) A fuzzy ontology: based framework for reasoning in visual video content analysis and indexing. In: Proceedings of the Eleventh International Workshop on Multimedia Data Mining, p. 1. ACM","DOI":"10.1145\/2237827.2237828"},{"key":"1955_CR10","unstructured":"Elleuch N, Zarka M, Feki I, Ammar AB, Alimi AM (2010) Regimvid at trecvid 2010: Semantic indexing. In: TRECVID 2010. Citeseer"},{"key":"1955_CR11","doi-asserted-by":"crossref","unstructured":"Gemert JC, Geusebroek JM, Veenman CJ, Smeulders AW (2008) Kernel codebooks for scene categorization. In: Proceedings of the 10th European Conference on Computer Vision: Part III, ECCV\u201908, pp. 696\u2013709. Springer-Verlag, Berlin, Heidelberg","DOI":"10.1007\/978-3-540-88690-7_52"},{"key":"1955_CR12","doi-asserted-by":"crossref","unstructured":"Grauman K, Darrell T (2005) Efficient image matching with distributions of local invariant features. In: Proceedings of the 2005 I.E. Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905) - Volume 2 - Volume 02, CVPR\u201905, pp. 627\u2013634. IEEE Computer Society, Washington, DC, USA","DOI":"10.1109\/CVPR.2005.138"},{"key":"1955_CR13","unstructured":"Hauptmann A, Baron RV, y. Chen M, Christel M, Duygulu P, Huang C, Jin R, h. Lin W, Ng T, Moraveji N, Snoek CGM, Tzanetakis G, Yang J, Yan R, Wactlar HD (2003) Informedia at trecvid 2003: analyzing and searching broadcast news video. In: Proc. Of TRECVID"},{"key":"1955_CR14","doi-asserted-by":"crossref","unstructured":"Hauptmann AG, Yan R, Qi Y, Jin R, Christel MG, Derthick M, yu Chen M, Baron RV, Lin WH, Ng TD (2002) Video classification and retrieval with the informedia digital video library system. In: TREC","DOI":"10.6028\/NIST.SP.500-251.video-cmu-Hauptmann-video"},{"key":"1955_CR15","unstructured":"Helmer S, Helmer (2004) CS object recognition with many local features. In: In Workshop on Generative Model Based Vision (GMBV)"},{"key":"1955_CR16","doi-asserted-by":"crossref","unstructured":"Jiang W, Chang SF, Loui AC (2006) Active context-based concept fusion with partial user labels. In: IEEE International Conference on Image Processing (ICIP 06). Atlanta, GA, USA","DOI":"10.1109\/ICIP.2006.313129"},{"key":"1955_CR17","unstructured":"Jiang YG, Wang J, Chang SF, Ngo CW (2009) Domain adaptive semantic diffusion for large scale context-based video annotation. In: International Conference on Computer Vision (ICCV). Kyoto, Japan"},{"key":"1955_CR18","doi-asserted-by":"crossref","unstructured":"Jurie F, Triggs B (2005) Creating efficient codebooks for visual recognition. In: Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV\u201905) Volume 1 \u2013 Volume 01, ICCV\u201905, pp. 604\u2013610. IEEE Computer Society, Washington, DC, USA","DOI":"10.1109\/ICCV.2005.66"},{"key":"1955_CR19","unstructured":"Karray H, Wali A, Elleuch N, Ammar AB, Ellouze M, Feki I, Alimi AM (2008) Regim at trecvid2008: high-level features extraction and video search. In: TRECVID"},{"key":"1955_CR20","doi-asserted-by":"crossref","unstructured":"Kennedy LS, Chang SF (2007) A reranking approach for context-based concept fusion in video indexing and retrieval. In: Proceedings of the 6th ACM international conference on Image and video retrieval, CIVR\u201907, pp. 333\u2013340. ACM, New York, NY, USA","DOI":"10.1145\/1282280.1282331"},{"key":"1955_CR21","volume-title":"Self-organizing maps","year":"2001","unstructured":"Kohonen T, Schroeder MR, Huang TS (eds) (2001) Self-organizing maps, 3rd edn. Springer-Verlag New York, Inc., Secaucus","edition":"3"},{"key":"1955_CR22","doi-asserted-by":"crossref","unstructured":"Ksibi A, Elleuch N, Ammar AB, Alimi AM (2011) Semi-automatic soft collaborative annotation for semantic video indexing. In: EUROCON, pp. 1\u20136","DOI":"10.1109\/EUROCON.2011.5929417"},{"key":"1955_CR23","doi-asserted-by":"crossref","unstructured":"Laptev I, Marszalek M, Schmid C, Rozenfeld B (2008) Learning realistic human actions from movies. In: CVPR","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"1955_CR24","doi-asserted-by":"crossref","unstructured":"Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: CVPR (2), pp. 2169\u20132178","DOI":"10.1109\/CVPR.2006.68"},{"key":"1955_CR25","unstructured":"Lin CY, Tseng BL, Smith JR (2003) Video collaborative annotation forum: establishing ground-truth labels on large multimedia datasets. In: Proceedings of the TRECVID 2003 Workshop"},{"issue":"2","key":"1955_CR26","doi-asserted-by":"crossref","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":"1955_CR27","doi-asserted-by":"crossref","unstructured":"Marsza\u0142ek M, Schmid C (2006) Spatial weighting for bag-of-features. In: IEEE Conference on Computer Vision & Pattern Recognition, CVPR 2006, June, 2006, vol. 2, pp. 2118\u20132125. IEEE, New York, NY, Etats-Unis","DOI":"10.1109\/CVPR.2006.288"},{"key":"1955_CR28","doi-asserted-by":"crossref","unstructured":"Matas J, Chum O, Urban M, Pajdla T (2002) Robust wide baseline stereo from maximally stable extremal regions. In: BMVC, pp. 1\u201310","DOI":"10.5244\/C.16.36"},{"issue":"1","key":"1955_CR29","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1023\/B:VISI.0000027790.02288.f2","volume":"60","author":"K Mikolajczyk","year":"2004","unstructured":"Mikolajczyk K, Schmid C (2004) Scale & affine invariant interest point detectors. Int J Comput Vis 60(1):63\u201386","journal-title":"Int J Comput Vis"},{"issue":"1\u20132","key":"1955_CR30","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/s11263-005-3848-x","volume":"65","author":"K Mikolajczyk","year":"2005","unstructured":"Mikolajczyk K, Tuytelaars T, Schmid C, Zisserman A, Matas J, Schaffalitzky F, Kadir T, Gool LV (2005) A comparison of affine region detectors. Int J Comput Vis 65(1\u20132):43\u201372","journal-title":"Int J Comput Vis"},{"issue":"11","key":"1955_CR31","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller GA (1995) Wordnet: a lexical database for english. Commun ACM 38(11):39\u201341","journal-title":"Commun ACM"},{"key":"1955_CR32","unstructured":"Murphy P, Torralba A, Freeman W (2003) Using the forest to see the trees: a graphical model relating features, objects and scenes. In: Adv. Neur. Inform. Process. Syst. 16 (NIPS). MIT Press, Cambridge"},{"issue":"3","key":"1955_CR33","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/s11042-007-0161-4","volume":"39","author":"P Mylonas","year":"2008","unstructured":"Mylonas P, Athanasiadis T, Wallace M, Avrithis YS, Kollias SD (2008) Semantic representation of multimedia content: knowledge representation and semantic indexing. Multimedia Tools Appl 39(3):293\u2013327","journal-title":"Multimedia Tools Appl"},{"key":"1955_CR34","unstructured":"Mylonas Ph, Avrithis Y (2005) Context modelling for multimedia analysis. In: Proc. 5th Int. Interdisciplinary Conf. Modeling and Using Context (CONTEXT\u201905), Paris, France, Jul. 2005"},{"issue":"2","key":"1955_CR35","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1109\/TMM.2008.2009681","volume":"11","author":"P Mylonas","year":"2009","unstructured":"Mylonas P, Spyrou E, Avrithis Y, Kollias S (2009) Using visual context and region semantics for high-level concept detection. Trans Multi 11(2):229\u2013243","journal-title":"Trans Multi"},{"issue":"3","key":"1955_CR36","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1109\/MMUL.2006.63","volume":"13","author":"M Naphade","year":"2006","unstructured":"Naphade M, Smith JR, Tesic J, Chang SF, Hsu W, Kennedy L, Hauptmann A, Curtis J (2006) Large-scale concept ontology for multimedia. IEEE Multimedia 13(3):86\u201391","journal-title":"IEEE Multimedia"},{"key":"1955_CR37","doi-asserted-by":"crossref","unstructured":"Natsev A, Tesic J, Xie L, Yan R, Smith JR (2007) Ibm multimedia search and retrieval system. In: CIVR, p. 645","DOI":"10.1145\/1282280.1282373"},{"key":"1955_CR38","unstructured":"Ngo CW, Zhu S, Tan HK, Zhao W, Wei XY (2010) Vireo at trecvid 2010: semantic indexing, known-item search, and content-based copy detection. In: TRECVID"},{"key":"1955_CR39","unstructured":"Petersohn C (2004) Fraunhofer hhi at trecvid 2004: shot boundary detection system. In: Proc. TRECVID Workshop"},{"key":"1955_CR40","unstructured":"Punitha P, Guru DS, Vikram TN \u201cProceedings of the international conference on cognition and recognition relative spatial distance matrix: a novel and invariant data structure for representation and retrieval of exact match symbolic images\u201d"},{"issue":"2","key":"1955_CR41","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1023\/A:1026543900054","volume":"40","author":"Y Rubner","year":"2000","unstructured":"Rubner Y, Tomasi C, Guibas LJ (2000) The earth mover\u2019s distance as a metric for image retrieval. Int J Comput Vis 40(2):99\u2013121","journal-title":"Int J Comput Vis"},{"issue":"2","key":"1955_CR42","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1023\/A:1008199403446","volume":"37","author":"C Schmid","year":"2000","unstructured":"Schmid C, Mohr R, Bauckhage C (2000) Evaluation of interest point detectors. Int J Comput Vis 37(2):151\u2013172","journal-title":"Int J Comput Vis"},{"key":"1955_CR43","doi-asserted-by":"crossref","unstructured":"Smeaton AF, Over P, Kraaij W (2006) Evaluation campaigns and trecvid. In: MIR\u201906: Proceedings of the 8th ACM International Workshop on Multimedia Information Retrieval, pp. 321\u2013330. ACM Press, New York, NY, USA","DOI":"10.1145\/1178677.1178722"},{"issue":"12","key":"1955_CR44","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1109\/34.895972","volume":"22","author":"AWM Smeulders","year":"2000","unstructured":"Smeulders AWM, Worring M, Santini S, Gupta A, Jain R (2000) Content-based image retrieval at the end of the early years. IEEE Trans Pattern Anal Mach Intell 22(12):1349\u20131380","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1955_CR45","doi-asserted-by":"crossref","unstructured":"Smith J, Naphade M, Natsev A (2003) Multimedia semantic indexing using model vectors. In: Multimedia and Expo, 2003. ICME\u201903. Proceedings. 2003 International Conference on, vol. 2, pp. II\u2013445\u20138 vol.2","DOI":"10.1109\/ICME.2003.1221649"},{"issue":"10","key":"1955_CR46","doi-asserted-by":"crossref","first-page":"1678","DOI":"10.1109\/TPAMI.2006.212","volume":"28","author":"CGM Snoek","year":"2006","unstructured":"Snoek CGM, Worring M, Geusebroek JM, Koelma DC, Seinstra FJ, Smeulders AWM (2006) The semantic pathfinder: using an authoring metaphor for generic multimedia indexing. IEEE Trans Pattern Anal Mach Intell 28(10):1678\u20131689","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"1955_CR47","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1145\/1142020.1142021","volume":"2","author":"C Snoek","year":"2006","unstructured":"Snoek C, Worring M, Hauptmann AG (2006) Learning rich semantics from news video archives by style analysis. TOMCCAP 2(2):91\u2013108","journal-title":"TOMCCAP"},{"key":"1955_CR48","doi-asserted-by":"crossref","unstructured":"Snoek CGM, Worring M, Smeulders AWM (2005) Early versus late fusion in semantic video analysis. In: Proceedings of the 13th annual ACM international conference on Multimedia, MULTIMEDIA\u201905, pp. 399\u2013402. ACM, New York, NY, USA","DOI":"10.1145\/1101149.1101236"},{"key":"1955_CR49","unstructured":"Spyrou E, Mylonas P, Avrithis Y (2008) A visual context ontology for multimedia high-level concept detection. In: Kofod-Petersen A, Cassens J, Leake D, Zacarias M (eds) HCP-2008 Proceedings, PArt II, MRC 2008\u2014Fifth InternationalWorkshop on Modelling and Reasoning in Context, pp. 25\u201336. TELECOM Bretagne"},{"key":"1955_CR50","doi-asserted-by":"crossref","unstructured":"Torralba A (2005) Contextual influences on saliency. In: Neurobiology of attention. Academic, London","DOI":"10.1016\/B978-012375731-9\/50100-2"},{"key":"1955_CR51","doi-asserted-by":"crossref","unstructured":"Vesanto J, Alhoniemi E (2000) Clustering of the self-organizing map","DOI":"10.1109\/72.846731"},{"key":"1955_CR52","doi-asserted-by":"crossref","unstructured":"Volkmer T, Smith JR, Natsev AP (2005) A web-based system for collaborative annotation of large image and video collections: an evaluation and user study. In: Proceedings of the 13th annual ACM international conference on Multimedia, MULTIMEDIA\u201905, pp. 892\u2013901. ACM, New York, NY, USA","DOI":"10.1145\/1101149.1101341"},{"key":"1955_CR53","doi-asserted-by":"crossref","unstructured":"Wang L, Song D, Elyan E (2012) Improving bag-of-visual-words model with spatial-temporal correlation for video retrieval. In: Proceedings of the 21st ACM International Conference on Information and Knowledge Management, CIKM\u201912, pp. 1303\u20131312. ACM, New York, NY, USA","DOI":"10.1145\/2396761.2398433"},{"key":"1955_CR54","doi-asserted-by":"crossref","unstructured":"Wei XY, Jiang YG, Ngo CW (2009) Exploring inter-concept relationship with context space for semantic video indexing. In: Proceedings of the ACM International Conference on Image and Video Retrieval, CIVR\u201909, pp. 15:1\u201315:8. ACM, New York, NY, USA","DOI":"10.1145\/1646396.1646416"},{"issue":"2","key":"1955_CR55","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1109\/TMM.2008.2009692","volume":"11","author":"L Wu","year":"2009","unstructured":"Wu L, Hu Y, Li M, Yu N, Hua XS (2009) Scale-invariant visual language modeling for object categorization. Trans Multi 11(2):286\u2013294","journal-title":"Trans Multi"},{"issue":"1","key":"1955_CR56","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1007\/s11265-008-0314-3","volume":"61","author":"M Zampoglou","year":"2010","unstructured":"Zampoglou M, Papadimitriou T, Diamantaras KI (2010) From low-level features to semantic classes: spatial and temporal descriptors for video indexing. Signal Proc Syst 61(1):75\u201383","journal-title":"Signal Proc Syst"},{"key":"1955_CR57","doi-asserted-by":"crossref","unstructured":"Zha ZJ, Mei T, Hua XS, Qi GJ, Wang Z (2007) Refining video annotation by exploiting pairwise concurrent relation. In: Proceedings of the 15th international conference on Multimedia, MULTIMEDIA\u201907, pp. 345\u2013348. ACM, New York, NY, USA","DOI":"10.1145\/1291233.1291308"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-014-1955-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-014-1955-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-014-1955-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T14:56:56Z","timestamp":1746197816000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-014-1955-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4,25]]},"references-count":57,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2015,2]]}},"alternative-id":["1955"],"URL":"https:\/\/doi.org\/10.1007\/s11042-014-1955-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,4,25]]}}}