{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T03:35:18Z","timestamp":1793158518279,"version":"4.5.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,3,26]],"date-time":"2013-03-26T00:00:00Z","timestamp":1364256000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2014,5]]},"DOI":"10.1007\/s11042-013-1419-7","type":"journal-article","created":{"date-parts":[[2013,3,25]],"date-time":"2013-03-25T08:48:11Z","timestamp":1364201291000},"page":"413-432","source":"Crossref","is-referenced-by-count":71,"title":["An innovative web-based collaborative platform for video annotation"],"prefix":"10.1007","volume":"70","author":[{"given":"Isaak","family":"Kavasidis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simone","family":"Palazzo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto Di","family":"Salvo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniela","family":"Giordano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Concetto","family":"Spampinato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2013,3,26]]},"reference":[{"issue":"6","key":"1419_CR1","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1109\/MC.2006.196","volume":"39","author":"LV Ahn","year":"2006","unstructured":"Ahn LV (2006) Games with a purpose. Computer 39(6):92\u201394","journal-title":"Computer"},{"key":"1419_CR2","doi-asserted-by":"crossref","unstructured":"Ambardekar A, Nicolescu M, Dascalu S (2009) Ground truth verification tool (GTVT) for video surveillance systems. In: Proceedings of the 2009 second international conferences on advances in computer-human interactions, ser. ACHI \u201909, pp 354\u2013359","DOI":"10.1109\/ACHI.2009.17"},{"key":"1419_CR3","doi-asserted-by":"crossref","unstructured":"Barbour B, Ricanek Jr K (2012) An interactive tool for extremely dense landmarking of faces. In: Proceedings of the 1st international workshop on visual interfaces for ground truth collection in computer vision applications, ser. VIGTA \u201912. ACM, New York, pp 13:1\u201313:5","DOI":"10.1145\/2304496.2304509"},{"issue":"6","key":"1419_CR4","doi-asserted-by":"crossref","first-page":"1709","DOI":"10.1109\/TIP.2010.2101613","volume":"20","author":"O Barnich","year":"2011","unstructured":"Barnich O, Van Droogenbroeck M (2011) ViBe: a universal background subtraction algorithm for video sequences. IEEE Trans Image Process 20(6):1709\u20131724 [Online]. Available: http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/21189241","journal-title":"IEEE Trans Image Process"},{"issue":"9","key":"1419_CR5","doi-asserted-by":"crossref","first-page":"3101","DOI":"10.1105\/tpc.111.088153","volume":"23","author":"GW Bassel","year":"2011","unstructured":"Bassel GW, Glaab E, Marquez J, Holdsworth MJ, Bacardit J (2011) Functional network construction in Arabidopsis using rule-based machine learning on large-scale data sets. Plant Cell 23(9):3101\u20133116","journal-title":"Plant Cell"},{"key":"1419_CR6","doi-asserted-by":"crossref","unstructured":"Bertini M, Del Bimbo A, Torniai C (2005) Automatic video annotation using ontologies extended with visual information. In: Proceedings of the 13th annual ACM international conference on multimedia, ser. MULTIMEDIA \u201905, pp 395\u2013398","DOI":"10.1145\/1101149.1101235"},{"key":"1419_CR7","doi-asserted-by":"crossref","unstructured":"Biewald L (2012) Massive multiplayer human computation for fun, money, and survival. In: Proceedings of the 11th international conference on current trends in web engineering, ser. ICWE\u201911, pp 171\u2013176","DOI":"10.1007\/978-3-642-27997-3_18"},{"key":"1419_CR8","first-page":"655","volume-title":"Advances in neural information processing systems","author":"A Blake","year":"1996","unstructured":"Blake A, Isard M (1996) The condensation algorithm\u2014conditional density propagation and applications to visual tracking. In: Advances in neural information processing systems. MIT Press, pp 655\u2013668"},{"issue":"1","key":"1419_CR9","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1177\/1354856507084420","volume":"14","author":"D Brabham","year":"2008","unstructured":"Brabham D (2008) Crowdsourcing as a model for problem solving an introduction and cases. Convergence 14(1):75\u201390","journal-title":"Convergence"},{"issue":"6","key":"1419_CR10","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","volume":"8","author":"J Canny","year":"1986","unstructured":"Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679\u2013698","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1419_CR11","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1145\/57167.57203","volume-title":"Proceedings of the SIGCHI conference on human factors in computing systems, ser. CHI \u201988","author":"JP Chin","year":"1988","unstructured":"Chin JP, Diehl VA, Norman KL (1988) Development of an instrument measuring user satisfaction of the human-computer interface. In: Proceedings of the SIGCHI conference on human factors in computing systems, ser. CHI \u201988. ACM, New York, pp 213\u2013218"},{"key":"1419_CR12","doi-asserted-by":"crossref","unstructured":"Doerman D, Mihalcik D (2000) Tools and techniques for video performance evaluation. In: Proceedings of 15th international conference on pattern recognition, vol 4, pp 167\u2013170","DOI":"10.1109\/ICPR.2000.902888"},{"key":"1419_CR13","doi-asserted-by":"crossref","first-page":"1398","DOI":"10.1109\/TITS.2011.2159266","volume":"12","author":"A Faro","year":"2011","unstructured":"Faro A, Giordano D, Spampinato C (2011) Adaptive background modeling integrated with luminosity sensors and occlusion processing for reliable vehicle detection. IEEE Trans Intell Transp Syst 12:1398\u20131412","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"1","key":"1419_CR14","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.cviu.2005.09.012","volume":"106","author":"L Fei-Fei","year":"2007","unstructured":"Fei-Fei L, Fergus R, Perona P (2007) Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. Comput Vis Image Underst 106(1):59\u201370","journal-title":"Comput Vis Image Underst"},{"key":"1419_CR15","unstructured":"Fisher R (2004) CAVIAR test case scenarios. Online Book"},{"key":"1419_CR16","doi-asserted-by":"crossref","unstructured":"Freund Y, Schapire RE (1995) A decision-theoretic generalization of on-line learning and an application to boosting. In: Computational learning theory. Springer, pp 23\u201337","DOI":"10.1007\/3-540-59119-2_166"},{"key":"1419_CR17","doi-asserted-by":"crossref","unstructured":"Giordano D, Kavasidis I, Pino C, Spampinato C (2011) A semantic-based and adaptive architecture for automatic multimedia retrieval composition. In: 2011 9th international workshop on content-based multimedia indexing (CBMI), pp 181\u2013186","DOI":"10.1109\/CBMI.2011.5972542"},{"key":"1419_CR18","unstructured":"Griffin G, Holub A, Perona P (2007) Caltech-256 object category dataset. California Institute of Technology, Tech. Rep. 7694"},{"key":"1419_CR19","doi-asserted-by":"crossref","unstructured":"Heroux P, Barbu E, Adam S, Trupin E (2007) Automatic ground-truth generation for document image analysis and understanding. In: Proceedings of the ninth international conference on document analysis and recognition, ser. ICDAR \u201907, vol 01, pp 476\u2013480","DOI":"10.1109\/ICDAR.2007.4378755"},{"issue":"6","key":"1419_CR20","first-page":"1","volume":"14","author":"J Howe","year":"2006","unstructured":"Howe J (2006) The rise of crowdsourcing. Wired Magazine 14(6):1\u20134","journal-title":"Wired Magazine"},{"key":"1419_CR21","unstructured":"Jaynes C, Webb S, Steele R, Xiong Q (2002) An open development environment for evaluation of video surveillance systems. In: PETS02, pp 32\u201339"},{"key":"1419_CR22","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1007\/BF00133570","volume":"1","author":"M Kass","year":"1988","unstructured":"Kass M, Witkin A, Terzopoulos D (1988) Snakes: active contour models. Int J Comput Vis 1: 321\u2013331","journal-title":"Int J Comput Vis"},{"key":"1419_CR23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2304496.2304502","volume-title":"VIGTA \u201912: proceedings of the 1st international workshop on visual interfaces for ground truth collection in computer vision applications","author":"I Kavasidis","year":"2012","unstructured":"Kavasidis I, Palazzo S, Di Salvo R, Giordano D, Spampinato C (2012) A semi-automatic tool for detection and tracking ground truth generation in videos. In: VIGTA \u201912: proceedings of the 1st international workshop on visual interfaces for ground truth collection in computer vision applications. ACM, New York, pp 1\u20135"},{"key":"1419_CR24","unstructured":"Kawahara T, Nanjo H, Shinozaki T, Furui S (2003) Benchmark test for speech recognition using the corpus. In: Proceedings of ISCA & IEEE workshop on spontaneous speech processing and recognition, pp 135\u2013138"},{"key":"1419_CR25","doi-asserted-by":"crossref","unstructured":"Mai HT, Kim MH (2013) Utilizing similarity relationships among existing data for high accuracy processing of content-based image retrieval. Multimed Tools Appl. doi: 10.1007\/s11042-013-1360-9","DOI":"10.1007\/s11042-013-1360-9"},{"key":"1419_CR26","doi-asserted-by":"crossref","unstructured":"Marques O, Barman N (2003) Semi-automatic semantic annotation of images using machine learning techniques. The Semantic Web-ISWC 2003, pp 550\u2013565","DOI":"10.1007\/978-3-540-39718-2_35"},{"key":"1419_CR27","doi-asserted-by":"crossref","unstructured":"Martin D, Fowlkes C, Tal D, Malik J (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proc. 8th int\u2019l conf. computer vision, vol 2, pp 416\u2013423","DOI":"10.1109\/ICCV.2001.937655"},{"key":"1419_CR28","unstructured":"Mihalcea R, Corley C, Strapparava C (2006) Corpus-based and knowledge-based measures of text semantic similarity. In: Proceedings of the national conference on artificial intelligence, vol 21, no 1. AAAI Press, Menlo Park, MIT Press, Cambridge, p 775, 1999"},{"key":"1419_CR29","doi-asserted-by":"crossref","unstructured":"Moehrmann J, Heidemann G (2012) Efficient annotation of image data sets for computer vision applications. In: Proceedings of the 1st international workshop on visual interfaces for ground truth collection in computer vision applications, ser. VIGTA \u201912, pp 2:1\u20132:6","DOI":"10.1145\/2304496.2304498"},{"key":"1419_CR30","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/s11263-007-0118-0","volume":"80","author":"J Mutch","year":"2008","unstructured":"Mutch J, Lowe D (2008) Object class recognition and localization using sparse features with limited receptive fields. Int J Comput Vis 80:45\u201357","journal-title":"Int J Comput Vis"},{"key":"1419_CR31","doi-asserted-by":"crossref","unstructured":"Quinn AJ, Bederson BB (2011) Human computation: a survey and taxonomy of a growing field. In: Proceedings of the 2011 annual conference on human factors in computing systems, ser. CHI \u201911, pp 1403\u20131412","DOI":"10.1145\/1978942.1979148"},{"key":"1419_CR32","unstructured":"Rashtchian C, Young P, Hodosh M, Hockenmaier J (2010) Collecting image annotations using Amazon\u2019s Mechanical Turk. In: Proceedings of the NAACL HLT 2010 workshop on creating speech and language data with Amazon\u2019s Mechanical Turk, ser. CSLDAMT \u201910, pp 139\u2013147"},{"issue":"3","key":"1419_CR33","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1145\/1015706.1015720","volume":"23","author":"C Rother","year":"2004","unstructured":"Rother C, Kolmogorov V, Blake A (2004) \u201cGrabCut\u201d: interactive foreground extraction using iterated graph cuts. ACM Trans Graph 23(3):309\u2013314","journal-title":"ACM Trans Graph"},{"key":"1419_CR34","doi-asserted-by":"crossref","unstructured":"Rotter P (2013) Relevance feedback based on n-tuplewise comparison and the ELECTRE methodology and an application in content-based image retrieval. Multimed Tools Appl. doi: 10.1007\/s11042-013-1384-1","DOI":"10.1007\/s11042-013-1384-1"},{"issue":"1\u20133","key":"1419_CR35","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","volume":"77","author":"BC Russell","year":"2008","unstructured":"Russell BC, Torralba A, Murphy KP, Freeman WT (2008) Labelme: a database and web-based tool for image annotation. Int J Comput Vis 77(1\u20133):157\u2013173","journal-title":"Int J Comput Vis"},{"issue":"1","key":"1419_CR36","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s11263-009-0273-6","volume":"87","author":"L Sigal","year":"2010","unstructured":"Sigal L, Balan A, Black M (2010) Humaneva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. Int J Comput Vis 87(1):4\u201327. doi: 10.1007\/s11263-009-0273-6","journal-title":"Int J Comput Vis"},{"key":"1419_CR37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/CVPRW.2008.4562953","volume-title":"2008 IEEE computer society conference on computer vision and pattern recognition workshops","author":"A Sorokin","year":"2008","unstructured":"Sorokin A, Forsyth D (2008) Utility data annotation with Amazon Mechanical Turk. In: 2008 IEEE computer society conference on computer vision and pattern recognition workshops. IEEE, Piscataway, pp 1\u20138"},{"key":"1419_CR38","volume-title":"VIGTA \u201912: proceedings of the 1st international workshop on visual interfaces for ground truth collection in computer vision applications","year":"2012","unstructured":"Spampinato C, Boom B, He J (eds) (2012) VIGTA \u201912: proceedings of the 1st international workshop on visual interfaces for ground truth collection in computer vision applications. ACM, New York"},{"key":"1419_CR39","doi-asserted-by":"crossref","unstructured":"Spampinato C, Palazzo S, Boom B, van Ossenbruggen J, Kavasidis I, Di R, Salvo Lin F, Giordano D, Hardman L, Fisher R (2012) Understanding fish behavior during typhoon events in real-life underwater environments. Multimed Tools Appl. doi: 10.1007\/s11042-012-1101-5","DOI":"10.1007\/s11042-012-1101-5"},{"key":"1419_CR40","unstructured":"Spampinato C, Palazzo S, Giordano D, Kavasidis I, Lin F, Lin Y (2012) Covariance based fish tracking in real-life underwater environment. In: International conference on computer vision theory and applications, VISAPP 2012, pp 409\u2013414"},{"key":"1419_CR41","doi-asserted-by":"crossref","unstructured":"Stork DG (1999) Character and document research in the open mind initiative. In: Proceedings of the fifth international conference on document analysis and recognition, ser. ICDAR \u201999","DOI":"10.1109\/ICDAR.1999.791712"},{"key":"1419_CR42","doi-asserted-by":"crossref","unstructured":"Utasi A, Benedek C (2012) A multi-view annotation tool for people detection evaluation. In: Proceedings of the 1st international workshop on visual interfaces for ground truth collection in computer vision applications, ser. VIGTA \u201912, pp 3:1\u20133:6","DOI":"10.1145\/2304496.2304499"},{"key":"1419_CR43","doi-asserted-by":"crossref","unstructured":"von Ahn L, Dabbish L (2004) Labeling images with a computer game. In: Proceedings of the SIGCHI conference on human factors in computing systems, ser. CHI \u201904. ACM, New York, pp 319\u2013326 [Online]. Available: http:\/\/doi.acm.org\/10.1145\/985692.985733","DOI":"10.1145\/985692.985733"},{"key":"1419_CR44","unstructured":"Wache H, Voegele T, Visser U, Stuckenschmidt H, Schuster G, Neumann H, H\u00fcbner S (2001) Ontology-based integration of information-a survey of existing approaches. In: IJCAI-01 workshop: ontologies and information sharing, vol 2001. Citeseer, pp 108\u2013117"},{"key":"1419_CR45","doi-asserted-by":"crossref","unstructured":"Yuen J, Russell BC, Liu C, Torralba A (2009) Labelme video: building a video database with human annotations. In: ICCV\u201909, pp 1451\u20131458","DOI":"10.1109\/ICCV.2009.5459289"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-013-1419-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-013-1419-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-013-1419-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,11]],"date-time":"2019-07-11T09:24:39Z","timestamp":1562837079000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-013-1419-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,3,26]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,5]]}},"alternative-id":["1419"],"URL":"https:\/\/doi.org\/10.1007\/s11042-013-1419-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,3,26]]}}}