{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T13:56:56Z","timestamp":1758981416695,"version":"3.37.0"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2009,2,5]],"date-time":"2009-02-05T00:00:00Z","timestamp":1233792000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Univ Access Inf Soc"],"published-print":{"date-parts":[[2009,8]]},"DOI":"10.1007\/s10209-008-0141-0","type":"journal-article","created":{"date-parts":[[2009,2,4]],"date-time":"2009-02-04T14:41:09Z","timestamp":1233758469000},"page":"199-218","source":"Crossref","is-referenced-by-count":23,"title":["Towards computer-vision software tools to increase production and accessibility of video description for people with vision loss"],"prefix":"10.1007","volume":"8","author":[{"given":"Langis","family":"Gagnon","sequence":"first","affiliation":[]},{"given":"Samuel","family":"Foucher","sequence":"additional","affiliation":[]},{"given":"Maguelonne","family":"Heritier","sequence":"additional","affiliation":[]},{"given":"Marc","family":"Lalonde","sequence":"additional","affiliation":[]},{"given":"David","family":"Byrns","sequence":"additional","affiliation":[]},{"given":"Claude","family":"Chapdelaine","sequence":"additional","affiliation":[]},{"given":"James","family":"Turner","sequence":"additional","affiliation":[]},{"given":"Suzanne","family":"Mathieu","sequence":"additional","affiliation":[]},{"given":"Denis","family":"Laurendeau","sequence":"additional","affiliation":[]},{"given":"Nath Tan","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Denis","family":"Ouellet","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2009,2,5]]},"reference":[{"key":"141_CR1","unstructured":"Canadian Radio-television and Telecommunications Communication: Broadcasting Decision CRTC 2002-384. http:\/\/www.crtc.gc.ca\/archive\/ENG\/Decisions\/2002\/db2002-384.htm (2002)"},{"issue":"8","key":"141_CR2","first-page":"1","volume":"98","author":"PJ Piety","year":"2004","unstructured":"Piety, P.J.: The language system of audio description: an investigation as a discursive process. J. Vis. Impair. Blind. 98(8), 1\u201336 (2004)","journal-title":"J. Vis. Impair. Blind."},{"key":"141_CR3","unstructured":"Turner, J.M.: Some characteristics of audio description and the corresponding moving image. In: Preston, C.M., Medford, N.J. (eds.) Proceedings of the 61st ASIS Annual Meeting, Pittsburgh, 24\u201329 October 1998, Information Today, pp. 108\u2013117 (1998)"},{"issue":"4","key":"141_CR4","first-page":"222","volume":"31","author":"JM Turner","year":"2004","unstructured":"Turner, J.M., Colinet, E.: Using audio description for indexing moving images. Knowl. Org. 31(4), 222\u2013230 (2004)","journal-title":"Knowl. Org."},{"key":"141_CR5","unstructured":"Office of Communication: ITC guidance on standards for audio description. http:\/\/www.ofcom.org.uk\/static\/archive\/itc\/itc_publications\/codes_guidance\/audio_description\/index.asp.html (2000)"},{"key":"141_CR6","unstructured":"Canadian Network for Inclusive Cultural Exchange: Online video description guidelines. http:\/\/cnice.utoronto.ca\/guidelines\/video.php (2005)"},{"key":"141_CR7","unstructured":"Guidelines for video description. http:\/\/www.joeclark.org\/access\/description\/ad-principles.html"},{"key":"141_CR8","unstructured":"Mathieu, S.: Audiovision Interactive et Adaptable, Technical Report for the E-inclusion Research Network (2007)"},{"key":"141_CR9","doi-asserted-by":"crossref","unstructured":"Gagnon, L., Foucher, S., Lalibert\u00e9, F., Lalonde, M., Beaulieu, M.: Towards an application of content-based video indexing to computer-assisted descriptive video. In: Proceedings of Computer and Robot Vision 2006, 8 pp (on CD-ROM) (2006)","DOI":"10.1109\/CRV.2006.78"},{"key":"141_CR10","doi-asserted-by":"crossref","unstructured":"H\u00e9ritier, M., Gagnon, L., Foucher, S.: Places clustering of full-length film key-frames using latent aspects modeling over SIFT matches. IEEE Trans. Circuits Syst. Video Technol. (to appear) (2008)","DOI":"10.1109\/TCSVT.2009.2017304"},{"key":"141_CR11","doi-asserted-by":"crossref","unstructured":"Foucher, S., Gagnon, L.: Automatic detection and clustering of actor faces based on spectral clustering techniques. In: Proceedings of Computer and Robot Vision 2007, 8 pp (on CD-ROM) (2007)","DOI":"10.1109\/CRV.2007.13"},{"key":"141_CR12","doi-asserted-by":"crossref","unstructured":"Lalonde, M., Gagnon, L.: Key-text spotting in documentary videos using Adaboost. In: Proceedings of the IS&T\/SPIE Symposium on Electronic Imaging: Applications of Neural Networks and Machine Learning in Image Processing X (SPIE #6064B) (2006)","DOI":"10.1117\/12.641924"},{"key":"141_CR13","unstructured":"Branje, C., Marshall, S., Tyndall, A., Fels, D.I.: LiveDescribe. In: Proceedings of the AMCIS 2006 (2006)"},{"key":"141_CR14","unstructured":"TRECVID. http:\/\/www-nlpir.nist.gov\/projects\/trecvid\/"},{"key":"141_CR15","unstructured":"State-of-the-art on Multimedia Search Engines, Technical Report D2.1. Chorus Project Consortium (2007)"},{"key":"141_CR16","unstructured":"CIMWOS project. http:\/\/www.xanthi.ilsp.gr\/cimwos"},{"key":"141_CR17","unstructured":"SCHEMA network of excellence. http:\/\/www.iti.gr\/SCHEMA\/index.html"},{"key":"141_CR18","unstructured":"VIZIR project. http:\/\/vizir.ims.tuwien.ac.at\/index.html"},{"key":"141_CR19","unstructured":"Center for Digital Video Processing. http:\/\/www.cdvp.dcu.i.e"},{"key":"141_CR20","unstructured":"CALIPH and EMIR project. http:\/\/caliph-emir.sourceforge.net"},{"key":"141_CR21","unstructured":"IBM VideoAnnEx project. http:\/\/www.research.ibm.com\/VideoAnnEx"},{"key":"141_CR22","unstructured":"Ricoh MovieTool project. http:\/\/www.ricoh.co.jp\/src\/multimedia\/MovieTool"},{"key":"141_CR23","unstructured":"IBM Marvel project. http:\/\/mp7.watson.ibm.com\/marvel"},{"key":"141_CR24","unstructured":"MADIS project. http:\/\/madis.crim.ca"},{"key":"141_CR25","doi-asserted-by":"crossref","unstructured":"Gagnon, L., Foucher, S., Gouaillier, V., Brousseau, J., Boulianne, G., Osterrath, F., Chapdelaine, C., Brun, C., Dutrisac, J., St-Onge, F., Champagne, B., Lu, X.: MPEG-7 Audio-Visual Indexing Test-Bed for Video Retrieval, IS&T\/SPIE Electronic Imaging 2004: Internet Imaging V (SPIE #5304), pp. 319\u2013329 (2003)","DOI":"10.1117\/12.524495"},{"key":"141_CR26","unstructured":"Foucher, S., H\u00e9ritier, M., Lalonde, M., Byrns, D., Chapdelaine, C., Gagnon, L.: Proof-of-concept software tools for video content extraction applied to computer-assisted descriptive video, and results of consultations with producers, technical report, CRIM-07\/04-07, 2007 (2007)"},{"key":"141_CR27","unstructured":"Mathieu, S., Turner, J.M.: Audiovision interactive et adaptable, technical report, 2007. http:\/\/hdl.handle.net\/1866\/1307 (2007)"},{"key":"141_CR28","unstructured":"Turner, J.M., Mathieu, S.: Audio description for indexing films, World Library and Information Congress (IFLA), Durban. http:\/\/members.e-inclusion.crim.ca\/files\/articles\/IFLA-en.pdf (2007)"},{"issue":"5","key":"141_CR29","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1177\/0145482X0610000507","volume":"100","author":"DI Fels","year":"2006","unstructured":"Fels, D.I., Udo, J.P., Diamond, J.E., Diamond, J.I.: A first person narrative approach to video description for animated comedy. J. Vis. Impair. Blind. 100(5), 295\u2013305 (2006)","journal-title":"J. Vis. Impair. Blind."},{"issue":"4","key":"141_CR30","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1109\/TMM.2002.802021","volume":"4","author":"J Vendrig","year":"2000","unstructured":"Vendrig, J., Worring, M.: Systematic evaluation of logical story unit segmentation. IEEE Trans. Multimed. 4(4), 492\u2013499 (2000)","journal-title":"IEEE. Trans. Multimed"},{"key":"141_CR31","unstructured":"Bovik, A.C. (ed.): Handbook of Image and Video Processing. Academic Press, New York (2000)"},{"key":"141_CR32","doi-asserted-by":"crossref","unstructured":"Schaffalitzky, F., Zisserman, A.: Automated location matching in movies. Comput. Vis. Image Underst. 42:236\u2013264 (2003)","DOI":"10.1016\/j.cviu.2003.06.008"},{"key":"141_CR33","doi-asserted-by":"crossref","unstructured":"Hofmann, T.: Probabilistic Latent Semantic Indexing. In: SIGIR (1999)","DOI":"10.1145\/312624.312649"},{"key":"141_CR34","doi-asserted-by":"crossref","unstructured":"Bosch, A., Zisserman, A., Munoz, S.: Scene Classification via pLSA. In: ECCV (2006)","DOI":"10.1007\/11744085_40"},{"key":"141_CR35","doi-asserted-by":"crossref","unstructured":"Quelhas, P., Monay, F., Odobez, J.M., Gatica-Perez, D., Tuytelaars, T., Van Gool, L.: Modeling Scenes with Local Descriptors and Latent Aspects. In: ICCV (2005)","DOI":"10.1109\/ICCV.2005.152"},{"key":"141_CR36","doi-asserted-by":"crossref","unstructured":"Fei-Fei, L., Perona, P.: A Bayesian Hierarchical Model for Learning Natural Scene Categories. In: CVPR (2005)","DOI":"10.1109\/CVPR.2005.16"},{"key":"141_CR37","doi-asserted-by":"crossref","unstructured":"Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering objects categories in image collection, MIT AI Lab Memo AIM-2005-005 (2005)","DOI":"10.1109\/ICCV.2005.77"},{"key":"141_CR38","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Distinctive Image Features from Scale-invariant Keypoints. In: IJCV (2004)","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"141_CR39","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3, 993\u20131022 (2003)","journal-title":"J Mach Learn Res"},{"key":"141_CR40","unstructured":"Ng, A.Y., Jordan, M., Weiss, Y.: On Spectral Clustering: Analysis and an Algorithm. In: NIPS (2002)"},{"key":"141_CR41","doi-asserted-by":"crossref","unstructured":"Viola, P., Jones, M.: Robust real-time face detection. IJCV 57(2) (2004)","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"141_CR42","doi-asserted-by":"crossref","unstructured":"Gagnon, L., Lalibert\u00e9, F., Foucher, S., Laurendeau, D., Branzan Albu, A.: A System for Tracking and Recognizing Pedestrian Faces using a Network of Loosely Coupled Cameras, SPIE Defense and Security: Visual Information Processing XV (SPIE #6246), Orlando (2006)","DOI":"10.1117\/12.663648"},{"issue":"1","key":"141_CR43","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1109\/TPAMI.2004.1261097","volume":"26","author":"J Yang","year":"2004","unstructured":"Yang, J., Zhang, D., Frangi, A.F., Yanf, J.: Two-dimensional PCA: a new approach to appearance-based face representation and recognition. Trans. Pattern Anal. Mach. Intell. 26(1), 131\u2013137 (2004)","journal-title":"Trans Pattern Anal Mach Intell"},{"key":"141_CR44","doi-asserted-by":"crossref","unstructured":"Kong, H., Li, X., Wang, L., Teoh, E.K., Wang, J.G., Venkateswarlu, R.: Generalized 2D principal component analysis. In: IEEE International Joint Conference on Neural Networks (IJCNN) (2005)","DOI":"10.1016\/j.neunet.2005.06.041"},{"issue":"1","key":"141_CR45","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.patcog.2005.08.002","volume":"39","author":"D Zhang","year":"2006","unstructured":"Zhang, D., Zhou, Z.H., Chen, S.: Diagonal principal component analysis for face recognition. Pattern Recognit. 39(1), 140\u2013142 (2006)","journal-title":"Pattern Recognit"},{"issue":"5","key":"141_CR46","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1007\/s005300050140","volume":"7","author":"T Sato","year":"1999","unstructured":"Sato, T., Kanade, T., Hughes, E.K., Smith, M.A., Satoh, S.: VideoOCR: indexing digital news libraries by recognition of superimposed caption. ACM J. Multime. Syst. 7(5), 385\u2013395 (1999)","journal-title":"ACM J Multimed Syst"},{"issue":"4","key":"141_CR47","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1109\/76.999203","volume":"12","author":"R Lienhart","year":"2002","unstructured":"Lienhart, R., Wernicke, A.: Localizing and segmenting text in images and videos. IEEE Trans. Circuits Syst. Video Technol. 12(4), 256\u2013268 (2002)","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"141_CR48","unstructured":"Chen, X., Yuille, A.L.: Detecting and Reading Text in Natural Scenes. In: CVPR, vol. II, pp. 366\u2013373 (2004)"},{"key":"141_CR49","unstructured":"http:\/\/www.up.univ-mrs.fr\/veronis\/data\/bigrammes.html"},{"key":"141_CR50","unstructured":"Ouellet, D., Nguyen, N.T., Dung, V.V., Laurendeau, D.: Gait and Gesture Description, Technical Report, Laval University (2007)"},{"key":"141_CR51","unstructured":"Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: International Joint Conference on Artificial Intelligence, pp. 674\u2013679 (1981)"},{"key":"141_CR52","unstructured":"Tomasi, C., Kanade, T.: Detection and Tracking of Point Features, Carnegie Mellon University Technical Report CMU-CS-91-132 (1991)"},{"key":"141_CR53","unstructured":"Birchfield, S.: KLT: an Implementation of the Kanade-Lucas-Tomasi Feature Tracker. http:\/\/www.ces.clemson.edu\/~stb\/klt"},{"key":"141_CR54","unstructured":"Bailer, W., Schallauer, P., Thallinger, G.: Camera Motion Detection, Joanneum Research. In: TRECVID (2005)"},{"key":"141_CR55","unstructured":"Birchfield, S.: Derivation of Kanade-Lucas-Tomasi Tracking Equation. http:\/\/www.ces.clemson.edu\/~stb\/klt\/birchfield-klt-derivation.pdf (unpublished) (1997)"},{"key":"141_CR56","doi-asserted-by":"crossref","unstructured":"Bezdec, J.C.: Pattern Recognition with Fuzzy Objective Function Algorithms, Plenum Press, New York (1981)","DOI":"10.1007\/978-1-4757-0450-1"},{"key":"141_CR57","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/0020-0190(91)90233-8","volume":"38","author":"G Rote","year":"1991","unstructured":"Rote, G.: Computing the minimum Hausdorff distance between two point sets on a line under translation. Inf. Process. Lett. 38, 123\u2013127 (1991)","journal-title":"Inf Process Lett"},{"key":"141_CR58","unstructured":"AVISynth. http:\/\/avisynth.org"}],"container-title":["Universal Access in the Information Society"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10209-008-0141-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10209-008-0141-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10209-008-0141-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T11:19:33Z","timestamp":1738927173000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10209-008-0141-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,2,5]]},"references-count":58,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2009,8]]}},"alternative-id":["141"],"URL":"https:\/\/doi.org\/10.1007\/s10209-008-0141-0","relation":{},"ISSN":["1615-5289","1615-5297"],"issn-type":[{"type":"print","value":"1615-5289"},{"type":"electronic","value":"1615-5297"}],"subject":[],"published":{"date-parts":[[2009,2,5]]}}}