{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T13:52:22Z","timestamp":1758981142821,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,8,31]],"date-time":"2018-08-31T00:00:00Z","timestamp":1535673600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Univ Access Inf Soc"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s10209-018-0634-4","type":"journal-article","created":{"date-parts":[[2018,8,31]],"date-time":"2018-08-31T12:51:39Z","timestamp":1535719899000},"page":"99-111","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["CineAD: a system for automated audio description script generation for the visually impaired"],"prefix":"10.1007","volume":"19","author":[{"given":"Virginia P.","family":"Campos","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5953-5435","authenticated-orcid":false,"given":"Tiago M. U.","family":"de Ara\u00fajo","sequence":"additional","affiliation":[]},{"given":"Guido L.","family":"de Souza Filho","sequence":"additional","affiliation":[]},{"given":"Luiz M. G.","family":"Gon\u00e7alves","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,31]]},"reference":[{"key":"634_CR1","unstructured":"ANCINE: Brazilian nations cinema agency (ancine)\u2013 Regulatory News: accessibility (2015). \nhttp:\/\/www.ancine.gov.br\/sites\/default\/files\/consultas-publicas\/Not%C3%ADcia%20Regulat%C3%B3ria%20-%20acessibilidade%20exibicao.pdf\n\n.\u00a0Accessed Dec 2015"},{"key":"634_CR2","first-page":"156","volume":"1\/2","author":"VLS Araujo","year":"2006","unstructured":"Araujo, V.L.S.: O processo de legendagem no Brasil (the subtitling process in Brazil). Revista do GELNE (GELNE Magazine), Fortaleza 1\/2, 156\u2013159 (2006)","journal-title":"Revista do GELNE (GELNE Magazine), Fortaleza"},{"issue":"1","key":"634_CR3","first-page":"78","volume":"49","author":"B Benecke","year":"2004","unstructured":"Benecke, B.: Audio-description. Meta Transl. J. 49(1), 78\u201380 (2004)","journal-title":"Meta Transl. J."},{"key":"634_CR4","unstructured":"Bojanowski, P., Lajugie, R., Bach, F.R., Laptev, I., Ponce, J., Schmid, C., Sivic, J.: Weakly supervised action labeling in videos under ordering constraints. European Conference on Computer Vision - ECCV (2014), \u00a0Zurich, Switzerland. Springer, 8693 (Part V), pp. 628\u2013643 (2014)"},{"key":"634_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-4625-2","volume-title":"Experimentation in Software Engineering: An Introduction","author":"C Wohlin","year":"2000","unstructured":"Wohlin, C., Runeson, P., Host, M., Ohlsson, M.C., Regnell, B., Wessl\u00e9n, A.: Experimentation in Software Engineering: An Introduction. Kluwer Academic Publisher, Norwell, MA, USA (2000)"},{"key":"634_CR6","doi-asserted-by":"publisher","unstructured":"Chapdelaine, C., Gagnon, L.: Accessible videodescription on-demand. In: Proceedings of the 11th International ACM SIGACCESS Conference on Computers and Accessibility, Assets \u201909, pp. 221\u2013222. ACM, New York, NY, USA (2009). \nhttps:\/\/doi.org\/10.1145\/1639642.1639685","DOI":"10.1145\/1639642.1639685"},{"key":"634_CR7","first-page":"2422","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"X Chen","year":"2015","unstructured":"Chen, X., Zitnick, C.L.: Mind\u2019s eye: a recurrent visual representation for image caption generation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2422\u20132431. IEEE, Boston, MA (2015)"},{"key":"634_CR8","doi-asserted-by":"publisher","unstructured":"Cour, T., Sapp, B., Jordan, C., Taskar, B.: Learning from ambiguously labeled images. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20\u201325 June 2009, Miami, Florida, USA, pp. 919\u2013926 (2009). \nhttps:\/\/doi.org\/10.1109\/CVPRW.2009.5206667","DOI":"10.1109\/CVPRW.2009.5206667"},{"key":"634_CR9","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. NIPS'16 Proceedings of the 30th international conference on neural information processing systems - Barcelona, Spain, pp. 379\u2013387\u00a0(2016)"},{"key":"634_CR10","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1016\/j.ins.2014.04.008","volume":"281","author":"TMU Ara\u00fajo De","year":"2014","unstructured":"De Ara\u00fajo, T.M.U., Ferreira, F.L.S., Silva, D.A.N.S., Oliveira, L.D., Falc\u00e3o, E.L., Domingues, L.A., Martins, V.F., Portela, I.A.C., N\u00f3brega, Y.S., Lima, H.R.G., Souza Filho, G.L., Tavares, T.A., Duarte, A.N.: An approach to generate and embed sign language video tracks into multimedia contents. Inf. Sci. 281, 762\u2013780 (2014). \nhttps:\/\/doi.org\/10.1016\/j.ins.2014.04.008","journal-title":"Inf. Sci."},{"key":"634_CR11","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","volume-title":"IEEE Transactions on Pattern Analysis and Machine intelligence (CVPR 15)","author":"J Donahue","year":"2017","unstructured":"Donahue, J., Hendricks, L.A., Rohrbach, M., Venugopalan, S., Guadarrama, S.,\u00a0Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. IEEE Transactions on Pattern Analysis and Machine intelligence (CVPR 15), vol. 39, no. 4, pp. 677\u2013691. IEEE, Washington, DC, USA (2017). \nhttps:\/\/doi.org\/10.1109\/TPAMI.2016.2599174"},{"key":"634_CR12","doi-asserted-by":"crossref","unstructured":"Duchenne, O., Laptev, I., Sivic, J., Bach, F.R., Ponce, J.: Automatic annotation of human actions in video. In: 2009 IEEE 12th International Conference on Computer Vision (2009)","DOI":"10.1109\/ICCV.2009.5459279"},{"issue":"2","key":"634_CR13","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1145\/321510.321519","volume":"16","author":"HP Edmundson","year":"1969","unstructured":"Edmundson, H.P.: New methods in automatic extracting. J. ACM 16(2), 264\u2013285 (1969). \nhttps:\/\/doi.org\/10.1145\/321510.321519","journal-title":"J. ACM"},{"key":"634_CR14","doi-asserted-by":"publisher","unstructured":"Encelle, B., Beldame, M.O., Pri\u00e9, Y.: Towards the usage of pauses in audio-described videos. In: Proceedings of the 10th International Cross-Disciplinary Conference on Web Accessibility, W4A \u201913, pp. 31:1\u201331:4. ACM, New York, NY, USA (2013). \nhttps:\/\/doi.org\/10.1145\/2461121.2461130","DOI":"10.1145\/2461121.2461130"},{"key":"634_CR15","unstructured":"Fang, H., Gupta, S., Iandola, F.N., Srivastava, R.K., Deng, L., Doll\u00e1r, P., Gao, J., He, X., Mitchell, M., Platt, J.C., Zitnick, C.L., Zweig, G.: From captions to visual concepts and back. (2014) CoRR \nhttp:\/\/arxiv.org\/abs\/abs\/1411.4952\n\n\n\narXiv:abs\/1411.4952"},{"key":"634_CR16","unstructured":"Fern\u00e1ndez-Torn\u00e9, A.: Audio description and technologies: study on the semi-automatisation of the translation and voicing of audio descriptions. Ph.D. thesis, Universitat Autnoma de Barcelona, Barcelona, Spain (2016)"},{"issue":"12","key":"634_CR17","doi-asserted-by":"publisher","first-page":"e0144610","DOI":"10.1371\/journal.pone.0144610","volume":"10","author":"T Giannakopoulos","year":"2015","unstructured":"Giannakopoulos, T.: pyAudioAnalysis: an open-source python library for audio signal analysis. PloS One 10(12):e0144610 (2015). \nhttps:\/\/doi.org\/10.1371\/journal.pone.0144610","journal-title":"PloS One"},{"key":"634_CR18","doi-asserted-by":"publisher","unstructured":"Kobayashi, M., Nagano, T., Fukuda, K., Takagi, H.: Describing online videos with text-to-speech narration. In: Proceedings of the 2010 International Cross Disciplinary Conference on Web Accessibility (W4A), W4A \u201910, pp. 29:1\u201329:2. ACM, New York, NY, USA (2010). \nhttps:\/\/doi.org\/10.1145\/1805986.1806025","DOI":"10.1145\/1805986.1806025"},{"key":"634_CR19","doi-asserted-by":"publisher","unstructured":"Kobayashi, M., O\u2019Connell, T., Gould, B., Takagi, H., Asakawa, C.: Are synthesized video descriptions acceptable? In: Proceedings of the 12th International ACM SIGACCESS Conference on Computers and Accessibility, ASSETS \u201910, pp. 163\u2013170. ACM, New York, NY, USA (2010). \nhttps:\/\/doi.org\/10.1145\/1878803.1878833","DOI":"10.1145\/1878803.1878833"},{"key":"634_CR20","unstructured":"Lakritz, J., Salway, A.: The semi-automatic generation of audio description from screenplays. Technical report CS-06-05, Dept. Of Computing, University of Surrey (2002)"},{"key":"634_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/CVPR.2008.4587756","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition","author":"I Laptev","year":"2008","unstructured":"Laptev, I., Marszaek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE, Anchorage, AK (2008). \nhttps:\/\/doi.org\/10.1109\/CVPR.2008.4587756"},{"key":"634_CR22","doi-asserted-by":"publisher","first-page":"2929","DOI":"10.1109\/CVPR.2009.5206557","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition","author":"M Marszalek","year":"2009","unstructured":"Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2929\u20132936. IEEE, Miami, FL (2009). \nhttps:\/\/doi.org\/10.1109\/CVPR.2009.5206557"},{"key":"634_CR23","unstructured":"Morrissey, S.: Data-driven machine translation for sign languages. Ph.D. thesis, Dublin City University, Dublin, Ireland (2008)"},{"key":"634_CR24","unstructured":"Nenkova, A., Maskey, S., Liu, Y.: Automatic summarization. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts of ACL 2011, HLT-11, pp. 3:1\u20133:86. Association for Computational Linguistics, Stroudsburg, PA, USA, Article 3, 86 pp \u00a0(2011)"},{"key":"634_CR25","unstructured":"Nunes, E.V., Machado, F.O., Vanzin, T.: Audiodescricao como Tecnologia Assistiva para o Acesso ao Conhecimento por Pessoas Cegas. (Audio description as assistive technology for access to knowledge for the blind). In: Ulbricht, V.R., Vanzin, T., Villarouco, V. (eds.) Ambiente Virtual de Aprendizagem Inclusivo (Inclusive Virtual Learning Environment), p. 352. Pandion, Florianopolis (2011)"},{"key":"634_CR26","first-page":"4594","volume-title":"IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Y Pan","year":"2016","unstructured":"Pan, Y., Mei, T., Yao, T., Li, H., Rui, Y.: Jointly modeling embedding and translation to bridge video and language. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4594\u20134602. IEEE, Las Vegas, NV (2016)"},{"key":"634_CR27","first-page":"6517","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"J Redmon","year":"2017","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6517\u20136525. IEEE, Honolulu, HI\u00a0(2017)"},{"issue":"6","key":"634_CR28","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"Shaoqing Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In:\u00a0IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137\u20131149 \u00a0(2017)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"634_CR29","series-title":"Lecture Notes in Computer Science","volume-title":"Pattern recognition. DAGM 2015","author":"A Rohrbach","year":"2015","unstructured":"Rohrbach, A., Rohrbach, M., Schiele, B.: The long-short story of movie description. In: Gall J., Gehler P., Leibe B. (eds.) Pattern recognition. DAGM 2015. Lecture Notes in Computer Science, vol. 9358. Springer, Cham (2015)"},{"key":"634_CR30","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1007\/s11263-016-0987-1","volume":"123","author":"A Rohrbach","year":"2017","unstructured":"Rohrbach, A., Torabi, A., Rohrbach, M., Tandon, N., Pal, C., Larochelle, H., Courville, A., Schiele, B.: Movie description. Int. J. Comput. Vis. 123, 94\u2013120 (2017). \nhttps:\/\/doi.org\/10.1007\/s11263-016-0987-1","journal-title":"Int. J. Comput. Vis."},{"key":"634_CR31","unstructured":"Salway, A., Vassiliou, A., Ahmad, K.: Whats happens in films? In: Proceedings of the IEEE International Conference on Multimedia an Expo, ICME (2005)"},{"key":"634_CR32","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/s10044-011-0243-9","volume":"15","author":"R San-Segundo","year":"2012","unstructured":"San-Segundo, R., Montero, J., C\u00f3rdoba, R., Sama, V., Fernndez, F., Dharo, L., L\u00f3pez-Lude\u00f1a, V., S\u00e1nchez, D., Garc\u00eda, A.: Design, development and field evaluation of a Spanish into sign language translation system. Pattern Anal. Appl. 15, 203\u2013224 (2012)","journal-title":"Pattern Anal. Appl."},{"key":"634_CR33","first-page":"142","volume":"15","author":"A Szarkowska","year":"2011","unstructured":"Szarkowska, A.: Text-to-speech audio description: towards wider availability of AD. J. Spec. Transl. 15, 142\u2013162 (2011)","journal-title":"J. Spec. Transl."},{"key":"634_CR34","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R.J., Darrell, T., Saenko, K.: Sequence to sequence\u2013video to text. (2015)\u00a0ICCV '15 Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV),\u00a0pp. 4534\u20134542\u00a0(2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"634_CR35","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R.J., Saenko, K.: Translating videos to natural language using deep recurrent neural networks.\u00a0In: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), Denver, Colorado, USA, pp. 1494\u20131504, May 31\u2013June 5 (2015)","DOI":"10.3115\/v1\/N15-1173"},{"key":"634_CR36","doi-asserted-by":"publisher","unstructured":"Wang, K.C., Yang, Y.M., Yang, Y.R.: Speech\/music discrimination using hybrid-based feature extraction for audio data indexing. In: 2017 International Conference on System Science and Engineering (ICSSE), pp. 515\u2013519 (2017). \nhttps:\/\/doi.org\/10.1109\/ICSSE.2017.8030927","DOI":"10.1109\/ICSSE.2017.8030927"}],"container-title":["Universal Access in the Information Society"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10209-018-0634-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10209-018-0634-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10209-018-0634-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,3,5]],"date-time":"2020-03-05T09:22:46Z","timestamp":1583400166000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10209-018-0634-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,31]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["634"],"URL":"https:\/\/doi.org\/10.1007\/s10209-018-0634-4","relation":{},"ISSN":["1615-5289","1615-5297"],"issn-type":[{"type":"print","value":"1615-5289"},{"type":"electronic","value":"1615-5297"}],"subject":[],"published":{"date-parts":[[2018,8,31]]},"assertion":[{"value":"31 August 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}