{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T15:00:05Z","timestamp":1761663605939,"version":"3.41.0"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2017,2,14]],"date-time":"2017-02-14T00:00:00Z","timestamp":1487030400000},"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":["Machine Vision and Applications"],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1007\/s00138-017-0825-7","type":"journal-article","created":{"date-parts":[[2017,2,14]],"date-time":"2017-02-14T19:56:03Z","timestamp":1487102163000},"page":"243-265","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Generating natural language tags for video information management"],"prefix":"10.1007","volume":"28","author":[{"given":"Muhammad Usman Ghani","family":"Khan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshihiko","family":"Gotoh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,2,14]]},"reference":[{"key":"825_CR1","unstructured":"Abella, A., Kender, J.R., Starren, J.: Description generation of abnormal densities found in radiographs. In: Proceedings of the Annual Symposium on Computer Application in Medical Care, p. 42 (1995)"},{"key":"825_CR2","unstructured":"Aker, A., Gaizauskas, R.: Generating image descriptions using dependency relational patterns. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 1250\u20131258 (2010)"},{"issue":"2","key":"825_CR3","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/0004-3702(84)90008-0","volume":"23","author":"JF Allen","year":"1984","unstructured":"Allen, J.F.: Towards a general theory of action and time. Artif. Intell. 23(2), 123\u2013154 (1984)","journal-title":"Artif. Intell."},{"key":"825_CR4","doi-asserted-by":"crossref","unstructured":"Bai, L., Li, K., Pei, J., Jiang, S.: Main objects interaction activity recognition in real images. Neural Comput. Appl. 1\u201314 (2015)","DOI":"10.1007\/s00521-015-1846-7"},{"key":"825_CR5","volume-title":"Trajectory-Based Abnormality Categorization for Learning Route Patterns in Surveillance","author":"P Baiget","year":"2012","unstructured":"Baiget, P., Fern\u00e1ndez, C., Roca, X., Gonz\u00e0lez, J.: Trajectory-Based Abnormality Categorization for Learning Route Patterns in Surveillance. Springer, Berlin (2012)"},{"key":"825_CR6","unstructured":"Chen, D.L., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 190\u2013200. Association for Computational Linguistics (2011)"},{"key":"825_CR7","doi-asserted-by":"publisher","unstructured":"Cruz-Perez, C., Starostenko, O., Alarcon-Aquino, V., Rodriguez-Asomoza, J.: Automatic image annotation for description of urban and outdoor scenes. In: Innovations and Advances in Computing, Informatics, Systems Sciences, Networking and Engineering, pp. 139\u2013147. Springer (2015)","DOI":"10.1007\/978-3-319-06773-5_20"},{"key":"825_CR8","doi-asserted-by":"publisher","unstructured":"Das, D.: Human gait classification using combined HMM & SVM hybrid classifier. In: IEEE International Conference on Electronic Design, Computer Networks & Automated Verification (EDCAV), pp. 169\u2013174 (2015)","DOI":"10.1109\/EDCAV.2015.7060561"},{"key":"825_CR9","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. arXiv preprint arXiv:1411.4389 (2014)","DOI":"10.21236\/ADA623249"},{"key":"825_CR10","unstructured":"Feng, Y., Lapata, M.: How many words is a picture worth? automatic caption generation for news images. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 1239\u20131249 (2010)"},{"key":"825_CR11","doi-asserted-by":"publisher","unstructured":"Filice, S., Da\u00a0San\u00a0Martino, G., Moschitti, A.: Structural representations for learning relations between pairs of texts. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics, Beijing, China, July. Association for Computational Linguistics (2015)","DOI":"10.3115\/v1\/P15-1097"},{"key":"825_CR12","unstructured":"Gitte, M., Bawaskar, H., Sethi, S., Shinde, A.: Content based video retrieval system. Int. J. Res. Eng. Technol. 3(6), 1 (2014)"},{"key":"825_CR13","doi-asserted-by":"publisher","unstructured":"Guadarrama, S., Krishnamoorthy, N., Malkarnenkar, G., Venugopalan, S., Mooney, R., Darrell, T., Saenko, K.: Youtube2text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013, pp. 2712\u20132719. IEEE (2013)","DOI":"10.1109\/ICCV.2013.337"},{"issue":"2","key":"825_CR14","first-page":"123","volume":"2","author":"WC Hu","year":"2011","unstructured":"Hu, W.C., Yang, C.Y., Huang, D.Y., Huang, C.H.: Feature-based face detection against skin-color like backgrounds with varying illumination. J. Inf. Hiding Multimed. Signal Process. 2(2), 123\u2013132 (2011)","journal-title":"J. Inf. Hiding Multimed. Signal Process."},{"key":"825_CR15","unstructured":"Khan, M.U.G., Gotoh, Y.: Describing video contents in natural language. In: Proceedings of the EACL Workshop, Avignon (2012)"},{"key":"825_CR16","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.ins.2014.12.034","volume":"303","author":"MUG Khan","year":"2015","unstructured":"Khan, M.U.G., Al Harbi, N., Gotoh, Y.: A framework for creating natural language descriptions of video streams. Inf. Sci. 303, 61\u201382 (2015)","journal-title":"Inf. Sci."},{"key":"825_CR17","unstructured":"Khan, M.U.G., Saeed, A.: Human detection in videos. J. Theor. Appl. Inf. Technol. 5(2), 1 (2009)"},{"key":"825_CR18","doi-asserted-by":"publisher","unstructured":"Khan, M.U.G., Zhang, L., Gotoh, Y.: Towards coherent natural language description of video streams. In: Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on, pp. 664\u2013671. IEEE (2011)","DOI":"10.1109\/ICCVW.2011.6130306"},{"key":"825_CR19","unstructured":"Khan, M.U.G., Nawab, R.M.A., Gotoh, Y.: Natural language descriptions of visual scenes: corpus generation and analysis. In: Proceedings of the Joint Workshop on Exploiting Synergies Between Information Retrieval and Machine Translation (ESIRMT) and Hybrid Approaches to Machine Translation (HyTra), pp. 38\u201347. Association for Computational Linguistics (2012)"},{"key":"825_CR20","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/s11265-009-0446-0","volume":"61","author":"W Kim","year":"2010","unstructured":"Kim, W., Park, J., Kim, C.: A novel method for efficient indoor\u2013outdoor image classification. J. Signal Process. Syst. 61, 251\u2013258 (2010)","journal-title":"J. Signal Process. Syst."},{"key":"825_CR21","doi-asserted-by":"publisher","unstructured":"Klein, D., Manning, C.D.: Accurate unlexicalized parsing. In: Proceedings of the 41st Annual Meeting on Association for Computational Linguistics, pp. 423\u2013430 (2003)","DOI":"10.3115\/1075096.1075150"},{"key":"825_CR22","doi-asserted-by":"publisher","unstructured":"Kojima, A., Takaya, M., Aoki, S., Miyamoto, T., Fukunaga, K.: Recognition and textual description of human activities by mobile robot. In: Proceedings of the 3rd International Conference on Innovative Computing Information and Control, pp. 53\u201353 (2008)","DOI":"10.1109\/ICICIC.2008.440"},{"key":"825_CR23","doi-asserted-by":"publisher","unstructured":"Kulkarni, G., Premraj, V., Dhar, S., Li, S., Choi, Y., Berg, A.C., Berg, T.L.: Baby talk: understanding and generating simple image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1601\u20131608 (2011)","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"825_CR24","doi-asserted-by":"publisher","unstructured":"Lee, H., Morariu, V., Davis, L.S.: Clauselets: leveraging temporally related actions for video event analysis. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1161\u20131168 (2015)","DOI":"10.1109\/WACV.2015.159"},{"key":"825_CR25","doi-asserted-by":"crossref","unstructured":"Lee, M.W., Hakeem, A., Haering, N., Zhu, S.C.: Save: a framework for semantic annotation of visual events. In: Proceedings of the Computer Vision and Pattern Recognition Workshops, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPRW.2008.4562954"},{"key":"825_CR26","unstructured":"Li, S., Kulkarni, G., Berg, T.L., Berg, A.C., Choi, Y.: Composing simple image descriptions using web-scale n-grams. In: Proceedings of the 15th Conference on Computational Natural Language Learning, pp. 220\u2013228 (2011)"},{"key":"825_CR27","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Proceedings of the ACL-04 Workshop (2004)"},{"key":"825_CR28","doi-asserted-by":"crossref","unstructured":"Lin, D., Kong, C., Fidler, S., Urtasun, R.: Generating multi-sentence lingual descriptions of indoor scenes. arXiv preprint arXiv:1503.00064 (2015)","DOI":"10.5244\/C.29.93"},{"issue":"2","key":"825_CR29","first-page":"313","volume":"19","author":"MP Marcus","year":"1993","unstructured":"Marcus, M.P., Marcinkiewicz, M.A., Santorini, B.: Building a large annotated corpus of English: The Penn Treebank. Comput. Linguist. 19(2), 313\u2013330 (1993)","journal-title":"Comput. Linguist."},{"key":"825_CR30","doi-asserted-by":"publisher","unstructured":"Muller, P., Reymonet, A.: Using inference for evaluating models of temporal discourse. In: 12th International Symposium on Temporal Representation and Reasoning (2005)","DOI":"10.1109\/TIME.2005.39"},{"key":"825_CR31","doi-asserted-by":"publisher","unstructured":"Nevatia, R., Zhao, T., Hongeng, S.: Hierarchical language-based representation of events in video streams. In: Proceedings of the Conference on Computer Vision and Pattern Recognition Workshop, vol. 4, pp. 39\u201339 (2003)","DOI":"10.1109\/CVPRW.2003.10038"},{"key":"825_CR32","unstructured":"Pustejovsky, J., Castano, J., Ingria, R., Saur\u00ed, R., Gaizauskas, R., Setzer, A., Katz, G., Radev, D.: TimeML: robust specification of event and temporal expressions in text. In: Proceedings of the 5th International Workshop on Computational Semantics (2003)"},{"key":"825_CR33","volume-title":"The Specification Language TimeML. The Language of Time: A Reader","author":"J Pustejovsky","year":"2004","unstructured":"Pustejovsky, J., Ingria, B., Sauri, R., Castano, J., Littman, J., Gaizauskas, R., Setzer, A., Katz, G., Mani, I.: The Specification Language TimeML. The Language of Time: A Reader. Oxford University Press, Oxford (2004)"},{"key":"825_CR34","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Qiu, W., Friedrich, A., Pinkal, M., Schiele, B.: Coherent Multi-Sentence Video Description with Variable Level of Detail. Pattern Recognition, Lecture Notes in Computer Science, vol. 8753, pp. 184\u2013195. Springer (2014)","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"825_CR35","doi-asserted-by":"publisher","unstructured":"Rohrbach, M., Qiu, W., Titov, I., Thater, S., Pinkal, M., Schiele, B.: Translating video content to natural language descriptions. In: Computer Vision (ICCV), 2013 IEEE International Conference on, pp. 433\u2013440. IEEE (2013)","DOI":"10.1109\/ICCV.2013.61"},{"key":"825_CR36","doi-asserted-by":"crossref","unstructured":"Rosani, A., Conci, N., De\u00a0Natale, F.G.B.: Human behavior understanding for assisted living by means of hierarchical context free grammars. In: IS&T\/SPIE Electronic Imaging, pp. 90260E-90260E. International Society for Optics and Photonics (2014)","DOI":"10.1117\/12.2040346"},{"key":"825_CR37","doi-asserted-by":"crossref","unstructured":"Singh, B., Han, X., Wu, Z., Morariu, V.I., Davis, L.S.: Selecting relevant web trained concepts for automated event retrieval. arXiv preprint arXiv:1509.07845 (2015)","DOI":"10.1109\/ICCV.2015.518"},{"key":"825_CR38","unstructured":"Singh, D., Yadav, A.K., Kumar, V.: Human activity tracking using star skeleton and activity recognition using hmms and neural network. Int. J. Sci. Res. Publ. 4(5), 9 (2014)"},{"key":"825_CR39","doi-asserted-by":"crossref","unstructured":"Smeaton, A.F., Over, P., Kraaij, W.: High-level feature detection from video in TRECVid: a 5-year retrospective of achievements. In: Multimedia Content Analysis, pp. 1\u201324 (2009)","DOI":"10.1007\/978-0-387-76569-3_6"},{"key":"825_CR40","doi-asserted-by":"crossref","unstructured":"Stolcke, A.: SRILM\u2014an extensible language modeling toolkit. In: Proceedings of the International Conference on Spoken Language Processing, vol. 2, pp. 901\u2013904 (2002)","DOI":"10.21437\/ICSLP.2002-303"},{"key":"825_CR41","doi-asserted-by":"publisher","unstructured":"Tan, C.C., Jiang, Y.-G., Ngo, C.-W.: Towards textually describing complex video contents with audio-visual concept classifiers. In: Proceedings of the 19th ACM International Conference on Multimedia, pp. 655\u2013658. ACM (2011)","DOI":"10.1145\/2072298.2072411"},{"key":"825_CR42","unstructured":"Thomason, J., Venugopalan, S., Guadarrama, S., Saenko, K., Mooney, R.: Integrating language and vision to generate natural language descriptions of videos in the wild. In: Proceedings of the 25th International Conference on Computational Linguistics (COLING) (2014)"},{"key":"825_CR43","unstructured":"Thomason, J., Venugopalan, S., Guadarrama, S., Saenko, K., Mooney, R.: Integrating language and vision to generate natural language descriptions of videos in the wild. In: Proceedings of the 25th International Conference on Computational Linguistics (COLING), August (2014)"},{"key":"825_CR44","doi-asserted-by":"crossref","DOI":"10.4324\/9781315802213","volume-title":"A Theory of Action Identification","author":"RR Vallacher","year":"2014","unstructured":"Vallacher, R.R., Wegner, D.M.: A Theory of Action Identification. Psychology Press, Hove (2014)"},{"key":"825_CR45","doi-asserted-by":"publisher","unstructured":"Verhagen, M., Mani, I., Sauri, R., Knippen, R., Jang, S.B., Littman, J., Rumshisky, A., Phillips, J., Pustejovsky, J.: Automating temporal annotation with TARSQI. In: Proceedings of the ACL 2005 on Interactive Poster and Demonstration Sessions, pp. 81\u201384 (2005)","DOI":"10.3115\/1225753.1225774"},{"key":"825_CR46","doi-asserted-by":"publisher","unstructured":"Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1 (2001)","DOI":"10.1109\/CVPR.2001.990517"},{"key":"825_CR47","doi-asserted-by":"publisher","unstructured":"Wilhelm, T., B\u00f6hme, H.-J., Gross, H.-M.: Classification of face images for gender, age, facial expression, and identity. In: Artificial Neural Networks: Biological Inspirations\u2013ICANN 2005, pp. 569\u2013574. Springer (2005)","DOI":"10.1007\/11550822_89"},{"key":"825_CR48","unstructured":"Wise, M.J.: String similarity via greedy string tiling and running karp-rabin matching. Online Preprint, Dec (1993)"},{"key":"825_CR49","doi-asserted-by":"publisher","unstructured":"Yan, F., Mikolajczyk, K.: Leveraging high level visual information for matching images and captions. In: Computer Vision\u2013ACCV 2014, pp. 613\u2013627. Springer (2015)","DOI":"10.1007\/978-3-319-16865-4_40"},{"key":"825_CR50","unstructured":"Yang, Y., Teo, C.L., Daum\u00e9\u00a0III, H., Ferm\u00fcller, C., Aloimonos, Y.: Corpus-guided sentence generation of natural images. In: Proceedings of the EMNLP (2011)"},{"key":"825_CR51","first-page":"67","volume":"3","author":"Y Yang","year":"2014","unstructured":"Yang, Y., Guha, A., Fermuller, C., Aloimonos, Y.: A cognitive system for understanding human manipulation actions. Adv. Cognit. Syst. 3, 67\u201386 (2014)","journal-title":"Adv. Cognit. Syst."},{"issue":"8","key":"825_CR52","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.1109\/JPROC.2010.2050411","volume":"98","author":"BZ Yao","year":"2010","unstructured":"Yao, B.Z., Yang, X., Lin, L., Lee, M.W., Zhu, S.C.: I2T: image parsing to text description. Proc. IEEE 98(8), 1485\u20131508 (2010)","journal-title":"Proc. IEEE"},{"key":"825_CR53","unstructured":"Yu, H., Siskind, J.M.: Grounded language learning from video described with sentences. In: ACL (1), pp. 53\u201363 (2013)"},{"key":"825_CR54","doi-asserted-by":"publisher","unstructured":"Zhang, L., Khan, M.U.G., Gotoh, Y.: Video scene classification based on natural language description. In: Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on, pp. 942\u2013949. IEEE (2011)","DOI":"10.1109\/ICCVW.2011.6130353"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-017-0825-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00138-017-0825-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-017-0825-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T10:40:30Z","timestamp":1749984030000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00138-017-0825-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,14]]},"references-count":54,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2017,5]]}},"alternative-id":["825"],"URL":"https:\/\/doi.org\/10.1007\/s00138-017-0825-7","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"type":"print","value":"0932-8092"},{"type":"electronic","value":"1432-1769"}],"subject":[],"published":{"date-parts":[[2017,2,14]]}}}