{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T20:26:15Z","timestamp":1776198375896,"version":"3.50.1"},"reference-count":18,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2002,11,1]],"date-time":"2002-11-01T00:00:00Z","timestamp":1036108800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2002,11,1]],"date-time":"2002-11-01T00:00:00Z","timestamp":1036108800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["International Journal of Computer Vision"],"published-print":{"date-parts":[[2002,11]]},"DOI":"10.1023\/a:1020346032608","type":"journal-article","created":{"date-parts":[[2003,3,15]],"date-time":"2003-03-15T08:44:30Z","timestamp":1047717870000},"page":"171-184","source":"Crossref","is-referenced-by-count":266,"title":["Natural Language Description of Human Activities from Video Images Based on Concept Hierarchy of Actions"],"prefix":"10.1007","volume":"50","author":[{"given":"Atsuhiro","family":"Kojima","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takeshi","family":"Tamura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunio","family":"Fukunaga","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"11","key":"5097830_CR1","first-page":"1351","volume":"119-C","author":"K. Asanuma","year":"1999","unstructured":"Asanuma, K., Onishi, M., Kojima, A., and Fukunaga, K. 1999. Extracting regions of human face and hands considering information of color and region tracking. Trans. IEEJ(C), 119-C(11):1351\u20131358 (in Japanese).","journal-title":"Trans. IEEJ(C)"},{"issue":"12","key":"5097830_CR2","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1016\/S0262-8856(01)00047-6","volume":"19","author":"D. Ayers","year":"2001","unstructured":"Ayers, D. and Shah, M. 2001. Monitoring human behavior from video taken in an office environment. Image and Vision Computing, 19(12):833\u2013846.","journal-title":"Image and Vision Computing"},{"key":"5097830_CR3","doi-asserted-by":"crossref","unstructured":"Babaguchi, N., Dan, S., and Kitahashi, T. 1996. Generation of sketch map image and its instructions to support the understanding of geographical information. In Proc. of ICPR'96, pp. 274\u2013278.","DOI":"10.1109\/ICPR.1996.546954"},{"key":"5097830_CR4","volume-title":"WordNet: An Electronic Lexical Database","year":"1998","unstructured":"Fellbaum, C. (Ed.) 1998. WordNet: An Electronic Lexical Database. MIT Press: Cambridge."},{"key":"5097830_CR5","first-page":"1","volume-title":"Universals in Linguistic Theory","author":"C.J. Fillmore","year":"1968","unstructured":"Fillmore, C.J. 1968. The case for case. In Universals in Linguistic Theory, E. Bach and R. Harms (Eds.). Rinehart and Wiston: New York, pp. 1\u201388."},{"key":"5097830_CR6","doi-asserted-by":"crossref","unstructured":"Herzog, G. and Rohr, K. 1995. Integrating vision and language: Towards automatic description of human movements. In Proc. 19th Annual German Conf. on Artificial Intelligence, pp. 257\u2013268.","DOI":"10.1007\/3-540-60343-3_42"},{"key":"5097830_CR7","volume-title":"Guide to Patterns and Usage in English","author":"A.S. Hornby","year":"1975","unstructured":"Hornby, A.S. 1975. Guide to Patterns and Usage in English. Oxford Univ. Press: London."},{"key":"5097830_CR8","unstructured":"Intille, S. and Bobick, A. 1998. Representation and Visual Recognition of Complex, Multi-Agent Actions Using Belief Networks, Technical Report 454, M.I.T Media Lab. Perceptual Computing Section."},{"key":"5097830_CR9","doi-asserted-by":"crossref","unstructured":"Kitahashi, T., Ohya, M., Kakusho, K., and Babaguchi, N. 1997. Media information processing in documents\u2014Generation of manuals of mechanical parts assembling\u2014. In Proc. of 4th Int. Conf. on Document Analysis and Recognition, Ulm, Germany, pp. 792\u2013796.","DOI":"10.1109\/ICDAR.1997.620619"},{"key":"5097830_CR10","first-page":"728","volume":"4","author":"A. Kojima","year":"2000","unstructured":"Kojima, A., Izumi, M., Tamura, T., and Fukunaga, K. 2000. Generating natural language description of human behavior from video images. In Proc. of ICPR 2000, vol. 4, pp. 728\u2013731.","journal-title":"Proc. of ICPR 2000"},{"key":"5097830_CR11","doi-asserted-by":"crossref","unstructured":"Kollnig, H., Nagel, H.-H., and Otte, M. 1994. Association of motion verbs with vehicle movements extracted from dense optical flow fields. In Proc. of 3rd European Conf. on Computer Vision'94, pp. 338\u2013347.","DOI":"10.1007\/BFb0028366"},{"key":"5097830_CR12","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1007\/BF00849074","volume":"8","author":"H.-H. Nagel","year":"1994","unstructured":"Nagel, H.-H. 1994. A vision of \u2018vision and language\u2019 comprises action: An example from road traffic. Artificial Intelligence Review, 8:189\u2013214.","journal-title":"Artificial Intelligence Review"},{"key":"5097830_CR13","doi-asserted-by":"crossref","unstructured":"Nishida, F. and Takamatsu, S. 1982. Japanese-English translation through internal expressions. In Proc. of COLING-82, pp. 271\u2013276.","DOI":"10.3115\/991813.991856"},{"key":"5097830_CR14","doi-asserted-by":"crossref","unstructured":"Nishida, F., Takamatsu, S., Tani, T., and Doi, T. 1988. Feed-back of correcting information in postediting to a ma-chine translation system. In Proc. of COLING-88, pp. 476\u2013481.","DOI":"10.3115\/991719.991737"},{"key":"5097830_CR15","doi-asserted-by":"crossref","unstructured":"Okada, N. 1980. Conceptual taxonomy of Japanese verbs for un-derstanding natural language and picture patterns. In Proc. of COLING-80, pp. 123\u2013135.","DOI":"10.3115\/990174.990196"},{"key":"5097830_CR16","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1007\/BF00127680","volume":"8","author":"N. Okada","year":"1996","unstructured":"Okada, N. 1996. Integrating vision, motion and language through mind. Artificial Intelligence Review, 8:209\u2013234.","journal-title":"Artificial Intelligence Review"},{"key":"5097830_CR17","doi-asserted-by":"crossref","DOI":"10.1515\/9780691214696","volume-title":"A Mathematical Theory of Evidence","author":"D. Shafer","year":"1976","unstructured":"Shafer, D. 1976. A Mathematical Theory of Evidence. Princeton Univ. Press: Princeton, NJ."},{"key":"5097830_CR18","unstructured":"Thonnat, M. and Rota, N. 1999. Image understanding for visual surveillance applications. In Proc. of 3rd Int. Workshop on Cooperative Distributed Vision, pp. 51\u201382."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1020346032608.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1020346032608\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1020346032608.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T09:54:34Z","timestamp":1754906074000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1020346032608"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002,11]]},"references-count":18,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2002,11]]}},"alternative-id":["5097830"],"URL":"https:\/\/doi.org\/10.1023\/a:1020346032608","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2002,11]]}}}