{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T09:11:14Z","timestamp":1760346674160,"version":"3.37.3"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2018,5,2]],"date-time":"2018-05-02T00:00:00Z","timestamp":1525219200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/\"http:\/\/dx.doi.org\/10.13039\/501100001691\"","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["2670002"],"award-info":[{"award-number":["2670002"]}],"id":[{"id":"10.13039\/\"http:\/\/dx.doi.org\/10.13039\/501100001691\"","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Robot"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1007\/s10514-018-9762-1","type":"journal-article","created":{"date-parts":[[2018,5,2]],"date-time":"2018-05-02T13:14:18Z","timestamp":1525266858000},"page":"913-925","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Linking human motions and objects to language for synthesizing action sentences"],"prefix":"10.1007","volume":"43","author":[{"given":"Wataru","family":"Takano","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshihiko","family":"Yamada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshihiko","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,5,2]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Abdel-Kalim, A. E., & Farag, A. A. (2006). Asift: A sift descriptor with color invariant characteristics. In Proceedings of 2006 IEEE Computer society conference on computer vision and pattern recognition, Vol. 2, pp. 1978\u20131983.","key":"9762_CR1","DOI":"10.1109\/CVPR.2006.95"},{"doi-asserted-by":"crossref","unstructured":"Bengio, Y., Schwenk, H., Sen\u00e9cal, J., Morin, F., & Gauvain, J. (2006). Neural probabilistic language models. In Innovations in machine learning, pp. 137\u2013186.","key":"9762_CR2","DOI":"10.1007\/3-540-33486-6_6"},{"issue":"1","key":"9762_CR3","first-page":"281","volume":"13","author":"J Bergstra","year":"2012","unstructured":"Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. The Journal of Machine Learning Research, 13(1), 281\u2013305.","journal-title":"The Journal of Machine Learning Research"},{"issue":"10","key":"9762_CR4","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1163\/156855307781389356","volume":"21","author":"G Cheng","year":"2007","unstructured":"Cheng, G., Hyon, S. H., Morimoto, J., Ude, A., Hale, J. G., Colvin, G., et al. (2007). CB: A humanoid research platform for exploring neuroscience. Advanced Robotics, 21(10), 1097\u20131114.","journal-title":"Advanced Robotics"},{"issue":"3","key":"9762_CR5","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273\u2013297.","journal-title":"Machine Learning"},{"issue":"10","key":"9762_CR6","doi-asserted-by":"publisher","first-page":"1775","DOI":"10.1109\/TPAMI.2009.83","volume":"31","author":"A Gupta","year":"2009","unstructured":"Gupta, A., Kembhavi, A., & Davis, L. S. (2009). Observing human\u2013object interactions: Using spatial and functional compatibility for recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(10), 1775\u20131789.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9762_CR7","doi-asserted-by":"publisher","first-page":"2201","DOI":"10.1162\/089976601750541778","volume":"13","author":"M Haruno","year":"2001","unstructured":"Haruno, M., Wolpert, D., & Kawato, M. (2001). Mosaic model for sensorimotor learning and control. Neural Computation, 13, 2201\u20132220.","journal-title":"Neural Computation"},{"doi-asserted-by":"crossref","unstructured":"Ho, E. S., & Shum, H. (2013). Motion adaptation for humanoid robots in constrained environments. In Proceedings of IEEE international conference on advanced robotics, pp. 3813\u20133818.","key":"9762_CR8","DOI":"10.1109\/ICRA.2013.6631113"},{"doi-asserted-by":"crossref","unstructured":"Ho, E. S., Komura, T., & Tai, C. (2010). Spatial relationship preserving character motion adaptation. In ACM transactions on graphics, Vol. 29, p. 33.","key":"9762_CR9","DOI":"10.1145\/1778765.1778770"},{"issue":"4","key":"9762_CR10","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1177\/0278364904042199","volume":"23","author":"T Inamura","year":"2004","unstructured":"Inamura, T., Toshima, I., Tanie, H., & Nakamura, Y. (2004). Embodied symbol emergence based on mimesis theory. International Journal of Robotics Research, 23(4), 363\u2013377.","journal-title":"International Journal of Robotics Research"},{"issue":"3","key":"9762_CR11","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1002\/jor.1100080310","volume":"8","author":"MP Kadaba","year":"1990","unstructured":"Kadaba, M. P., Ramakrishnan, H. K., & Wootten, M. E. (1990). Measurement of lower extremity kinematics during level walking. Journal of Orthopaedic Research, 8(3), 383\u2013392.","journal-title":"Journal of Orthopaedic Research"},{"doi-asserted-by":"crossref","unstructured":"Kaneko, K., Kanehiro, F., Kajita, S., Yokoyama, K., Akachi, K., Kawasaki, T., et al. (2002). Design of prototype humanoid robotics platform for HRP. In Proceedings of the 2002 IEEE\/RSJ international conference on intelligent robots and systems, Vol. 3, pp. 2431\u20132436.","key":"9762_CR12","DOI":"10.1109\/IRDS.2002.1041632"},{"issue":"4","key":"9762_CR13","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TPAMI.2016.2598339","volume":"39","author":"A Karpathy","year":"2015","unstructured":"Karpathy, A., & Fei-Fei, L. (2015). Deep visual semantic alignments for generating image descriptions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4), 664\u2013676.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"9762_CR14","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1023\/A:1020346032608","volume":"50","author":"A Kojima","year":"2002","unstructured":"Kojima, A., Tamura, T., & Fukunaga, K. (2002). Natural language description of human activities from video images based on concept hierarchy of actions. International Journal of Computer Vision, 50(2), 171\u2013184.","journal-title":"International Journal of Computer Vision"},{"doi-asserted-by":"crossref","unstructured":"Krishnamoorthy, N., Malkarnenkar, G., Mooney, R., Saenko, K., & Guadarrama, S. (2013). Generating natural-language video descriptions using text-mined knowledge. In Proceedings of the 27th AAAI conference on artificial intelligence, pp. 541\u2013547.","key":"9762_CR15","DOI":"10.1609\/aaai.v27i1.8679"},{"doi-asserted-by":"crossref","unstructured":"Kulkarni, G., Premraj, V., Dhar, S., & Li, S. (2011). Baby talk: Understanding and generating simple image descriptions. In Proceedings of IEEE conference on computer vision and pattern recognition, pp. 1601\u20131608.","key":"9762_CR16","DOI":"10.1109\/CVPR.2011.5995466"},{"issue":"6","key":"9762_CR17","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1109\/70.338535","volume":"10","author":"Y Kuniyoshi","year":"1994","unstructured":"Kuniyoshi, Y., Inaba, M., & Inoue, H. (1994). Learning by watching: Extracting reusable task knowledge from visual observation of human performance. IEEE Transactions on Robotics and Automation, 10(6), 799\u2013822.","journal-title":"IEEE Transactions on Robotics and Automation"},{"doi-asserted-by":"crossref","unstructured":"Kuroki, Y., Fujita, M., Ishida, T., Nagasaka, K., & Yamaguchi, J. (2003). A small biped entertainment robot exploring attractive applications. In Proceedings of the IEEE international conference on robotics and automation, Vol. 1, pp. 471\u2013476.","key":"9762_CR18","DOI":"10.1109\/ROBOT.2003.1241639"},{"unstructured":"Li, S., Kulkarni, G., Berg, T. L. , Berg, A. C., & Choi, Y. (2011). Composing simple image descriptions using web-scale n-grams. In Proceedings of the 15th conference on computational natural language learning, pp. 220\u2013228.","key":"9762_CR19"},{"doi-asserted-by":"crossref","unstructured":"Lowe, D. G. (1999). Object recognition from local scale-invariant features. In Proceedings of the seventh IEEE international conference on Computer vision, Vol. 2, pp. 1150\u20131157.","key":"9762_CR20","DOI":"10.1109\/ICCV.1999.790410"},{"issue":"4","key":"9762_CR21","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/5254.867908","volume":"15","author":"MJ Mataric","year":"2000","unstructured":"Mataric, M. J. (2000). Getting humanoids to move and imitate. IEEE Intelligent Systems, 15(4), 18\u201324.","journal-title":"IEEE Intelligent Systems"},{"doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., Cernock\u1ef3, J., & Khudanpur, S. (2010). Recurrent neural network based language model. In INTERSPEECH, pp. 1045\u20131048.","key":"9762_CR22","DOI":"10.21437\/Interspeech.2010-343"},{"issue":"1","key":"9762_CR23","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/S0921-8890(01)00113-0","volume":"36","author":"J Morimoto","year":"2001","unstructured":"Morimoto, J., & Doya, K. (2001). Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning. Robotics and Autonomous Systems, 36(1), 37\u201351.","journal-title":"Robotics and Autonomous Systems"},{"doi-asserted-by":"crossref","unstructured":"Rabiner, L. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. In Proceedings of the IEEE, Vol. 77, pp. 257\u2013286.","key":"9762_CR24","DOI":"10.1109\/5.18626"},{"key":"9762_CR25","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1038\/35090060","volume":"2","author":"G Rizzolatti","year":"2001","unstructured":"Rizzolatti, G., Fogassi, L., & Gallese, V. (2001). Neurophysiological mechanisms underlying the understanding and imitation of action. Nature Reviews, 2, 661\u2013670.","journal-title":"Nature Reviews"},{"key":"9762_CR26","volume-title":"Course in general linguistics","author":"FD Saussure","year":"1966","unstructured":"Saussure, F. D. (1966). Course in general linguistics. New York: McGraw-Hill Book Company."},{"doi-asserted-by":"crossref","unstructured":"Sugano, S., & Kato, I. (1987). Wabot-2: Autonomous robot with dexterous finger-arm\u2013finger-arm coordination control in keyboard performance. In Proceedings of 1987 IEEE international conference on robotics and automation, Vol. 4, pp. 90\u201397.","key":"9762_CR27","DOI":"10.1109\/ROBOT.1987.1088025"},{"key":"9762_CR28","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.robot.2014.12.008","volume":"66","author":"W Takano","year":"2015","unstructured":"Takano, W., & Nakamura, Y. (2015). Symbolically structured database for human whole body motions based on association between motion symbols and motion words. Robotics and Autonomous Systems, 66, 75\u201385.","journal-title":"Robotics and Autonomous Systems"},{"issue":"10","key":"9762_CR29","doi-asserted-by":"publisher","first-page":"1314","DOI":"10.1177\/0278364915587923","volume":"34","author":"W Takano","year":"2015","unstructured":"Takano, W., & Nakamura, Y. (2015). Statistical mutual conversion between whole body motion primitives and linguistic sentences for human motions. International Journal of Robotics Research, 34(10), 1314\u20131328.","journal-title":"International Journal of Robotics Research"},{"issue":"4","key":"9762_CR30","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1109\/TSMCA.2003.809171","volume":"33","author":"J Tani","year":"2003","unstructured":"Tani, J., & Ito, M. (2003). Self-organization of behavioral primitives as multiple attractor dynamics: A robot experiment. IEEE Transactions on Systems, Man and Cybernetics Part A: Systems and Humans, 33(4), 481\u2013488.","journal-title":"IEEE Transactions on Systems, Man and Cybernetics Part A: Systems and Humans"},{"doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015). Show and tell: A neural image caption generator. In Proceedings of IEEE conference on computer vision and pattern recognition, pp. 3156\u20133164 .","key":"9762_CR31","DOI":"10.1109\/CVPR.2015.7298935"},{"doi-asserted-by":"crossref","unstructured":"Wang, J., Liu, Z., Wu, Y., & Yuan, J. (2012). Mining actionlet ensemble for action recognition with depth cameras. In IEEE conference on computer vision and pattern recognition, pp. 1290\u20131297.","key":"9762_CR32","DOI":"10.1109\/CVPR.2012.6247813"},{"issue":"9","key":"9762_CR33","doi-asserted-by":"publisher","first-page":"1691","DOI":"10.1109\/TPAMI.2012.67","volume":"34","author":"B Yao","year":"2012","unstructured":"Yao, B., & Fei-Fei, L. (2012). Recognizing human\u2013object interactions in still images by modeling the mutual context of objects and human poses. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(9), 1691\u20131703.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"unstructured":"Yu, G., Liu, Z., & Yuan, J. (2014). Discriminative orderlet mining for real-time recognition of human\u2013object interaction. In In Proceedings of Asian conference on computer vision, pp. 50\u201365.","key":"9762_CR34"},{"unstructured":"Zhan, Q., Liang, Y., & Xiao, Y. (2009). Color-based segmentation of point clouds. In Proceedings of ISPRS laser scanning workshop, Vol. 38, pp. 248\u2013252.","key":"9762_CR35"}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-018-9762-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10514-018-9762-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-018-9762-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,2]],"date-time":"2023-09-02T11:08:44Z","timestamp":1693652924000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10514-018-9762-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,2]]},"references-count":35,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,4]]}},"alternative-id":["9762"],"URL":"https:\/\/doi.org\/10.1007\/s10514-018-9762-1","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"type":"print","value":"0929-5593"},{"type":"electronic","value":"1573-7527"}],"subject":[],"published":{"date-parts":[[2018,5,2]]},"assertion":[{"value":"6 March 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}