{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T09:22:36Z","timestamp":1725873756883},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319508313"},{"type":"electronic","value":"9783319508320"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-50832-0_6","type":"book-chapter","created":{"date-parts":[[2016,12,8]],"date-time":"2016-12-08T19:42:47Z","timestamp":1481226167000},"page":"55-64","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Multi-modal Analyses and Online Knowledge Base for Video Aboutness Generation"],"prefix":"10.1007","author":[{"given":"Raj Kumar","family":"Gupta","sequence":"first","affiliation":[]},{"given":"Yang","family":"Yinping","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,12,10]]},"reference":[{"key":"6_CR1","unstructured":"Barbu, A., Bridge, E., Burchill, Z., Coroian, D., Dickinson, S., Fidler, S., Michaux, A., Mussman, S., Narayanaswamy, S., Salvi, D., Schmidt, L., Shangguan, J., Siskind, J.M., Waggoner, J., Wang, S., Wei, J., Yin, Y., Zhang, Z.: Video in sentences out. In: Association for Uncertainty in Artificial Intelligence (UAI) (2012)"},{"key":"6_CR2","unstructured":"Khan, M.U.G., Gotoh, Y.: Describing video contents in natural language. In: Proceedings of the Workshop on Innovative Hybrid Approaches to the Processing of Textual Data (2012)"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Li, G., Ma, S., Han, Y.: Summarization-based video caption via deep neural networks. In: ACM Multimedia (2015)","DOI":"10.1145\/2733373.2806314"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Qiu, W., Titov, I., Thater, S., Pinkal, M., Schiele, B.: Translating video content to natural language descriptions. In: International Conference on Computer Vision (2013)","DOI":"10.1109\/ICCV.2013.61"},{"key":"6_CR5","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: 25th International Conference on Computational Linguistics (COLING) (2014)"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Huggins-Daines, D., Kumar, M., Chan, A., Black, A.W., Ravishankar, M., Rudnicky, A.I.: Pocketsphinx: a free, real-time continuous speech recognition system for hand-held devices. In: International Conference on Acoustics Speech and Signal Processing (2006)","DOI":"10.1109\/ICASSP.2006.1659988"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"McKinney, M.F., Breebaart, J.: Features for audio and music classification. In: International Conference on Music Information Retrieval (2003)","DOI":"10.1007\/978-94-017-0703-9_6"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Text localization in real-world images using efficiently pruned exhaustive search. In: International Conference on Document Analysis and Recognition (2011)","DOI":"10.1109\/ICDAR.2011.144"},{"key":"6_CR9","first-page":"73","volume":"4","author":"RA Fairthorne","year":"1969","unstructured":"Fairthorne, R.A.: Content analysis, specification and control. Ann. Rev. Inf. Sci. Technol. 4, 73\u2013109 (1969)","journal-title":"Ann. Rev. Inf. Sci. Technol."},{"key":"6_CR10","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139173452","volume-title":"Intentionality: An Essay in the Philosophy of Mind","author":"J Searle","year":"1983","unstructured":"Searle, J.: Intentionality: An Essay in the Philosophy of Mind. Cambridge University Press, Cambridge (1983)"},{"key":"6_CR11","unstructured":"Khosla, A., Hamid, R., Lin, C.J., Sundaresan, N.: Large-scale video summarization using web-image priors. In: Computer Vision and Pattern Recognition (2009)"},{"issue":"1\u201327","key":"6_CR12","first-page":"27","volume":"27","author":"CC Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 27(1\u201327), 27 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Conference on Computer Vision and Pattern Recognition (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Aghajanian, J., Warrell, J., Prince, S.J., Li, P., Rohn, J.L., Baum, B.: Patch-based within-object classification. In: International Conference on Computer Vision (2009)","DOI":"10.1109\/ICCV.2009.5459352"},{"key":"6_CR15","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1627\u20131645 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Hays, J., Efros, A.A.: Scene completion using millions of photographs. In: ACM SIGGRAPH (2007)","DOI":"10.1145\/1275808.1276382"},{"key":"6_CR17","unstructured":"Trefny, J., Matas, J.: Extended set of local binary patterns for rapid object detection. In: Proceedings of the Computer Vision Winter Workshop (2010)"},{"key":"6_CR18","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2012)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: IEEE Conference on Computer Vision and Pattern Recognition (2006)","DOI":"10.1109\/CVPR.2006.68"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Marsza\u0142ek, M., Laptev, I., Schmid, C.: Actions in context. In: IEEE Conference on Computer Vision and Pattern Recognition (2009)","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"6_CR21","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1037\/0022-3514.45.3.513","volume":"45","author":"N Schwarz","year":"1983","unstructured":"Schwarz, N., Clore, G.L.: Mood, misattribution, and judgments of well-being: informative and directive functions of affective states. J. Pers. Soc. Psychol. 45, 513\u2013523 (1983)","journal-title":"J. Pers. Soc. Psychol."},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Schwarz, N.: Feelings-as-information theory. In: Van Lange, P., Kruglanski, A., Higgins, E.T. (eds.) Handbook of Theories of Social Psychology, pp. 289\u2013308 (2012)","DOI":"10.4135\/9781446249215.n15"}],"container-title":["Lecture Notes in Computer Science","Advances in Visual Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-50832-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,16]],"date-time":"2019-09-16T06:25:45Z","timestamp":1568615145000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-50832-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319508313","9783319508320"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-50832-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}