{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T23:01:01Z","timestamp":1793055661690,"version":"4.5.0"},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642113000","type":"print"},{"value":"9783642113017","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-11301-7_74","type":"book-chapter","created":{"date-parts":[[2009,12,24]],"date-time":"2009-12-24T15:29:10Z","timestamp":1261668550000},"page":"713-718","source":"Crossref","is-referenced-by-count":6,"title":["Learning Cooking Techniques from YouTube"],"prefix":"10.1007","author":[{"given":"Guangda","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richang","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan-Tao","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"74_CR1","doi-asserted-by":"crossref","unstructured":"Chua, T.-S., Hong, R., Li, G., Tang, J.: From Text Question-Answering to Multimedia QA. To appear in ACM Multimedia Workshop on Large-Scale Multimedia Retrieval and Mining, LS-MMRM (2009)","DOI":"10.1145\/1631058.1631069"},{"key":"74_CR2","unstructured":"Sun, J., Wu, X., Yan, S., Cheong, L.F., Chua, T.-S., Li, J.: Hierarchical Spatio-Temporal Context Modeling for Action Recognition. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Miami, Florida, US (2009)"},{"key":"74_CR3","doi-asserted-by":"crossref","unstructured":"Shibata, T., Kato, N., Kurohashi, S.: Automatic object model acquisition and object recognition by integrating linguistic and visual information. In: ACM\u2019MM (2007)","DOI":"10.1145\/1291233.1291327"},{"key":"74_CR4","doi-asserted-by":"crossref","unstructured":"Hamada, R., Satoh, S., Sakai, S.: Detection of Important Segments in Cooking Videos. In: Proceedings of the IEEE Workshop on Content-Based Access of Image and Video Libraries (Cbaivl 2001), p. 118 (2001)","DOI":"10.1109\/IVL.2001.990865"},{"key":"74_CR5","doi-asserted-by":"crossref","unstructured":"Dollar, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: VS-PETS 2005, pp. 65\u201372 (2005)","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"74_CR6","doi-asserted-by":"crossref","unstructured":"Kennedy, L.S., Naaman, M.: Generating diverse and representative image search results for landmarks. In: Proceeding of the 17th international Conference on World Wide Web, Beijing, China, pp. 297\u2013306 (2008)","DOI":"10.1145\/1367497.1367539"},{"key":"74_CR7","doi-asserted-by":"crossref","unstructured":"Li, G., Ming, Z., Li, H., Chua, T.-S.: Video Reference: Question Answering on YouTube. In: ACM\u2019MM (2009)","DOI":"10.1145\/1631272.1631411"},{"key":"74_CR8","doi-asserted-by":"crossref","unstructured":"Hong, R., Tang, J., Tan, H.-K., Yan, S., Ngo, C.-W., Chua, T.-S.: Event Driven Summarization for Web Videos. In: ACM Multimedia Workshop on Social Media, WSM (2009)","DOI":"10.1145\/1631144.1631154"},{"key":"74_CR9","doi-asserted-by":"crossref","unstructured":"Li, H., Tang, J., Li, G., Chua, T.-S.: Word2Image: Towards Visual Interpretation of Words. In: ACM\u2019MM 2008 (2008)","DOI":"10.1145\/1459359.1459494"},{"key":"74_CR10","doi-asserted-by":"crossref","unstructured":"Wang, M., Yang, K., Hua, X.-S., Zhang, H.-J.: Visual Tag Dictionary: Interpreting Tags with Visual Words. In: ACM Multimedia Workshop on Web-Scale Multimedia Corpus (2009)","DOI":"10.1145\/1631135.1631137"},{"key":"74_CR11","unstructured":"Tang, S., Li, J.-T., et al.: TRECVID 2008 High-Level Feature Extraction By MCG-ICT-CAS. In: TRECVID Workshop, Gaithesburg, USA (2008)"}],"container-title":["Lecture Notes in Computer Science","Advances in Multimedia Modeling"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-11301-7_74.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T02:39:17Z","timestamp":1606185557000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-11301-7_74"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642113000","9783642113017"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-11301-7_74","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010]]}}}