{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T04:35:04Z","timestamp":1780634104380,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2013,12,9]],"date-time":"2013-12-09T00:00:00Z","timestamp":1386547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2013,12,9]]},"DOI":"10.1145\/2522848.2531741","type":"proceedings-article","created":{"date-parts":[[2013,11,27]],"date-time":"2013-11-27T14:14:02Z","timestamp":1385561642000},"page":"517-524","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":74,"title":["Multiple kernel learning for emotion recognition in the wild"],"prefix":"10.1145","author":[{"given":"Karan","family":"Sikka","sequence":"first","affiliation":[{"name":"University of California, San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karmen","family":"Dykstra","sequence":"additional","affiliation":[{"name":"University of California, San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suchitra","family":"Sathyanarayana","sequence":"additional","affiliation":[{"name":"University of California, San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gwen","family":"Littlewort","sequence":"additional","affiliation":[{"name":"University of California, San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marian","family":"Bartlett","sequence":"additional","affiliation":[{"name":"University of California, San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2013,12,9]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"1","article-title":"Multiple dictionaries for bag of words large scale image search","author":"Aly M.","year":"2011","journal-title":"Probe"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.6043708"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30568-2_27"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/938978.939163"},{"key":"e_1_3_2_1_5_1","first-page":"1473","volume-title":"Advances in Neural Information Processing Systems","author":"Blitzer J.","year":"2005"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1282280.1282340"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1282280.1282340"},{"key":"e_1_3_2_1_8_1","first-page":"325","volume-title":"Advances in Neural Information Processing Systems","author":"Bucak S.","year":"2010"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1027933.1027968"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1027933.1027968"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.76"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.20.95"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICICS.1997.647126"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2011.5771366"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2531739"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.26"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.799905"},{"key":"e_1_3_2_1_19_1","volume-title":"Consulting Psychologists Press","author":"Ekman P.","year":"1978"},{"key":"e_1_3_2_1_20_1","unstructured":"L. S. hsien Chen. Joint processing of audio-visual information for the recognition of emotional expressions in human-computer interaction. Technical report University of Illinois at Urbana-Champaign 2000.  L. S. hsien Chen. Joint processing of audio-visual information for the recognition of emotional expressions in human-computer interaction. Technical report University of Illinois at Urbana-Champaign 2000."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/1005332.1005334"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"e_1_3_2_1_23_1","first-page":"1150","volume-title":"The proceedings of the seventh IEEE international conference on","volume":"2","author":"Lowe D. G.","year":"1999"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/1126250.1126288"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/520809.796143"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029666.37597.d3"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017623"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69905-7_27"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"A. Oliva and A. Torralba. Building the gist of a scene: The role of global image features in recognition. Progress in brain research 155:23--36 2006.  A. Oliva and A. Torralba. Building the gist of a scene: The role of global image features in recognition. Progress in brain research 155:23--36 2006.","DOI":"10.1016\/S0079-6123(06)55002-2"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/2009594.2009633"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2002.1035712"},{"key":"e_1_3_2_1_33_1","unstructured":"M. Pantic I. Patras and M. F. Valstar. Learning spatio-temporal models of facial expressions 2005.  M. Pantic I. Patras and M. F. Valstar. Learning spatio-temporal models of facial expressions 2005."},{"key":"e_1_3_2_1_34_1","first-page":"5","volume-title":"Multimedia and Expo, 2005. ICME 2005. IEEE International Conference on","author":"Pantic M."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.54.101601.145102"},{"key":"e_1_3_2_1_36_1","unstructured":"K. R. Scherer. Adding the affective dimension: A new look in speech analysis and synthesis 1996.  K. R. Scherer. Adding the affective dimension: A new look in speech analysis and synthesis 1996."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","first-page":"2794","DOI":"10.21437\/Interspeech.2010-739","volume-title":"INTERSPEECH","author":"Schuller B.","year":"2010"},{"key":"e_1_3_2_1_38_1","volume-title":"Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series","volume":"5670","author":"Sebe N.","year":"2004"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553762"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33868-7_25"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018628609742"},{"key":"e_1_3_2_1_42_1","first-page":"1120","volume-title":"Pattern Recognition (ICPR), 2012 21st International Conference on","author":"Tawari A.","year":"2012"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2006.85"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553510"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874249"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"e_1_3_2_1_48_1","first-page":"145","volume-title":"Proc. 3rd International Conference on Computer Vision Theory and Applications","author":"Wimmer M.","year":"2008"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"X. Xiong and F. De la Torre. Supervised descent method and its applications to face alignment. 2013.  X. Xiong and F. De la Torre. Supervised descent method and its applications to face alignment. 2013.","DOI":"10.1109\/CVPR.2013.75"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1994.323812"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.52"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553533"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1110"},{"key":"e_1_3_2_1_54_1","first-page":"2879","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhu X.","year":"2012"}],"event":{"name":"ICMI '13: 2013 International Conference on Multimodal Interaction","location":"Sydney Australia","acronym":"ICMI '13","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 15th ACM on International conference on multimodal interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2522848.2531741","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2522848.2531741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:10:02Z","timestamp":1750234202000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2522848.2531741"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12,9]]},"references-count":54,"alternative-id":["10.1145\/2522848.2531741","10.1145\/2522848"],"URL":"https:\/\/doi.org\/10.1145\/2522848.2531741","relation":{},"subject":[],"published":{"date-parts":[[2013,12,9]]},"assertion":[{"value":"2013-12-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}