{"id":"https://openalex.org/W2083270451","doi":"https://doi.org/10.1145/2324796.2324843","title":"Joint audio-visual bi-modal codewords for video event detection","display_name":"Joint audio-visual bi-modal codewords for video event detection","publication_year":2012,"publication_date":"2012-06-05","ids":{"openalex":"https://openalex.org/W2083270451","doi":"https://doi.org/10.1145/2324796.2324843","mag":"2083270451"},"language":"en","primary_location":{"id":"doi:10.1145/2324796.2324843","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2324796.2324843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003276783","display_name":"Guangnan Ye","orcid":"https://orcid.org/0009-0007-4973-7942"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guangnan Ye","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075510768","display_name":"I\u2010Hong Jhuo","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"I-Hong Jhuo","raw_affiliation_strings":["National Taiwan University","National Taiwan University > > > > > >"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University > > > > > >","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407381","display_name":"Dong Liu","orcid":"https://orcid.org/0000-0001-9100-2906"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Liu","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088946301","display_name":"D. T. Lee","orcid":"https://orcid.org/0009-0009-6527-8883"},"institutions":[{"id":"https://openalex.org/I162838928","display_name":"National Chung Hsing University","ror":"https://ror.org/05vn3ca78","country_code":"TW","type":"education","lineage":["https://openalex.org/I162838928"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"D. T. Lee","raw_affiliation_strings":["National Taiwan University and National Chung Hsing University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University and National Chung Hsing University","institution_ids":["https://openalex.org/I162838928"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037340457","display_name":"Shih\u2010Fu Chang","orcid":"https://orcid.org/0000-0003-1444-1205"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shih-Fu Chang","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003276783"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":4.9987,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.95953436,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.797552227973938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7772728204727173},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7091517448425293},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.618254542350769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5506288409233093},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49659615755081177},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.47677281498908997},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4740733206272125},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4510308504104614},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44094762206077576},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.43838271498680115},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.4371722340583801},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41631385684013367},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.406521201133728},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40327146649360657},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15808320045471191},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.11891639232635498}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.797552227973938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7772728204727173},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7091517448425293},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.618254542350769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5506288409233093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49659615755081177},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.47677281498908997},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4740733206272125},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4510308504104614},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44094762206077576},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.43838271498680115},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.4371722340583801},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41631385684013367},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.406521201133728},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40327146649360657},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15808320045471191},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.11891639232635498},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2324796.2324843","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2324796.2324843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.394.1190","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.394.1190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.columbia.edu/ln/dvmm/publications/12/ICMR_Event.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306116","display_name":"U.S. Department of the Interior","ror":"https://ror.org/03v0pmy70"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333452","display_name":"Interior Business Center","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W142803501","https://openalex.org/W1532325895","https://openalex.org/W1606925698","https://openalex.org/W1625255723","https://openalex.org/W1965555842","https://openalex.org/W2009616550","https://openalex.org/W2010243644","https://openalex.org/W2020163092","https://openalex.org/W2024051019","https://openalex.org/W2025954386","https://openalex.org/W2109124605","https://openalex.org/W2132827378","https://openalex.org/W2133576408","https://openalex.org/W2140647972","https://openalex.org/W2151103935","https://openalex.org/W2162931300","https://openalex.org/W2172188317","https://openalex.org/W2182437395","https://openalex.org/W2274583232","https://openalex.org/W4285719527","https://openalex.org/W6636494156","https://openalex.org/W6656675045"],"related_works":["https://openalex.org/W2811390910","https://openalex.org/W2291847203","https://openalex.org/W2951391129","https://openalex.org/W2546942002","https://openalex.org/W2016461833","https://openalex.org/W3197541072","https://openalex.org/W4226125296","https://openalex.org/W2969680539","https://openalex.org/W3202266780","https://openalex.org/W2999511321"],"abstract_inverted_index":{"Joint":[0],"audio-visual":[1,45],"patterns":[2,88],"often":[3],"exist":[4],"in":[5],"videos":[6],"and":[7,23,68,101,108,139,143],"provide":[8],"strong":[9],"multi-modal":[10,127,145],"cues":[11],"for":[12,159],"detecting":[13],"multimedia":[14,118],"events.":[15],"However,":[16],"conventional":[17],"methods":[18,135],"generally":[19],"fuse":[20],"the":[21,61,66,73,81,86,99,105,125,155],"visual":[22,67,100,138],"audio":[24,69,102,140],"information":[25],"only":[26],"at":[27],"a":[28,43,54],"superficial":[29],"level,":[30],"without":[31],"adequately":[32],"exploring":[33],"deep":[34],"intrinsic":[35],"joint":[36,44,87],"patterns.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,149],"propose":[42],"bi-modal":[46,49,82,106,110,160],"representation,":[47],"called":[48],"words.":[50],"We":[51,121],"first":[52],"build":[53],"bipartite":[55,74],"graph":[56,75],"to":[57,79,97,116],"model":[58],"relation":[59],"across":[60,89],"quantized":[62],"words":[63,83,103,107],"extracted":[64],"from":[65],"modalities.":[70,90],"Partitioning":[71],"over":[72,134],"is":[76,154],"then":[77],"applied":[78],"construct":[80],"that":[84,113,124,151],"reveal":[85],"Finally,":[91],"different":[92],"pooling":[93,153],"strategies":[94],"are":[95,114],"employed":[96],"re-quantize":[98],"into":[104],"form":[109],"Bag-of-Words":[111],"representations":[112],"fed":[115],"subsequent":[117],"event":[119],"classifiers.":[120],"experimentally":[122],"show":[123],"proposed":[126],"feature":[128,161],"achieves":[129],"statistically":[130],"significant":[131],"performance":[132],"gains":[133],"using":[136],"individual":[137],"features":[141],"alone":[142],"alternative":[144],"fusion":[146],"methods.":[147],"Moreover,":[148],"found":[150],"average":[152],"most":[156],"suitable":[157],"strategy":[158],"generation.":[162]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}