{"id":"https://openalex.org/W4399418593","doi":"https://doi.org/10.1145/3652583.3658094","title":"Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection","display_name":"Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418593","doi":"https://doi.org/10.1145/3652583.3658094"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658094","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658094","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658094","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658094","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yang Liu","orcid":"https://orcid.org/0009-0004-2757-0801"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-2757-0801","affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046146934","display_name":"Tongfei Shen","orcid":"https://orcid.org/0009-0008-7621-8125"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongfei Shen","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-7621-8125","affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115603674","display_name":"Dong Zhang","orcid":"https://orcid.org/0000-0002-8948-2856"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Zhang","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8948-2856","affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082914971","display_name":"Qingying Sun","orcid":"https://orcid.org/0000-0003-2580-8957"},"institutions":[{"id":"https://openalex.org/I4210147117","display_name":"Huaiyin Normal University","ror":"https://ror.org/03xvggv44","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210147117"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingying Sun","raw_affiliation_strings":["Huaiyin Normal University, Huai'an, China"],"raw_orcid":"https://orcid.org/0000-0003-2580-8957","affiliations":[{"raw_affiliation_string":"Huaiyin Normal University, Huai'an, China","institution_ids":["https://openalex.org/I4210147117"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003885809","display_name":"Shoushan Li","orcid":"https://orcid.org/0000-0002-1000-3278"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shoushan Li","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1000-3278","affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012794465","display_name":"Guodong Zhou","orcid":"https://orcid.org/0000-0002-7887-5099"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guodong Zhou","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7887-5099","affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":0.4762,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61359863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"442","last_page":"450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9934999942779541,"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":0.9934999942779541,"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/T11795","display_name":"Humor Studies and Applications","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9664000272750854,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.8305312991142273},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.646558940410614},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5734890103340149},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5409868359565735},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4842262268066406},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3677750825881958},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36491480469703674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305312991142273},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.646558940410614},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5734890103340149},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5409868359565735},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4842262268066406},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3677750825881958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36491480469703674},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658094","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658094","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658094","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658094","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658094","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658094","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1397134175","display_name":null,"funder_award_id":"62206193","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7939979782","display_name":null,"funder_award_id":"62006093","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324720","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418593.pdf","grobid_xml":"https://content.openalex.org/works/W4399418593.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2804900514","https://openalex.org/W2883429621","https://openalex.org/W2951804840","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2981851019","https://openalex.org/W2984008963","https://openalex.org/W2990503944","https://openalex.org/W3016193994","https://openalex.org/W3035265375","https://openalex.org/W3105232955","https://openalex.org/W3119298692","https://openalex.org/W3156636935","https://openalex.org/W3176481196","https://openalex.org/W3177099139","https://openalex.org/W3205255970","https://openalex.org/W3206020652","https://openalex.org/W3206529771","https://openalex.org/W3207721564","https://openalex.org/W4224916778","https://openalex.org/W4229455678","https://openalex.org/W4288804239","https://openalex.org/W4312560592","https://openalex.org/W4321485324","https://openalex.org/W4377140104","https://openalex.org/W4386076615","https://openalex.org/W4386076661","https://openalex.org/W4387185535"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2795079307","https://openalex.org/W2714992399","https://openalex.org/W2793058541"],"abstract_inverted_index":{"The":[0,81],"growing":[1],"importance":[2],"of":[3,15],"multi-modal":[4,46,67],"humor":[5,36,86],"detection":[6,37,87],"within":[7,76],"affective":[8],"computing":[9],"correlates":[10],"with":[11],"the":[12,71],"expanding":[13],"influence":[14],"short-form":[16,34],"video":[17,35,72],"sharing":[18],"on":[19,55,84],"social":[20],"media":[21],"platforms.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26],"propose":[27],"a":[28,77],"novel":[29],"two-branch":[30],"hierarchical":[31],"model":[32],"for":[33],"(SVHD),":[38],"named":[39],"Comment-aided":[40],"Video-Language":[41],"Alignment":[42],"(CVLA)":[43],"via":[44],"data-augmented":[45],"contrastive":[47],"pre-training.":[48],"Notably,":[49],"our":[50],"CVLA":[51,95],"not":[52],"only":[53],"operates":[54],"raw":[56],"signals":[57],"across":[58],"various":[59],"modal":[60],"channels":[61],"but":[62],"also":[63],"yields":[64],"an":[65],"appropriate":[66],"representation":[68],"by":[69],"aligning":[70],"and":[73,91,99,106],"language":[74],"components":[75],"consistent":[78],"semantic":[79],"space.":[80],"experimental":[82],"results":[83],"two":[85],"datasets,":[88],"including":[89],"DY11k":[90],"UR-FUNNY,":[92],"demonstrate":[93],"that":[94],"dramatically":[96],"outperforms":[97],"state-of-the-art":[98],"several":[100],"competitive":[101],"baseline":[102],"approaches.":[103],"Our":[104],"dataset":[105],"code":[107],"release":[108],"at":[109],"https://github.com/yliu-cs/CVLA.":[110]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}