{"id":"https://openalex.org/W4410637122","doi":"https://doi.org/10.1145/3701716.3718369","title":"Optimizing Discriminative Vision-Language Models for Efficient Multimodal Intent Recognition","display_name":"Optimizing Discriminative Vision-Language Models for Efficient Multimodal Intent Recognition","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410637122","doi":"https://doi.org/10.1145/3701716.3718369"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3718369","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3718369","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3718369","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3718369","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102632341","display_name":"Jinwang Song","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinwang Song","raw_affiliation_strings":["Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-1001-1966","affiliations":[{"raw_affiliation_string":"Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117649552","display_name":"Zhongtian Hua","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongtian Hua","raw_affiliation_strings":["Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-0344-9601","affiliations":[{"raw_affiliation_string":"Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062969664","display_name":"Hongying Zan","orcid":"https://orcid.org/0000-0002-8874-1262"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongying Zan","raw_affiliation_strings":["Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8874-1262","affiliations":[{"raw_affiliation_string":"Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102366295","display_name":"Yingjie Han","orcid":"https://orcid.org/0000-0002-8613-8996"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjie Han","raw_affiliation_strings":["Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8613-8996","affiliations":[{"raw_affiliation_string":"Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114778045","display_name":"Min Peng","orcid":"https://orcid.org/0000-0002-8766-1105"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Peng","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-8766-1105","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3063","last_page":"3067"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9003999829292297,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9003999829292297,"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/discriminative-model","display_name":"Discriminative model","score":0.8417041301727295},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7885701656341553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6237867474555969},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43514636158943176},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42880910634994507},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42073673009872437},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34871748089790344}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8417041301727295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7885701656341553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6237867474555969},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43514636158943176},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42880910634994507},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42073673009872437},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34871748089790344}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3718369","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3718369","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3718369","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701716.3718369","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3718369","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3718369","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G2511542536","display_name":null,"funder_award_id":"U23A20316","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6131237001","display_name":null,"funder_award_id":"U23A20316","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410637122.pdf","grobid_xml":"https://content.openalex.org/works/W4410637122.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W4281758439","https://openalex.org/W4392172801","https://openalex.org/W4399317728","https://openalex.org/W4403573100"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2395910192","https://openalex.org/W2112752961","https://openalex.org/W2113687551"],"abstract_inverted_index":{"The":[0],"WWW2025":[1],"Multimodal":[2],"Dialogue":[3],"System":[4],"Intent":[5],"Recognition":[6],"Challenge":[7],"aims":[8],"to":[9,22],"enhance":[10],"the":[11,43,89,97,100],"understanding":[12],"capabilities":[13],"of":[14,75],"e-commerce":[15],"intelligent":[16],"customer":[17],"service":[18],"systems,":[19],"requiring":[20],"participants":[21],"develop":[23],"intent":[24,38],"recognition":[25],"models":[26],"that":[27,72],"jointly":[28],"analyze":[29],"textual":[30],"and":[31,63,66,83,102],"visual":[32],"information":[33],"for":[34],"more":[35],"precise":[36],"user":[37],"interpretation.":[39],"This":[40],"paper":[41],"presents":[42],"solution":[44],"proposed":[45],"by":[46],"Team":[47],"Adventure,":[48],"which":[49,94],"proposes":[50],"an":[51],"optimized":[52],"framework":[53],"based":[54],"on":[55],"Vision-Language":[56],"Models":[57],"(VLMs),":[58],"incorporating":[59],"data":[60],"augmentation,":[61],"generative":[62],"discriminative":[64,73,103],"fine-tuning,":[65],"inference":[67,84],"optimization.":[68],"Experimental":[69],"results":[70],"demonstrate":[71],"fine-tuning":[74,104],"VLMs":[76],"offers":[77],"significant":[78],"advantages":[79],"in":[80],"training":[81],"efficiency":[82],"speed.":[85],"Furthermore,":[86],"we":[87],"introduce":[88],"Label-Token":[90],"Initialization":[91],"(LTI)":[92],"method,":[93],"effectively":[95],"mitigates":[96],"mismatch":[98],"between":[99],"pre-training":[101],"stages.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}