{"id":"https://openalex.org/W4415428926","doi":"https://doi.org/10.3233/faia250879","title":"Unlocking the Potential of mLLMs: Enhancing Video-Text Retrieval Through Caption Supplementation and Conical Embedding Optimization","display_name":"Unlocking the Potential of mLLMs: Enhancing Video-Text Retrieval Through Caption Supplementation and Conical Embedding Optimization","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428926","doi":"https://doi.org/10.3233/faia250879"},"language":null,"primary_location":{"id":"doi:10.3233/faia250879","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250879","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250879","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015849144","display_name":"Baoyao Yang","orcid":"https://orcid.org/0000-0001-9092-3164"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoyao Yang","raw_affiliation_strings":["School of Computers, Guangdong University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computers, Guangdong University of Technology","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091082342","display_name":"Junxiang Chen","orcid":"https://orcid.org/0000-0002-8897-754X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junxiang Chen","raw_affiliation_strings":["WeChat, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeChat, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080718178","display_name":"Wenbin Yao","orcid":"https://orcid.org/0000-0002-2830-102X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbin Yao","raw_affiliation_strings":["WeChat, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeChat, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63894408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9984999895095825,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9937000274658203,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/robustness","display_name":"Robustness (evolution)","score":0.5860999822616577},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5857999920845032},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5719000101089478},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.43880000710487366},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4138000011444092},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.41190001368522644},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.38269999623298645},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3752000033855438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760999798774719},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5860999822616577},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5857999920845032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5723000168800354},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.43880000710487366},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3944000005722046},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3752000033855438},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.366100013256073},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3034999966621399},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30070000886917114},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2727999985218048},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia250879","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250879","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia250879","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250879","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"burgeoning":[1],"field":[2],"of":[3,13,44,52,113,153,176],"video-text":[4,80],"retrieval":[5,81,118],"has":[6],"witnessed":[7],"significant":[8],"advancements":[9],"with":[10],"the":[11,31,42,72,94,110,117,138,174],"advent":[12],"deep":[14],"learning.":[15,119],"However,":[16,75],"understanding":[17],"and":[18,22,37,97,192,194,201],"matching":[19],"textual":[20,36],"descriptions":[21],"video":[23,38,46],"data":[24],"remains":[25],"a":[26,45,177],"formidable":[27],"challenge":[28],"due":[29],"to":[30,63,70,88,136,155,206],"large":[32],"information":[33,115],"gap":[34,140],"across":[35,141],"modalities.":[39,142],"As":[40],"observed,":[41],"caption":[43,131],"is":[47,83,171],"commonly":[48],"under-described,":[49],"lacking":[50],"expressions":[51],"minor":[53],"characters":[54],"or":[55],"local":[56],"details.":[57],"Some":[58],"recent":[59],"advances":[60],"have":[61],"attempted":[62],"leverage":[64],"multimodal":[65],"Large":[66],"Language":[67],"Model":[68],"(mLLM)":[69],"bridge":[71,137],"comprehension":[73],"gap.":[74],"mLLMs\u2019":[76],"potential":[77],"in":[78,103],"enhancing":[79],"(VTR)":[82],"understudied.":[84],"This":[85],"paper":[86],"aims":[87],"fill":[89],"this":[90],"research":[91],"vacancy,":[92],"analyzing":[93],"practical":[95],"significance":[96],"model":[98,182],"preferences":[99],"for":[100],"utilizing":[101],"mLLMs":[102],"VTR":[104],"enhancement,":[105],"as":[106,108,130,165],"well":[107],"investigating":[109],"effective":[111],"integration":[112],"mLLM-derived":[114],"into":[116],"Based":[120],"on":[121,186],"our":[122,203],"analytical":[123,195],"insights,":[124],"we":[125,148],"innovatively":[126],"propose":[127],"treating":[128,162],"mLLM":[129],"supplements":[132],"rather":[133],"than":[134],"substitutes":[135],"expression":[139],"To":[143],"achieve":[144],"better":[145],"cross-modal":[146,168],"alignment,":[147],"systematically":[149],"generate":[150],"diverse":[151],"variations":[152],"videos":[154],"construct":[156],"an":[157],"elastic":[158],"visual":[159],"space.":[160,180],"By":[161],"mLLM-supplemented":[163],"captions":[164],"out-of-space":[166],"points,":[167],"representation":[169,179],"learning":[170],"accomplished":[172],"through":[173],"optimization":[175],"conical-like":[178],"Our":[181],"achieves":[183],"state-of-the-art":[184],"results":[185],"various":[187],"benchmarks,":[188],"including":[189],"MSR-VTT,":[190],"MSVD,":[191],"DiDeMo,":[193],"experiments":[196],"suggest":[197],"appropriate":[198],"prompt":[199],"proposals":[200],"indicate":[202],"method\u2019s":[204],"robustness":[205],"different":[207],"mLLMs.":[208]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-24T00:00:00"}