{"id":"https://openalex.org/W7128809324","doi":"https://doi.org/10.26599/cvm.2025.9450444","title":"M2HF: Multi-Branch Multi-Modal Hybrid Fusion for Text-Video Retrieval","display_name":"M2HF: Multi-Branch Multi-Modal Hybrid Fusion for Text-Video Retrieval","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7128809324","doi":"https://doi.org/10.26599/cvm.2025.9450444"},"language":"en","primary_location":{"id":"doi:10.26599/cvm.2025.9450444","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450444","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.26599/cvm.2025.9450444","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125963448","display_name":"Shuo Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Liu","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences,Beijing,China,100190","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112268283","display_name":"Weize QUAN","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weize Quan","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences,Beijing,China,100190","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125958425","display_name":"Ming Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Zhou","raw_affiliation_strings":["School of Information Science and Technology, Donghua University,Shanghai,China,200051"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Donghua University,Shanghai,China,200051","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085164786","display_name":"Sihong Chen","orcid":null},"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":"Sihong Chen","raw_affiliation_strings":["Tencent,Shenzhen,China,518057"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shenzhen,China,518057","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125930159","display_name":"Jian Kang","orcid":null},"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":"Jian Kang","raw_affiliation_strings":["Tencent,Shenzhen,China,518057"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shenzhen,China,518057","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076585321","display_name":"Zhe Zhao","orcid":"https://orcid.org/0000-0002-8942-8761"},"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":"Zhe Zhao","raw_affiliation_strings":["Tencent,Shenzhen,China,518057"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shenzhen,China,518057","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074968914","display_name":"Kimmo Yan","orcid":null},"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":"Kimmo Yan","raw_affiliation_strings":["Tencent,Shenzhen,China,518057"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shenzhen,China,518057","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chen Chen","orcid":null},"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":"Chen Chen","raw_affiliation_strings":["Tencent,Shenzhen,China,518057"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shenzhen,China,518057","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125983154","display_name":"Dong-Ming Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong-Ming Yan","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences,Beijing,China,100190","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":22.6418,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.99298887,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"12","issue":"2","first_page":"449","last_page":"471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9866999983787537,"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":0.9866999983787537,"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":0.0026000000070780516,"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":0.002400000113993883,"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/exploit","display_name":"Exploit","score":0.5679000020027161},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5633999705314636},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5583999752998352},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4853000044822693},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.436599999666214},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.421999990940094},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4065999984741211},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.39969998598098755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8669000267982483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6025000214576721},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5583999752998352},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.421999990940094},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.39879998564720154},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.3788999915122986},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.375},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35109999775886536},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26599/cvm.2025.9450444","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450444","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1d14755b2caa4077b5142ba863dd79bd","is_oa":true,"landing_page_url":"https://doaj.org/article/1d14755b2caa4077b5142ba863dd79bd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Visual Media, Vol 12, Iss 2, Pp 449-471 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.26599/cvm.2025.9450444","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450444","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4177840054035187}],"awards":[{"id":"https://openalex.org/G5337790503","display_name":null,"funder_award_id":"62102418,62172415","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7192327807","display_name":null,"funder_award_id":"Z231100005923033","funder_id":"https://openalex.org/F4320335843","funder_display_name":"Beijing Science and Technology Planning Project"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335843","display_name":"Beijing Science and Technology Planning Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Videos":[0],"contain":[1],"multi-modal":[2,64,109,182],"content,":[3],"and":[4,76,93,104,115,127,175,214,221],"exploring":[5],"multi-branch":[6,63],"cross-modal":[7,53,137],"interactions":[8],"with":[9,91,139],"natural":[10],"language":[11],"queries":[12,75,142],"can":[13],"be":[14],"of":[15,44,168,191,209],"benefit":[16],"to":[17,69,99,135,156,187,201],"the":[18,27,131,158,189],"text-video":[19,160],"retrieval":[20,148,161],"task":[21],"(TVR).":[22],"However,":[23],"recent":[24],"methods":[25,43],"applying":[26],"large-scale":[28],"pre-trained":[29],"CLIP":[30,90],"model":[31],"for":[32,194],"TVR":[33],"only":[34],"focus":[35],"on":[36,205,216],"visual":[37,86,121],"cues":[38],"in":[39,55,80,117],"videos.":[40,56,81],"Furthermore,":[41],"traditional":[42],"simply":[45],"concatenating":[46],"multimodal":[47],"features":[48,87,95,103,106],"do":[49],"not":[50],"exploit":[51],"fine-grained":[52],"information":[54],"In":[57],"this":[58,118],"paper,":[59],"we":[60],"propose":[61],"a":[62,144,180],"hybrid":[65],"fusion":[66],"(M2HF)":[67],"network":[68],"hierarchically":[70],"explore":[71],"interaction":[72],"between":[73],"text":[74,128,141],"other":[77],"modality":[78,193],"content":[79],"Specifically,":[82],"M2HF":[83,198],"first":[84],"fuses":[85],"extracted":[88,96,129],"by":[89],"audio":[92],"motion":[94],"from":[97,130,150],"videos":[98],"obtain":[100,157,202],"fused":[101,155],"audio-visual":[102,123],"motion-visual":[105,125],"respectively.":[107,223],"The":[108,147],"completion":[110],"problem":[111],"is":[112,185],"also":[113],"considered":[114],"solved":[116],"process.":[119],"Then,":[120],"features,":[122,124,126],"video":[132],"are":[133,153],"used":[134],"establish":[136],"relationships":[138],"caption":[140],"using":[143,171],"multibranch":[145],"approach.":[146,178],"outputs":[149],"all":[151],"branches":[152],"then":[154],"final":[159],"results.":[162],"Our":[163],"framework":[164],"provides":[165],"two":[166],"kinds":[167],"training":[169],"strategies,":[170],"an":[172,176],"ensemble":[173],"approach":[174],"end-to-end":[177,196],"Moreover,":[179],"novel":[181],"loss":[183],"function":[184],"proposed":[186],"balance":[188],"contributions":[190],"each":[192],"efficient":[195],"training.":[197],"allows":[199],"us":[200],"state-of-the-art":[203],"results":[204],"various":[206],"benchmarks:":[207],"Rank@1":[208],"66.0%,":[210],"68.6%,":[211],"33.9%,":[212],"57.4%,":[213],"57.3%":[215],"MSR-VTT,":[217],"MSVD,":[218],"LSMDC,":[219],"DiDeMo,":[220],"ActivityNet,":[222]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2026-02-14T00:00:00"}