{"id":"https://openalex.org/W7128905149","doi":"https://doi.org/10.1145/3796712","title":"REFINE: Composed Video Retrieval via Shared and Differential Semantics Enhancement","display_name":"REFINE: Composed Video Retrieval via Shared and Differential Semantics Enhancement","publication_year":2026,"publication_date":"2026-02-14","ids":{"openalex":"https://openalex.org/W7128905149","doi":"https://doi.org/10.1145/3796712"},"language":"en","primary_location":{"id":"doi:10.1145/3796712","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3796712","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3796712","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yupeng Hu","orcid":"https://orcid.org/0000-0002-5653-8286"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupeng Hu","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-5653-8286","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zixu Li","orcid":"https://orcid.org/0009-0001-5136-159X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixu Li","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0001-5136-159X","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiwei Chen","orcid":"https://orcid.org/0009-0003-0365-8553"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Chen","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0003-0365-8553","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126005311","display_name":"Qinlei Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinlei Huang","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0009-0318-7599","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiheng Fu","orcid":"https://orcid.org/0009-0007-7724-5662"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiheng Fu","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0007-7724-5662","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mingzhu Xu","orcid":"https://orcid.org/0000-0002-1492-0970"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingzhu Xu","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-1492-0970","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126006005","display_name":"Liqiang Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.8969,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96058872,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"22","issue":"7","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9724000096321106,"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":0.9724000096321106,"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":0.013199999928474426,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.00279999990016222,"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/semantics","display_name":"Semantics (computer science)","score":0.6499999761581421},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.6208999752998352},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5586000084877014},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4959000051021576},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4945000112056732},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.460999995470047},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.3799000084400177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.902999997138977},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6499999761581421},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6227999925613403},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.6208999752998352},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5586000084877014},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4959000051021576},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4945000112056732},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3799000084400177},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.35249999165534973},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3059999942779541},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3796712","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3796712","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3796712","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3796712","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4544488787651062,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4980364176","display_name":null,"funder_award_id":"62276155, 62576195, and 62576194","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2597673421","https://openalex.org/W3092962760","https://openalex.org/W3154902219","https://openalex.org/W3157181916","https://openalex.org/W3172514680","https://openalex.org/W3174026887","https://openalex.org/W3206012133","https://openalex.org/W4224929299","https://openalex.org/W4312825288","https://openalex.org/W4313855701","https://openalex.org/W4385444701","https://openalex.org/W4385764644","https://openalex.org/W4386065703","https://openalex.org/W4386273457","https://openalex.org/W4386501573","https://openalex.org/W4387968356","https://openalex.org/W4390873539","https://openalex.org/W4390908058","https://openalex.org/W4391650123","https://openalex.org/W4393149123","https://openalex.org/W4393154871","https://openalex.org/W4393159792","https://openalex.org/W4401358015","https://openalex.org/W4402754243","https://openalex.org/W4403246017","https://openalex.org/W4403791707","https://openalex.org/W4404840231","https://openalex.org/W4409347665","https://openalex.org/W4409365871","https://openalex.org/W4409366213","https://openalex.org/W4409366745","https://openalex.org/W4409957270","https://openalex.org/W4410852654","https://openalex.org/W4412375108","https://openalex.org/W4412889669","https://openalex.org/W4412945336","https://openalex.org/W4414162697","https://openalex.org/W4414304383","https://openalex.org/W4415539507","https://openalex.org/W4416046108"],"related_works":[],"abstract_inverted_index":{"Composed":[0,168],"Video":[1],"Retrieval":[2,170],"(CVR)":[3],"is":[4,109],"a":[5,30,34,94,140],"novel":[6,95],"video":[7,13,19,21,32,42,68],"retrieval":[8,14,180],"paradigm.":[9],"Unlike":[10],"traditional":[11],"single-modal":[12],"paradigms":[15],"(e.g.,":[16],"text":[17],"to":[18,22,38,66,113,121,131,145,155,166],"or":[20,62],"video),":[23],"CVR":[24,51,96],"employs":[25,152],"multi-modal":[26,85,123,157,179],"queries":[27],"(including":[28],"both":[29],"reference":[31,48],"and":[33,80,100,117,151,182,188],"natural":[35],"language":[36],"modification)":[37],"retrieve":[39],"the":[40,46,74,78,110,115,167,196,199],"target":[41],"that":[43],"best":[44],"matches":[45],"modified":[47],"video.":[49],"Existing":[50],"methods":[52],"primarily":[53],"rely":[54],"on":[55,191],"generalized":[56],"knowledge":[57],"from":[58],"vision-language":[59],"pretrained":[60],"models":[61],"utilize":[63],"caption":[64],"expansions":[65],"enhance":[67],"comprehension.":[69,125],"However,":[70],"these":[71],"approaches":[72],"overlook":[73],"benefits":[75],"offered":[76],"by":[77],"shareability":[79,116],"variability":[81,118],"of":[82,119,198],"videos":[83,120],"for":[84],"query":[86,124,158],"understanding.":[87],"To":[88],"overcome":[89],"this":[90],"limitation,":[91],"we":[92],"introduce":[93],"framework":[97,112],"named":[98],"shaREd":[99],"diFferential":[101],"semantIcs":[102],"eNhancement":[103],"nEtwork":[104],"(":[105],"REFINE":[106,108,127,162,201],").":[107],"first":[111],"exploit":[114],"improve":[122],"Specifically,":[126],"leverages":[128],"learnable":[129],"tokens":[130],"achieve":[132],"enhanced":[133],"shared":[134],"feature":[135,159],"representation.":[136],"Moreover,":[137],"it":[138,173],"introduces":[139],"carefully":[141],"designed":[142],"Differential":[143],"Block":[144],"disentangle":[146],"differential":[147],"semantics":[148],"between":[149],"frames":[150],"modification":[153],"associations":[154],"guide":[156],"fusion.":[160],"Additionally,":[161],"has":[163],"been":[164],"extended":[165],"Image":[169],"task,":[171],"making":[172],"effectively":[174],"generalize":[175],"across":[176],"existing":[177,184],"composed":[178],"scenarios":[181],"outperform":[183],"methods.":[185],"Extensive":[186],"qualitative":[187],"quantitative":[189],"evaluations":[190],"four":[192],"benchmark":[193],"datasets":[194],"validate":[195],"superiority":[197],"proposed":[200],"framework.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-25T06:16:34.145877","created_date":"2026-02-15T00:00:00"}
