{"id":"https://openalex.org/W4411019516","doi":"https://doi.org/10.1109/tip.2025.3574925","title":"Text-Video Retrieval With Global-LocalSemantic Consistent Learning","display_name":"Text-Video Retrieval With Global-LocalSemantic Consistent Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411019516","doi":"https://doi.org/10.1109/tip.2025.3574925","pmid":"https://pubmed.ncbi.nlm.nih.gov/40465439"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3574925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3574925","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084439574","display_name":"Haonan Zhang","orcid":"https://orcid.org/0000-0003-1015-7338"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Zhang","raw_affiliation_strings":["Future Media Center, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Future Media Center and School of Computer Science and Engineering, University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0003-1015-7338","affiliations":[{"raw_affiliation_string":"Future Media Center, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Future Media Center and School of Computer Science and Engineering, University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087623065","display_name":"Pengpeng Zeng","orcid":"https://orcid.org/0000-0002-0672-3790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengpeng Zeng","raw_affiliation_strings":["Sichuan Artificial Intelligence Research Institute, Yibin, China"],"raw_orcid":"https://orcid.org/0000-0002-0672-3790","affiliations":[{"raw_affiliation_string":"Sichuan Artificial Intelligence Research Institute, Yibin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China","Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-2522-6394","affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China","School of Computer Science and Technology, Tongji University, China"],"raw_orcid":"https://orcid.org/0000-0002-2549-8322","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100591737","display_name":"Yihang Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihang Duan","raw_affiliation_strings":["Future Media Center, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Future Media Center and School of Computer Science and Engineering, University of Electronic Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future Media Center, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Future Media Center and School of Computer Science and Engineering, University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090700061","display_name":"Xinyu Lyu","orcid":"https://orcid.org/0000-0003-2479-8881"},"institutions":[{"id":"https://openalex.org/I204831749","display_name":"Southwestern University of Finance and Economics","ror":"https://ror.org/04ewct822","country_code":"CN","type":"education","lineage":["https://openalex.org/I204831749"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Lyu","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-2479-8881","affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics, Chengdu, China","institution_ids":["https://openalex.org/I204831749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China","School of Computer Science and Technology, Tongji University, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.896,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.94182816,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"34","issue":null,"first_page":"3463","last_page":"3474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9908000230789185,"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":0.9908000230789185,"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":0.9825000166893005,"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/T10028","display_name":"Topic Modeling","score":0.9753000140190125,"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/computer-science","display_name":"Computer science","score":0.7357234358787537},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.6059777736663818},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5277343988418579},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4739121198654175},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.42370229959487915},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4217830002307892},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4013557434082031},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19947317242622375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7357234358787537},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.6059777736663818},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5277343988418579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4739121198654175},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.42370229959487915},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4217830002307892},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4013557434082031},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19947317242622375},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3574925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3574925","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:40465439","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40465439","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2546663186","display_name":null,"funder_award_id":"62020106008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3767017300","display_name":null,"funder_award_id":"62402094","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5422811002","display_name":null,"funder_award_id":"U23A20315","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5556742800","display_name":null,"funder_award_id":"JCYJ20240813114208012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8418174427","display_name":null,"funder_award_id":"82441006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G975111477","display_name":null,"funder_award_id":"62425208","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1893116441","https://openalex.org/W1927052826","https://openalex.org/W2425121537","https://openalex.org/W2753311918","https://openalex.org/W2808399042","https://openalex.org/W2963017553","https://openalex.org/W2970231061","https://openalex.org/W2984008963","https://openalex.org/W3035356601","https://openalex.org/W3043840704","https://openalex.org/W3090449556","https://openalex.org/W3128401049","https://openalex.org/W3168640669","https://openalex.org/W3201864842","https://openalex.org/W3204588463","https://openalex.org/W4225414521","https://openalex.org/W4285606530","https://openalex.org/W4304014690","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312383773","https://openalex.org/W4312999114","https://openalex.org/W4376607849","https://openalex.org/W4382458283","https://openalex.org/W4385767942","https://openalex.org/W4386065342","https://openalex.org/W4386065627","https://openalex.org/W4386076265","https://openalex.org/W4386076424","https://openalex.org/W4386076600","https://openalex.org/W4387967944","https://openalex.org/W4390190228","https://openalex.org/W4390874542","https://openalex.org/W4392908457","https://openalex.org/W4393108955","https://openalex.org/W4400679250","https://openalex.org/W4403791665","https://openalex.org/W6631190155","https://openalex.org/W6684090549","https://openalex.org/W6758474948","https://openalex.org/W6791353385","https://openalex.org/W6797148833","https://openalex.org/W6803872405","https://openalex.org/W6843263998","https://openalex.org/W6847215460","https://openalex.org/W6849177959"],"related_works":["https://openalex.org/W2393699422","https://openalex.org/W1986902711","https://openalex.org/W2396760013","https://openalex.org/W2148433556","https://openalex.org/W2171776552","https://openalex.org/W98391849","https://openalex.org/W1600907701","https://openalex.org/W2726741344","https://openalex.org/W2168037874","https://openalex.org/W2135728080"],"abstract_inverted_index":{"Adapting":[0],"large-scale":[1],"image-text":[2],"pre-training":[3],"models,":[4],"e.g.,":[5],"CLIP,":[6],"to":[7,25,49,86,103,119,139,147],"the":[8,12,121,125,141,167,173],"video":[9],"domain":[10],"represents":[11],"current":[13],"state-of-the-art":[14],"for":[15,37,75,108],"text-video":[16,23,76],"retrieval.":[17,51,77],"The":[18],"primary":[19],"approaches":[20],"involve":[21],"transferring":[22],"pairs":[24],"a":[26,57,81,93],"common":[27],"embedding":[28],"space":[29],"and":[30,128,132,164,170],"leveraging":[31],"cross-modal":[32],"interactions":[33],"on":[34,69,154],"specific":[35],"entities":[36],"semantic":[38,106],"alignment.":[39,89,111],"Though":[40],"effective,":[41],"these":[42],"paradigms":[43],"entail":[44],"prohibitive":[45],"computational":[46,195],"costs,":[47],"leading":[48],"inefficient":[50],"To":[52],"address":[53],"this,":[54],"we":[55,79,91],"propose":[56],"simple":[58],"yet":[59],"effective":[60],"method,":[61],"Global-Local":[62],"Semantic":[63],"Consistent":[64],"Learning":[65],"(GLSCL),":[66],"which":[67],"capitalizes":[68],"latent":[70,105],"shared":[71,94],"semantics":[72],"across":[73],"modalities":[74],"Specifically,":[78],"introduce":[80],"parameter-free":[82],"global":[83],"interaction":[84,96],"module":[85,97],"explore":[87],"coarse-grained":[88],"Then,":[90],"devise":[92],"local":[95],"that":[98],"employs":[99],"several":[100],"learnable":[101],"queries":[102,146],"capture":[104],"concepts":[107],"learning":[109],"fine-grained":[110],"Furthermore,":[112],"an":[113,133],"Inter-Consistency":[114],"Loss":[115,135],"(ICL)":[116],"is":[117,137,198],"devised":[118],"accomplish":[120],"concept":[122],"alignment":[123],"between":[124],"visual":[126,144],"query":[127],"corresponding":[129],"textual":[130],"query,":[131],"Intra-Diversity":[134],"(IDL)":[136],"developed":[138],"repulse":[140],"distribution":[142],"within":[143],"(textual)":[145],"generate":[148],"more":[149],"discriminative":[150],"concepts.":[151],"Extensive":[152],"experiments":[153],"five":[155],"widely":[156],"used":[157],"benchmarks":[158],"(i.e.,":[159],"MSR-VTT,":[160],"MSVD,":[161],"DiDeMo,":[162],"LSMDC,":[163],"ActivityNet)":[165],"substantiate":[166],"superior":[168],"effectiveness":[169],"efficiency":[171],"of":[172,194],"proposed":[174],"method.":[175],"Remarkably,":[176],"our":[177],"method":[178],"achieves":[179],"comparable":[180],"performance":[181],"with":[182],"SOTA":[183],"as":[184,186],"well":[185],"being":[187],"nearly":[188],"220":[189],"times":[190],"faster":[191],"in":[192],"terms":[193],"cost.":[196],"Code":[197],"available":[199],"at:":[200],"https://github.com/zchoi/GLSCL.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}