{"id":"https://openalex.org/W4416214650","doi":"https://doi.org/10.1109/tip.2025.3630883","title":"Disentangling Inter- and Intra-Video Relations for Multi-Event Video-Text Retrieval and Grounding","display_name":"Disentangling Inter- and Intra-Video Relations for Multi-Event Video-Text Retrieval and Grounding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416214650","doi":"https://doi.org/10.1109/tip.2025.3630883","pmid":"https://pubmed.ncbi.nlm.nih.gov/41237030"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3630883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3630883","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/A5101694456","display_name":"Mengzhao Wang","orcid":"https://orcid.org/0009-0003-5717-5290"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengzhao Wang","raw_affiliation_strings":["Faculty of Information Engineering and Automation and the Key Laboratory of Artificial Intelligence in Yunnan Province, Kunming University of Science and Technology, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation and the Key Laboratory of Artificial Intelligence in Yunnan Province, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080535168","display_name":"Huafeng Li","orcid":"https://orcid.org/0000-0003-2462-6174"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huafeng Li","raw_affiliation_strings":["Faculty of Information Engineering and Automation and the Key Laboratory of Artificial Intelligence in Yunnan Province, Kunming University of Science and Technology, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation and the Key Laboratory of Artificial Intelligence in Yunnan Province, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005210261","display_name":"Yafei Zhang","orcid":"https://orcid.org/0000-0003-2347-5642"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yafei Zhang","raw_affiliation_strings":["Faculty of Information Engineering and Automation and the Key Laboratory of Artificial Intelligence in Yunnan Province, Kunming University of Science and Technology, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation and the Key Laboratory of Artificial Intelligence in Yunnan Province, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100753458","display_name":"Jinxing Li","orcid":"https://orcid.org/0000-0001-5156-0305"},"institutions":[{"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":"Jinxing Li","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067600725","display_name":"Dapeng Tao","orcid":"https://orcid.org/0000-0003-0783-5273"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dapeng Tao","raw_affiliation_strings":["FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, China"],"affiliations":[{"raw_affiliation_string":"FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100619287","display_name":"Zhengtao Yu","orcid":"https://orcid.org/0000-0002-4012-461X"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao Yu","raw_affiliation_strings":["Faculty of Information Engineering and Automation and the Key Laboratory of Artificial Intelligence in Yunnan Province, Kunming University of Science and Technology, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation and the Key Laboratory of Artificial Intelligence in Yunnan Province, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101694456"],"corresponding_institution_ids":["https://openalex.org/I10660446"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85065153,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"34","issue":null,"first_page":"7558","last_page":"7571"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.010499999858438969,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.0044999998062849045,"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/event","display_name":"Event (particle physics)","score":0.7386000156402588},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6570000052452087},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6504999995231628},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5526000261306763},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.46209999918937683},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.38370001316070557},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.357699990272522},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.30799999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816100001335144},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7386000156402588},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6570000052452087},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6504999995231628},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5817000269889832},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5526000261306763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4758000075817108},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.46209999918937683},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.357699990272522},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3456999957561493},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.304500013589859},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.2646999955177307},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3630883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3630883","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:41237030","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41237030","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/G6545507832","display_name":null,"funder_award_id":"62276120","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6648850327","display_name":null,"funder_award_id":"202401AS070106","funder_id":"https://openalex.org/F4320330387","funder_display_name":"Foundation for Fundamental Research of China"},{"id":"https://openalex.org/G6961297351","display_name":null,"funder_award_id":"202301AV070004","funder_id":"https://openalex.org/F4320330387","funder_display_name":"Foundation for Fundamental Research of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330387","display_name":"Foundation for Fundamental Research of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1927052826","https://openalex.org/W1942126453","https://openalex.org/W2016053056","https://openalex.org/W2111078031","https://openalex.org/W2612112834","https://openalex.org/W2885775891","https://openalex.org/W2963017553","https://openalex.org/W2970373903","https://openalex.org/W2973172293","https://openalex.org/W2979933490","https://openalex.org/W2981716253","https://openalex.org/W2997429269","https://openalex.org/W2998355566","https://openalex.org/W2998841681","https://openalex.org/W3035339529","https://openalex.org/W3035524453","https://openalex.org/W3086629156","https://openalex.org/W3104862079","https://openalex.org/W3128401049","https://openalex.org/W3130619535","https://openalex.org/W3130796238","https://openalex.org/W3155721152","https://openalex.org/W3167480762","https://openalex.org/W3174873881","https://openalex.org/W3176763654","https://openalex.org/W3180476551","https://openalex.org/W3180664244","https://openalex.org/W3186567887","https://openalex.org/W3206683855","https://openalex.org/W3207042189","https://openalex.org/W3207439579","https://openalex.org/W3210101297","https://openalex.org/W4205817612","https://openalex.org/W4211053420","https://openalex.org/W4220818090","https://openalex.org/W4225414521","https://openalex.org/W4225547367","https://openalex.org/W4230025115","https://openalex.org/W4283814553","https://openalex.org/W4283822025","https://openalex.org/W4285606530","https://openalex.org/W4293567872","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312402470","https://openalex.org/W4361988974","https://openalex.org/W4376607849","https://openalex.org/W4387969779","https://openalex.org/W4390872455","https://openalex.org/W4390873373","https://openalex.org/W4392162962","https://openalex.org/W4402754238","https://openalex.org/W4404783315","https://openalex.org/W4406415185","https://openalex.org/W4406983459","https://openalex.org/W4409367066","https://openalex.org/W4409986095","https://openalex.org/W4410027467"],"related_works":[],"abstract_inverted_index":{"Video-text":[0],"retrieval":[1,43,77,91,97,215,266],"aims":[2],"to":[3,10,23,48,89,116,140],"precisely":[4],"search":[5],"for":[6,184,205,264,274],"videos":[7],"most":[8],"relevant":[9],"text":[11,120,164],"queries":[12,26],"within":[13,52,221],"a":[14,63,101,260],"video":[15,138,166],"corpus.":[16],"However,":[17],"existing":[18,229],"methods":[19,38],"are":[20,28],"largely":[21],"limited":[22],"single-text":[24],"(single-event)":[25],"and":[27,44,69,78,85,92,121,132,147,155,165,167,195,238,267,277],"not":[29,46,210],"effective":[30,169],"at":[31,128,286],"handling":[32],"multi-text":[33],"(multi-event)":[34],"queries.":[35],"Furthermore,":[36],"these":[37,58],"typically":[39],"focus":[40],"solely":[41],"on":[42,108,189,234],"do":[45],"attempt":[47],"locate":[49],"multiple":[50,200],"events":[51,146,188,201,220],"the":[53,96,109,134,152,190,222,226,235,243],"retrieved":[54,223],"videos.":[55,148,172],"To":[56],"address":[57],"limitations,":[59],"our":[60,247],"paper":[61],"proposes":[62],"novel":[64],"method":[65,81],"named":[66],"Disentangling":[67],"Inter-":[68],"Intra-Video":[70],"Relations,":[71],"which":[72,182],"jointly":[73],"addresses":[74],"multi-event":[75,268],"video-text":[76,265],"grounding.":[79],"This":[80,149],"leverages":[82],"both":[83],"inter-video":[84],"intra-video":[86],"event":[87,125,158,174],"relationships":[88,139],"enhance":[90],"grounding":[93,198,269],"performance.":[94],"At":[95],"level,":[98],"we":[99,176],"devise":[100],"Relational":[102],"Event-Centric":[103],"Video-Text":[104],"Retrieval":[105],"module":[106],"based":[107],"principle":[110],"that":[111],"comprehensive":[112],"textual":[113],"information":[114],"leads":[115],"precise":[117,197],"correspondence":[118],"between":[119,145,163],"video.":[122],"It":[123],"incorporates":[124],"relationship":[126],"features":[127],"different":[129],"hierarchical":[130,135],"levels":[131],"exploits":[133],"structure":[136],"of":[137,157,199,228,246,254],"achieve":[141],"multi-level":[142],"contrastive":[143],"learning":[144,204],"approach":[150],"enhances":[151],"richness,":[153],"accuracy,":[154],"comprehensiveness":[156],"descriptions,":[159],"improving":[160],"alignment":[161],"precision":[162],"enabling":[168],"differentiation":[170],"among":[171,187],"For":[173],"grounding,":[175],"propose":[177],"Event":[178],"Contrast-Driven":[179],"Video":[180],"Grounding,":[181],"accounts":[183],"positional":[185],"differences":[186],"2D":[191],"temporal":[192],"score":[193],"map":[194],"achieves":[196],"through":[202],"divergence":[203],"their":[206],"locations.":[207],"Our":[208],"solution":[209],"only":[211],"provides":[212],"efficient":[213],"text-to-video":[214],"but":[216],"also":[217],"accurately":[218],"grounds":[219],"videos,":[224],"addressing":[225],"shortcomings":[227],"methods.":[230],"Extensive":[231],"experimental":[232],"results":[233],"ActivityNet":[236],"Captions":[237],"Charades-STA":[239],"benchmark":[240],"datasets":[241],"demonstrate":[242],"superior":[244],"performance":[245],"method,":[248],"validating":[249],"its":[250],"effectiveness.":[251],"The":[252,282],"innovation":[253],"this":[255],"research":[256,276],"lies":[257],"in":[258,279],"introducing":[259],"new":[261,272],"joint":[262],"framework":[263],"while":[270],"offering":[271],"ideas":[273],"further":[275],"applications":[278],"related":[280],"fields.":[281],"code":[283],"is":[284],"available":[285],"https://github.com/X7J92/MVT-RG.":[287]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}
