{"id":"https://openalex.org/W4415707678","doi":"https://doi.org/10.1109/icme59968.2025.11209958","title":"Key-semantics Alignment Learning with Contextual Understanding for Video Moment Retrieval","display_name":"Key-semantics Alignment Learning with Contextual Understanding for Video Moment Retrieval","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707678","doi":"https://doi.org/10.1109/icme59968.2025.11209958"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5075508706","display_name":"Chenghua Gao","orcid":"https://orcid.org/0000-0001-8677-3853"},"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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenghua Gao","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100719013","display_name":"Min Li","orcid":"https://orcid.org/0000-0002-0188-1394"},"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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102402394","display_name":"Junxing Ren","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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junxing Ren","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443774","display_name":"Lin Chen","orcid":"https://orcid.org/0000-0002-8702-9345"},"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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Chen","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113373707","display_name":"Jitao Fu","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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jitao Fu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110690932","display_name":"Wenwen Su","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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwen Su","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7627999782562256,"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":0.7627999782562256,"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":0.094200000166893,"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":0.0430000014603138,"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":0.6251000165939331},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6046000123023987},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5616000294685364},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5220000147819519},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.40959998965263367},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.40310001373291016},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.39570000767707825},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.38580000400543213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8130999803543091},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6251000165939331},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6046000123023987},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5616000294685364},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5220000147819519},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46810001134872437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2816999852657318},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2904824998","https://openalex.org/W2939519298","https://openalex.org/W2962869524","https://openalex.org/W2963017553","https://openalex.org/W2964089981","https://openalex.org/W2990503944","https://openalex.org/W2997429269","https://openalex.org/W3034743747","https://openalex.org/W3094550259","https://openalex.org/W3096609285","https://openalex.org/W3104862079","https://openalex.org/W3105232955","https://openalex.org/W4214582399","https://openalex.org/W4312544061","https://openalex.org/W4386083094","https://openalex.org/W4390190760","https://openalex.org/W4390873341","https://openalex.org/W4393148542","https://openalex.org/W4393159223","https://openalex.org/W4402754238"],"related_works":[],"abstract_inverted_index":{"Video":[0],"Moment":[1],"Retrieval":[2],"(VMR)":[3],"aims":[4],"to":[5,14,50,108,123,132,138,148],"retrieve":[6],"relevant":[7,87],"moments":[8],"of":[9,59,83,114],"an":[10],"untrimmed":[11],"video":[12,39,63,88,98,153],"corresponding":[13,38],"the":[15,28,32,37,47,110,115,134,139,145,150],"query.":[16],"While":[17],"many":[18],"approaches":[19],"have":[20],"shown":[21],"progress":[22],"in":[23,56],"cross-modal":[24,111],"interaction,":[25],"they":[26],"assume":[27],"precise":[29],"alignment":[30,48,82,103],"between":[31],"whole":[33],"query":[34,84,101,126,140],"semantics":[35,61],"and":[36,62,86,100,104,128,161],"clips.":[40,64],"However,":[41],"this":[42,67],"strong":[43],"assumption":[44],"often":[45],"causes":[46],"process":[49],"be":[51],"disturbed":[52],"by":[53],"noise,":[54],"resulting":[55],"suboptimal":[57],"matching":[58],"key":[60],"To":[65],"address":[66],"challenge,":[68],"we":[69,91,118,143],"propose":[70],"Key-semantics":[71],"Alignment":[72],"Learning":[73],"with":[74],"contextual":[75],"Understanding":[76],"(KALU),":[77],"a":[78],"novel":[79],"model":[80],"for":[81],"key-semantics":[85],"moments.":[89,154],"Firstly,":[90],"leverage":[92],"global":[93],"partial":[94],"aligner":[95],"module":[96,122,131],"via":[97],"clip":[99,135],"features":[102,136],"video-query":[105],"contrastive":[106],"learning":[107],"enhance":[109],"understanding":[112],"capabilities":[113],"model.":[116],"Subsequently,":[117],"employ":[119],"intent":[120],"focus":[121],"obtain":[124],"intention-driven":[125],"features,":[127],"visual":[129],"enhancement":[130],"refine":[133],"related":[137],"intent.":[141],"Finally,":[142],"adopt":[144],"DETR":[146],"structure":[147],"predict":[149],"possible":[151],"target":[152],"Through":[155],"extensive":[156],"evaluations":[157],"on":[158],"QVHighlights,":[159],"Charades-STA,":[160],"ActivityNet":[162],"datasets,":[163],"KALU":[164],"achieves":[165],"state-of-the-art":[166],"performance.":[167]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}
