{"id":"https://openalex.org/W4407638053","doi":"https://doi.org/10.1109/tmm.2025.3542894","title":"Aggregate and Discriminate: Pseudo Clips-Guided Boundary Perception for Video Moment Retrieval","display_name":"Aggregate and Discriminate: Pseudo Clips-Guided Boundary Perception for Video Moment Retrieval","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407638053","doi":"https://doi.org/10.1109/tmm.2025.3542894"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3542894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3542894","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},"type":"article","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/A5100375136","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-4690-1886"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-4690-1886","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zongbing Zhang","orcid":"https://orcid.org/0009-0001-2533-7473"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongbing Zhang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0001-2533-7473","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033713097","display_name":"Yuting Su","orcid":"https://orcid.org/0000-0001-5165-204X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Su","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5165-204X","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101434967","display_name":"Bing Yang","orcid":"https://orcid.org/0000-0001-8307-3683"},"institutions":[{"id":"https://openalex.org/I4210130112","display_name":"China Academy of Information and Communications Technology","ror":"https://ror.org/038dte259","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210130112","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Yang","raw_affiliation_strings":["China Academy of Electronics and Information Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8307-3683","affiliations":[{"raw_affiliation_string":"China Academy of Electronics and Information Technology, Beijing, China","institution_ids":["https://openalex.org/I4210130112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043405654","display_name":"Xiongkuo Min","orcid":"https://orcid.org/0000-0001-5693-0416"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongkuo Min","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5693-0416","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064168853","display_name":"Guangtao Zhai","orcid":"https://orcid.org/0000-0001-8165-9322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtao Zhai","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8165-9322","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67066236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"27","issue":null,"first_page":"4819","last_page":"4830"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9997000098228455,"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/computer-science","display_name":"Computer science","score":0.8208022713661194},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.6830295324325562},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.5929939150810242},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5731087327003479},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5029067397117615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49277499318122864},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45920947194099426},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.44423675537109375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33753612637519836},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32151657342910767},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07828378677368164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8208022713661194},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.6830295324325562},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.5929939150810242},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5731087327003479},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5029067397117615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49277499318122864},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45920947194099426},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.44423675537109375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33753612637519836},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32151657342910767},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07828378677368164},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3542894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3542894","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1691401027","display_name":null,"funder_award_id":"U22B2037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3007184350","display_name":null,"funder_award_id":"62371333","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5632917453","display_name":null,"funder_award_id":"62371330","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":61,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2111078031","https://openalex.org/W2250539671","https://openalex.org/W2961553857","https://openalex.org/W2963017553","https://openalex.org/W2963524571","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2970401629","https://openalex.org/W2970898753","https://openalex.org/W2974686944","https://openalex.org/W2997429269","https://openalex.org/W2997762001","https://openalex.org/W2998495542","https://openalex.org/W3034730770","https://openalex.org/W3035339529","https://openalex.org/W3035356601","https://openalex.org/W3088744711","https://openalex.org/W3096609285","https://openalex.org/W3132753749","https://openalex.org/W3135773387","https://openalex.org/W3157181916","https://openalex.org/W3175402857","https://openalex.org/W3176763654","https://openalex.org/W3178087530","https://openalex.org/W3199096350","https://openalex.org/W3211772574","https://openalex.org/W4205605843","https://openalex.org/W4224993577","https://openalex.org/W4284693480","https://openalex.org/W4285216227","https://openalex.org/W4285606530","https://openalex.org/W4290066011","https://openalex.org/W4292092982","https://openalex.org/W4312341368","https://openalex.org/W4312372711","https://openalex.org/W4312555593","https://openalex.org/W4312941859","https://openalex.org/W4313555695","https://openalex.org/W4320008746","https://openalex.org/W4320713023","https://openalex.org/W4322576376","https://openalex.org/W4322747262","https://openalex.org/W4327810593","https://openalex.org/W4327852044","https://openalex.org/W4385245566","https://openalex.org/W4385571847","https://openalex.org/W4385757441","https://openalex.org/W4385800698","https://openalex.org/W4386083094","https://openalex.org/W4386231783","https://openalex.org/W4386453815","https://openalex.org/W4391971934","https://openalex.org/W4392207775","https://openalex.org/W4394730979","https://openalex.org/W4403562293","https://openalex.org/W6784094891","https://openalex.org/W6804424445","https://openalex.org/W6841618256","https://openalex.org/W6850826453","https://openalex.org/W6854585117"],"related_works":["https://openalex.org/W2417253731","https://openalex.org/W2350469024","https://openalex.org/W2491583298","https://openalex.org/W2036154621","https://openalex.org/W2327827625","https://openalex.org/W2395860100","https://openalex.org/W1936207157","https://openalex.org/W795077857","https://openalex.org/W2376416463","https://openalex.org/W2007338512"],"abstract_inverted_index":{"Video":[0],"moment":[1,103,145],"retrieval":[2,104],"(VMR)":[3],"aims":[4],"to":[5,18,59,92,115,141,161],"localize":[6],"a":[7,19,68,100,135,151],"video":[8,13,35,64,102,113,127],"segment":[9],"in":[10,28,67,77,82],"an":[11],"untrimmed":[12],"that":[14,179],"is":[15],"semantically":[16,164],"relevant":[17,110,144],"language":[20,130],"query.":[21],"The":[22],"challenge":[23],"of":[24,51,63,158],"this":[25,96],"task":[26],"lies":[27],"effectively":[29],"aligning":[30],"the":[31,38,46,52,79,108,116,123,156,163,171],"intricate":[32],"and":[33,43,48,65,84,89,111,129,149,175],"information-dense":[34],"modality":[36,128],"with":[37,155],"succinctly":[39],"summarized":[40],"textual":[41],"modality,":[42],"further":[44],"localizing":[45],"starting":[47],"ending":[49],"timestamps":[50],"target":[53],"moments.":[54],"Previous":[55],"works":[56],"have":[57],"attempted":[58],"achieve":[60],"multi-granularity":[61],"alignment":[62],"query":[66,117],"coarse-to-fine":[69],"manner,":[70],"yet":[71],"these":[72],"efforts":[73],"still":[74],"fall":[75],"short":[76],"addressing":[78],"inherent":[80],"disparities":[81],"representation":[83],"information":[85],"density":[86],"between":[87,126],"videos":[88],"queries,":[90],"leading":[91],"modal":[93],"misalignments.":[94],"In":[95],"paper,":[97],"we":[98,133],"propose":[99,150],"progressive":[101],"framework,":[105],"initially":[106],"retrieving":[107],"most":[109],"irrelevant":[112],"clips":[114,137,146,160],"as":[118],"semantic":[119,124],"guidance,":[120],"thereby":[121],"bridging":[122],"gap":[125],"modality.":[131],"Futhermore,":[132],"introduce":[134],"pseudo":[136,159],"guided":[138],"aggregation":[139],"module":[140],"aggregate":[142],"densely":[143],"closer":[147],"together":[148],"discriminative":[152],"boundary-enhanced":[153],"decoder":[154],"guidance":[157],"push":[162],"confusing":[165],"proposals":[166],"away.":[167],"Extensive":[168],"experiments":[169],"on":[170],"Charades-STA,":[172],"ActivityNet":[173],"Captions":[174],"TACoS":[176],"datasets":[177],"demonstrate":[178],"our":[180],"method":[181],"outperforms":[182],"existing":[183],"methods.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}