{"id":"https://openalex.org/W4407826350","doi":"https://doi.org/10.1109/tip.2025.3542272","title":"Who, What, and Where: Composite-Semantics Instance Search for Story Videos","display_name":"Who, What, and Where: Composite-Semantics Instance Search for Story Videos","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407826350","doi":"https://doi.org/10.1109/tip.2025.3542272","pmid":"https://pubmed.ncbi.nlm.nih.gov/40031871"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3542272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3542272","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/A5102018989","display_name":"Jiahao Guo","orcid":"https://orcid.org/0009-0008-6682-7867"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiahao Guo","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101923081","display_name":"Ankang Lu","orcid":"https://orcid.org/0009-0002-7009-9205"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ankang Lu","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011464051","display_name":"Zhengqian Wu","orcid":"https://orcid.org/0009-0002-4258-9581"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqian Wu","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741750","display_name":"Zhongyuan Wang","orcid":"https://orcid.org/0000-0002-9796-488X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyuan Wang","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100748496","display_name":"Chao Liang","orcid":"https://orcid.org/0000-0002-8287-8655"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Liang","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102018989"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76206823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"34","issue":null,"first_page":"1412","last_page":"1426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":1.0,"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/T11439","display_name":"Video Analysis and Summarization","score":1.0,"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":0.9980999827384949,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9977999925613403,"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":0.6874215602874756},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6524308919906616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47672000527381897},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4489907920360565},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38986772298812866},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3508318066596985},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3302435576915741}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6874215602874756},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6524308919906616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47672000527381897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4489907920360565},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38986772298812866},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3508318066596985},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3302435576915741}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3542272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3542272","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:40031871","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40031871","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/G1414897554","display_name":null,"funder_award_id":"202102246004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1593960303","display_name":null,"funder_award_id":"62372339","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2454332764","display_name":null,"funder_award_id":"220800006041043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8278322568","display_name":null,"funder_award_id":"62371350","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8867103790","display_name":null,"funder_award_id":"202002142012","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":73,"referenced_works":["https://openalex.org/W1967140145","https://openalex.org/W2091390047","https://openalex.org/W2133065058","https://openalex.org/W2154642173","https://openalex.org/W2163292664","https://openalex.org/W2170480930","https://openalex.org/W2179298790","https://openalex.org/W2182930110","https://openalex.org/W2214124602","https://openalex.org/W2299778380","https://openalex.org/W2491030916","https://openalex.org/W2514348320","https://openalex.org/W2515770085","https://openalex.org/W2519200489","https://openalex.org/W2618160968","https://openalex.org/W2621096639","https://openalex.org/W2766730166","https://openalex.org/W2802567013","https://openalex.org/W2895800953","https://openalex.org/W2896457183","https://openalex.org/W2912859999","https://openalex.org/W2943235166","https://openalex.org/W2963566548","https://openalex.org/W2969985801","https://openalex.org/W2971680322","https://openalex.org/W2999851651","https://openalex.org/W3004301609","https://openalex.org/W3013718913","https://openalex.org/W3013942620","https://openalex.org/W3014043688","https://openalex.org/W3034364644","https://openalex.org/W3035598501","https://openalex.org/W3043840704","https://openalex.org/W3045623285","https://openalex.org/W3093814436","https://openalex.org/W3100211492","https://openalex.org/W3109813419","https://openalex.org/W3110420575","https://openalex.org/W3119324419","https://openalex.org/W3142513648","https://openalex.org/W3174989968","https://openalex.org/W3175939205","https://openalex.org/W3185960447","https://openalex.org/W4225856951","https://openalex.org/W4231791218","https://openalex.org/W4299783144","https://openalex.org/W4313186260","https://openalex.org/W4361761811","https://openalex.org/W4386072365","https://openalex.org/W4386255022","https://openalex.org/W4388188440","https://openalex.org/W4402775923","https://openalex.org/W6680597956","https://openalex.org/W6686765831","https://openalex.org/W6730520795","https://openalex.org/W6730854999","https://openalex.org/W6742227979","https://openalex.org/W6753375563","https://openalex.org/W6756614785","https://openalex.org/W6761937618","https://openalex.org/W6766691825","https://openalex.org/W6775305212","https://openalex.org/W6775334786","https://openalex.org/W6775722601","https://openalex.org/W6791353385","https://openalex.org/W6794013807","https://openalex.org/W6798805250","https://openalex.org/W6799488877","https://openalex.org/W6811013733","https://openalex.org/W6841668178","https://openalex.org/W6849177959","https://openalex.org/W6874582188","https://openalex.org/W6879093335"],"related_works":["https://openalex.org/W4231937131","https://openalex.org/W323219885","https://openalex.org/W2063928587","https://openalex.org/W1487966966","https://openalex.org/W1589342014","https://openalex.org/W1480341462","https://openalex.org/W598950423","https://openalex.org/W4256673449","https://openalex.org/W4292559016","https://openalex.org/W2143331802"],"abstract_inverted_index":{"Who,":[0],"What":[1],"and":[2,11,101,152,168,180,198,226,253],"Where":[3],"(3W)are":[4],"the":[5,14,21,29,96,105,119,137,159,174,177,185,205,208,244,249],"three":[6,142,214,221],"core":[7,131],"elements":[8],"of":[9,163,170,176,189,207],"storytelling,":[10],"accurately":[12],"identifying":[13],"3W":[15,30,138,200,216,257],"semantics":[16,164],"is":[17,107,133],"critical":[18],"to":[19,39,71,79,93,113,134],"understanding":[20],"story":[22,171,190,260],"in":[23,51,184,259],"a":[24,44,48,52,61,124],"video.":[25],"This":[26],"paper":[27],"studies":[28],"composite-semantics":[31,62],"video":[32,41,102,125,235],"Instance":[33],"Search":[34],"(INS)":[35],"problem,":[36],"which":[37,68],"aims":[38],"find":[40],"shots":[42,167,236],"about":[43],"specific":[45],"person":[46],"doing":[47],"concrete":[49],"action":[50],"particular":[53],"location.":[54],"The":[55,227],"popular":[56],"Complete-Decomposition":[57],"(CD)":[58],"methods":[59,87,255],"divide":[60],"query":[63,100],"into":[64,141],"multiple":[65],"single-semantics":[66],"queries,":[67],"are":[69],"likely":[70],"yield":[72],"inaccurate":[73],"or":[74],"incomplete":[75],"retrieval":[76],"results":[77],"due":[78],"neglecting":[80],"important":[81],"semantic":[82],"correlations.":[83],"Recent":[84],"Non-Decomposition":[85],"(ND)":[86],"utilize":[88],"Vision":[89],"Language":[90],"Model":[91],"(VLM)":[92],"directly":[94],"measure":[95],"similarity":[97],"between":[98,161],"textual":[99],"content.":[103],"However,":[104],"accuracy":[106],"limited":[108],"by":[109],"VLM's":[110],"immature":[111],"capability":[112],"recognize":[114],"fine-grained":[115],"objects.":[116],"To":[117,203],"address":[118],"above":[120],"challenges,":[121],"we":[122,156,192,211],"propose":[123],"structure-aware":[126],"Partial-Decomposition":[127],"(PD)":[128],"method.":[129],"Its":[130],"idea":[132],"partially":[135],"decompose":[136],"INS":[139,145,201,217,258],"problem":[140],"semantic-correlated":[143],"2W":[144],"problems":[146],"i.e.,":[147],"person-action":[148],"INS,":[149,151],"action-location":[150],"location-person":[153],"INS.":[154],"Thereafter,":[155],"respectively":[157],"model":[158],"correlations":[160],"pairs":[162],"at":[165],"frames,":[166],"scenes":[169],"videos.":[172,261],"With":[173],"help":[175],"spatial":[178],"consistency":[179],"temporal":[181],"continuity":[182],"contained":[183],"unique":[186],"hierarchical":[187],"structure":[188],"videos,":[191],"can":[193],"finally":[194],"obtain":[195],"identity-matching,":[196],"logic-consistent,":[197],"content-coherent":[199],"results.":[202],"validate":[204],"effectiveness":[206],"proposed":[209,245],"method,":[210],"specifically":[212],"build":[213],"large-scale":[215],"datasets":[218],"based":[219],"on":[220],"TV":[222],"series":[223],"Eastenders,":[224],"Friends":[225],"Big":[228],"Bang":[229],"Theory,":[230],"totally":[231],"comprising":[232],"over":[233],"670K":[234],"spanning":[237],"700":[238],"hours.":[239],"Extensive":[240],"experiments":[241],"show":[242],"that":[243],"PD":[246],"method":[247],"surpasses":[248],"current":[250],"state-of-the-art":[251],"CD":[252],"ND":[254],"for":[256]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}