{"id":"https://openalex.org/W4401847474","doi":"https://doi.org/10.1145/3689638","title":"QR-CLIP: Introducing Explicit Knowledge for Location and Time Reasoning","display_name":"QR-CLIP: Introducing Explicit Knowledge for Location and Time Reasoning","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401847474","doi":"https://doi.org/10.1145/3689638"},"language":"en","primary_location":{"id":"doi:10.1145/3689638","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689638","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3689638","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3689638","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102379100","display_name":"Weimin Shi","orcid":"https://orcid.org/0009-0004-2344-1025"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Shi","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-2344-1025","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062149619","display_name":"Dehong Gao","orcid":"https://orcid.org/0000-0002-6636-5702"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dehong Gao","raw_affiliation_strings":["School of Cybersecurity, Northwestern Polytechnical University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0000-0002-6636-5702","affiliations":[{"raw_affiliation_string":"School of Cybersecurity, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026163124","display_name":"Yuan Xiong","orcid":"https://orcid.org/0000-0002-7253-4998"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Xiong","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7253-4998","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102905671","display_name":"Zhong Zhou","orcid":"https://orcid.org/0000-0002-5825-7517"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Zhou","raw_affiliation_strings":["Zhongguancun Laboratory, Beijing, China and State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5825-7517","affiliations":[{"raw_affiliation_string":"Zhongguancun Laboratory, Beijing, China and State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4935,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60345682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"20","issue":"11","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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":0.9988999962806702,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965999722480774,"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":0.8475766181945801},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.678999125957489},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6646198034286499},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.604535698890686},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.49059978127479553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48778754472732544},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4427139163017273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8475766181945801},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.678999125957489},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6646198034286499},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.604535698890686},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.49059978127479553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48778754472732544},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4427139163017273},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3689638","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689638","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3689638","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3689638","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689638","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3689638","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5099911738","display_name":null,"funder_award_id":"62272018","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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401847474.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W29249083","https://openalex.org/W128638292","https://openalex.org/W2016540947","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2742330194","https://openalex.org/W2905129313","https://openalex.org/W2914304175","https://openalex.org/W2997129483","https://openalex.org/W3005680577","https://openalex.org/W3019129093","https://openalex.org/W3034275286","https://openalex.org/W3035524453","https://openalex.org/W3035738719","https://openalex.org/W3116109061","https://openalex.org/W3131500599","https://openalex.org/W3133755445","https://openalex.org/W3138516171","https://openalex.org/W3153682083","https://openalex.org/W3156892778","https://openalex.org/W3185106195","https://openalex.org/W4210334834","https://openalex.org/W4213144930","https://openalex.org/W4226099034","https://openalex.org/W4236544382","https://openalex.org/W4285171517","https://openalex.org/W4285212850","https://openalex.org/W4306800771","https://openalex.org/W4312407537","https://openalex.org/W4312629998","https://openalex.org/W4312825288","https://openalex.org/W4312854990","https://openalex.org/W4313156423","https://openalex.org/W4313175608","https://openalex.org/W4385804899","https://openalex.org/W4386065414","https://openalex.org/W4386065433","https://openalex.org/W4389523839","https://openalex.org/W4394625575","https://openalex.org/W4399804785","https://openalex.org/W6811009250"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W3006162251"],"abstract_inverted_index":{"This":[0],"article":[1],"focuses":[2],"on":[3],"reasoning":[4,55,59,79,161,186,210],"about":[5,92],"the":[6,45,87,116,145,149,166,174,179,197,204],"location":[7,35,93,182,207],"and":[8,21,36,94,122,127,148,153,168,184,189,208,213],"time":[9,95,185,209],"behind":[10],"images.":[11],"Given":[12],"that":[13,83,134],"pre-trained":[14],"vision-language":[15],"models":[16],"(VLMs)":[17],"exhibit":[18],"excellent":[19],"image":[20,117],"text":[22],"understanding":[23],"capabilities,":[24],"most":[25],"existing":[26],"methods":[27,41],"leverage":[28],"them":[29,124,156],"to":[30,52,90,125,137,157],"match":[31],"visual":[32,62,146],"cues":[33,67],"with":[34,64,98],"time-related":[37],"descriptions.":[38],"However,":[39],"these":[40],"cannot":[42],"look":[43],"beyond":[44],"actual":[46],"content":[47],"of":[48,108,170,181],"an":[49],"image,":[50],"failing":[51],"produce":[53],"satisfactory":[54],"results,":[56],"as":[57,103],"such":[58,102],"requires":[60],"connecting":[61],"details":[63],"rich":[65],"external":[66,99,129],"(e.g.,":[68],"relevant":[69],"event":[70],"contexts).":[71],"To":[72],"this":[73],"end,":[74],"we":[75],"propose":[76],"a":[77,159],"novel":[78],"method,":[80],"QR-CLIP":[81,106,171,177],",":[82],"aims":[84],"at":[85,220],"enhancing":[86],"model\u2019s":[88],"ability":[89],"reason":[91],"through":[96],"interaction":[97],"explicit":[100,151],"knowledge":[101,130,152],"Wikipedia.":[104],"Specifically,":[105],"consists":[107],"two":[109],"modules:":[110],"(1)":[111],"The":[112,141,216],"Quantity":[113],"module":[114,143],"abstracts":[115],"into":[118],"multiple":[119],"distinct":[120],"representations":[121],"uses":[123],"search":[126],"gather":[128],"from":[131],"different":[132],"perspectives":[133],"are":[135],"beneficial":[136],"model":[138],"reasoning.":[139],"(2)":[140],"Relevance":[142],"filters":[144],"features":[147],"searched":[150],"dynamically":[154],"integrates":[155],"form":[158],"comprehensive":[160],"result.":[162],"Extensive":[163],"experiments":[164],"demonstrate":[165],"effectiveness":[167],"generalizability":[169],".":[172,222],"On":[173,196],"WikiTiLo":[175],"dataset,":[176,201],"boosts":[178],"accuracy":[180,205],"(country)":[183],"by":[187,211],"7.03%":[188],"2.22%,":[190],"respectively,":[191],"over":[192],"previous":[193],"SOTA":[194],"methods.":[195],"more":[198],"challenging":[199],"TARA":[200],"it":[202],"improves":[203],"for":[206],"3.05%":[212],"2.45%,":[214],"respectively.":[215],"source":[217],"code":[218],"is":[219],"https://github.com/Shi-Wm/QR-CLIP":[221]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}