{"id":"https://openalex.org/W3010277541","doi":"https://doi.org/10.1109/wacv45572.2020.9093614","title":"Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval","display_name":"Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3010277541","doi":"https://doi.org/10.1109/wacv45572.2020.9093614","mag":"3010277541"},"language":"en","primary_location":{"id":"doi:10.1109/wacv45572.2020.9093614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-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/A5035660663","display_name":"Sijin Wang","orcid":"https://orcid.org/0009-0007-1637-9405"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sijin Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","Institute of Computing Technology, CAS,Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Computing Technology, CAS,Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614962","display_name":"Ruiping Wang","orcid":"https://orcid.org/0000-0003-1830-2595"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiping Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","Institute of Computing Technology, CAS,Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Computing Technology, CAS,Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101931697","display_name":"Ziwei Yao","orcid":"https://orcid.org/0009-0000-4854-8217"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziwei Yao","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","Institute of Computing Technology, CAS,Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Computing Technology, CAS,Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050297728","display_name":"Shiguang Shan","orcid":"https://orcid.org/0000-0002-8348-392X"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiguang Shan","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","Institute of Computing Technology, CAS,Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Computing Technology, CAS,Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083420537","display_name":"Xilin Chen","orcid":"https://orcid.org/0000-0003-3024-4404"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilin Chen","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","Institute of Computing Technology, CAS,Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Computing Technology, CAS,Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176","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":14.6825,"has_fulltext":false,"cited_by_count":245,"citation_normalized_percentile":{"value":0.99283409,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1497","last_page":"1506"},"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":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9830999970436096,"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":0.7537885904312134},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.6027708053588867},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5759616494178772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5668558478355408},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5653175115585327},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5034646391868591},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.49188685417175293},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4508093595504761},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4364754557609558},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4188944697380066},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4145117998123169},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4022350311279297},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38838624954223633},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.20213571190834045},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12330275774002075}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537885904312134},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.6027708053588867},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5759616494178772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5668558478355408},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5653175115585327},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5034646391868591},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.49188685417175293},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4508093595504761},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4364754557609558},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4188944697380066},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4145117998123169},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4022350311279297},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38838624954223633},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.20213571190834045},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12330275774002075},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv45572.2020.9093614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1527575280","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1957706851","https://openalex.org/W2077069816","https://openalex.org/W2112912048","https://openalex.org/W2123024445","https://openalex.org/W2149557440","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2250378130","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2552579943","https://openalex.org/W2579549467","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2765440071","https://openalex.org/W2774267535","https://openalex.org/W2798782720","https://openalex.org/W2890531016","https://openalex.org/W2894786240","https://openalex.org/W2904910963","https://openalex.org/W2953106684","https://openalex.org/W2956018683","https://openalex.org/W2962779575","https://openalex.org/W2962964995","https://openalex.org/W2963101956","https://openalex.org/W2963184176","https://openalex.org/W2963389687","https://openalex.org/W2963467339","https://openalex.org/W2963499204","https://openalex.org/W2963536419","https://openalex.org/W2963649796","https://openalex.org/W2963762755","https://openalex.org/W2964120214","https://openalex.org/W2964121744","https://openalex.org/W4210257598","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6631516269","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6676647902","https://openalex.org/W6678470764","https://openalex.org/W6747225742","https://openalex.org/W6749537441","https://openalex.org/W6807384801"],"related_works":["https://openalex.org/W2063218608","https://openalex.org/W4386105885","https://openalex.org/W2184288218","https://openalex.org/W2147874738","https://openalex.org/W2071180033","https://openalex.org/W2374066281","https://openalex.org/W2011260834","https://openalex.org/W4387423606","https://openalex.org/W155590726","https://openalex.org/W2513891871"],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1,128],"of":[2,20,45,67,72,75,99,112,159,189,215],"natural":[3,38,87],"scenes":[4],"has":[5],"been":[6],"a":[7,60,170,198],"popular":[8],"research":[9],"topic.":[10],"Since":[11],"image":[12,40,93,190],"and":[13,49,81,94,106,120,152,174,191,208],"text":[14,95,192],"are":[15,53],"heterogeneous":[16],"cross-modal":[17,135,176],"data,":[18],"one":[19],"the":[21,34,70,123,157,163,187,194,213],"key":[22],"challenges":[23],"is":[24,114,130],"how":[25],"to":[26,32,56,91,116,185],"learn":[27],"comprehensive":[28],"yet":[29],"unified":[30],"representations":[31],"express":[33],"multi-modal":[35],"data.":[36],"A":[37],"scene":[39,76,100,103,108,136,144],"mainly":[41],"involves":[42],"two":[43,97,142,195],"kinds":[44,98],"visual":[46,102],"concepts,":[47],"objects":[48,119],"their":[50],"relationships,":[51],"which":[52,113,154,181,211],"equally":[54],"essential":[55],"image-text":[57,127,222],"retrieval.":[58,223],"Therefore,":[59],"good":[61],"representation":[62,158],"should":[63],"account":[64],"for":[65,84,150,221],"both":[66,172],"them.":[68],"In":[69],"light":[71],"recent":[73],"success":[74],"graph":[77,104,109,137,145,164,217],"in":[78,122,147,193,197],"many":[79],"CV":[80],"NLP":[82],"tasks":[83],"describing":[85],"complex":[86],"scenes,":[88],"we":[89,140],"propose":[90],"represent":[92],"with":[96],"graphs:":[101],"(VSG)":[105],"textual":[107],"(TSG),":[110],"each":[111,160],"exploited":[115],"jointly":[117],"characterize":[118],"relationships":[121],"corresponding":[124],"modality.":[125],"The":[126],"task":[129],"then":[131],"naturally":[132],"formulated":[133],"as":[134],"matching.":[138],"Specifically,":[139],"design":[141],"particular":[143],"encoders":[146],"our":[148,216],"model":[149],"VSG":[151],"TSG,":[153],"can":[155,178],"refine":[156],"node":[161],"on":[162,206],"by":[165],"aggregating":[166],"neighborhood":[167],"information.":[168],"As":[169],"result,":[171],"object-level":[173],"relationship-level":[175],"features":[177],"be":[179],"obtained,":[180],"favorably":[182],"enables":[183],"us":[184],"evaluate":[186],"similarity":[188],"levels":[196],"more":[199],"plausible":[200],"way.":[201],"We":[202],"achieve":[203],"state-of-the-art":[204],"results":[205],"Flickr30k":[207],"MS":[209],"COCO,":[210],"verifies":[212],"advantages":[214],"matching":[218],"based":[219],"approach":[220]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":61},{"year":2023,"cited_by_count":46},{"year":2022,"cited_by_count":51},{"year":2021,"cited_by_count":44},{"year":2020,"cited_by_count":9}],"updated_date":"2026-06-28T08:01:55.173337","created_date":"2025-10-10T00:00:00"}