{"id":"https://openalex.org/W4295679074","doi":"https://doi.org/10.1145/3563390","title":"Scene Graph Semantic Inference for Image and Text Matching","display_name":"Scene Graph Semantic Inference for Image and Text Matching","publication_year":2022,"publication_date":"2022-09-14","ids":{"openalex":"https://openalex.org/W4295679074","doi":"https://doi.org/10.1145/3563390"},"language":"en","primary_location":{"id":"doi:10.1145/3563390","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3563390","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"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 Asian and Low-Resource Language Information Processing","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/A5029365003","display_name":"Jiaming Pei","orcid":"https://orcid.org/0000-0003-2774-0511"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiaming Pei","raw_affiliation_strings":["School of Computer Science, University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-2774-0511","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051095951","display_name":"Kaiyang Zhong","orcid":"https://orcid.org/0000-0002-5575-0306"},"institutions":[{"id":"https://openalex.org/I204831749","display_name":"Southwestern University of Finance and Economics","ror":"https://ror.org/04ewct822","country_code":"CN","type":"education","lineage":["https://openalex.org/I204831749"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiyang Zhong","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0002-5575-0306","affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I204831749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006367063","display_name":"Zhi Yu","orcid":"https://orcid.org/0000-0003-2305-0492"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Yu","raw_affiliation_strings":["School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0003-2305-0492","affiliations":[{"raw_affiliation_string":"School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101572893","display_name":"Lukun Wang","orcid":"https://orcid.org/0000-0001-9207-7424"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lukun Wang","raw_affiliation_strings":["College of Intelligent equipment, Shandong University of Science and Technology, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-9207-7424","affiliations":[{"raw_affiliation_string":"College of Intelligent equipment, Shandong University of Science and Technology, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005478174","display_name":"Kuruva Lakshmanna","orcid":"https://orcid.org/0000-0003-3480-4851"},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kuruva Lakshmanna","raw_affiliation_strings":["School of Information Technology and Engineering, Vellore Institute of Technology, Tamil Nadu, India"],"raw_orcid":"https://orcid.org/0000-0003-3480-4851","affiliations":[{"raw_affiliation_string":"School of Information Technology and Engineering, Vellore Institute of Technology, Tamil Nadu, India","institution_ids":["https://openalex.org/I876193797"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9364,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.92508694,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"22","issue":"5","first_page":"1","last_page":"23"},"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":0.9987000226974487,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9929999709129333,"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":0.8128683567047119},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6879386305809021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6505602598190308},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.5552240014076233},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5414711236953735},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5287147164344788},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5261927247047424},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5148688554763794},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5113846659660339},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4904913306236267},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4746342599391937},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4745631814002991},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4486793875694275},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3613940477371216},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.12489345669746399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8128683567047119},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6879386305809021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6505602598190308},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.5552240014076233},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5414711236953735},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5287147164344788},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5261927247047424},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5148688554763794},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5113846659660339},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4904913306236267},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4746342599391937},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4745631814002991},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4486793875694275},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3613940477371216},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.12489345669746399},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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:10.1145/3563390","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3563390","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"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 Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W1949478088","https://openalex.org/W1957706851","https://openalex.org/W2112912048","https://openalex.org/W2123024445","https://openalex.org/W2185175083","https://openalex.org/W2250378130","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2546696630","https://openalex.org/W2579549467","https://openalex.org/W2596164567","https://openalex.org/W2606473278","https://openalex.org/W2613718673","https://openalex.org/W2624614404","https://openalex.org/W2745461083","https://openalex.org/W2765440071","https://openalex.org/W2770804203","https://openalex.org/W2778100917","https://openalex.org/W2778940641","https://openalex.org/W2786796754","https://openalex.org/W2798280084","https://openalex.org/W2883311563","https://openalex.org/W2888166343","https://openalex.org/W2890531016","https://openalex.org/W2894786240","https://openalex.org/W2900597592","https://openalex.org/W2903529742","https://openalex.org/W2904910963","https://openalex.org/W2953106684","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/W2963536419","https://openalex.org/W2963649796","https://openalex.org/W2963762755","https://openalex.org/W2963882743","https://openalex.org/W2963907629","https://openalex.org/W2964094751","https://openalex.org/W2964120214","https://openalex.org/W2964187781","https://openalex.org/W2964216321","https://openalex.org/W2964593454","https://openalex.org/W2967957126","https://openalex.org/W2981586349","https://openalex.org/W2982078236","https://openalex.org/W2988823324","https://openalex.org/W2990571534","https://openalex.org/W2994818707","https://openalex.org/W3010277541","https://openalex.org/W3014067266","https://openalex.org/W3034305926","https://openalex.org/W3035605030","https://openalex.org/W3138298063","https://openalex.org/W3153232703","https://openalex.org/W3155230099","https://openalex.org/W3163363326","https://openalex.org/W3171812887","https://openalex.org/W3195489797","https://openalex.org/W3198064418","https://openalex.org/W3201877472","https://openalex.org/W3207608362","https://openalex.org/W3210656256","https://openalex.org/W3210887046","https://openalex.org/W3211125622","https://openalex.org/W4206546481","https://openalex.org/W4214891830","https://openalex.org/W6678470764"],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2272354214","https://openalex.org/W2120383820","https://openalex.org/W2043010663","https://openalex.org/W2667588871","https://openalex.org/W1986106996","https://openalex.org/W4285012873","https://openalex.org/W2122517733"],"abstract_inverted_index":{"With":[0],"the":[1,52,60,71,87,149,178],"rapid":[2],"development":[3],"of":[4,54,62,89,152,159,180],"information":[5,23,119,146],"technology,":[6],"image":[7,110],"and":[8,15,27,30,42,47,75,78,94,111,122,135,155,161,170,172],"text":[9,16,28,112,123],"data":[10],"have":[11],"increased":[12],"dramatically.":[13],"Image":[14],"matching":[17,113,133,141],"techniques":[18],"enable":[19],"computers":[20],"to":[21,59,124,147],"understand":[22],"from":[24],"both":[25],"visual":[26,41,74,160],"modalities":[29],"match":[31],"them":[32],"based":[33],"on":[34,40],"semantic":[35,56,81,105,118,150],"content.":[36],"Existing":[37],"methods":[38],"focus":[39],"textual":[43,76,162],"object":[44,154],"co-occurrence":[45],"statistics":[46],"learning":[48],"coarse-level":[49],"associations.":[50],"However,":[51],"lack":[53],"intramodal":[55,80],"inference":[57,106],"leads":[58],"failure":[61],"fine-level":[63,117,157],"association":[64],"between":[65,73],"modalities.":[66,163],"Scene":[67],"graphs":[68,138],"can":[69],"capture":[70],"interactions":[72],"objects":[77],"model":[79],"associations,":[82],"which":[83,176],"are":[84],"crucial":[85],"for":[86,109,143],"understanding":[88],"scenes":[90],"contained":[91],"in":[92,120,168],"images":[93],"text.":[95],"In":[96],"this":[97],"article,":[98],"we":[99,130],"propose":[100],"a":[101],"novel":[102],"scene":[103,137],"graph":[104],"network":[107],"(SGSIN)":[108],"that":[114],"effectively":[115],"learns":[116],"vision":[121],"facilitate":[125],"bridging":[126],"cross-modal":[127],"discrepancies.":[128],"Specifically,":[129],"design":[131],"two":[132],"modules":[134],"construct":[136],"within":[139],"each":[140,153],"module":[142],"aggregating":[144],"neighborhood":[145],"refine":[148],"representation":[151],"achieve":[156,173],"alignment":[158],"We":[164],"perform":[165],"extended":[166],"experiments":[167],"Flickr30K":[169],"MSCOCO":[171],"state-of-the-art":[174],"results,":[175],"validate":[177],"advantages":[179],"our":[181],"proposed":[182],"approach.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}