{"id":"https://openalex.org/W4396827020","doi":"https://doi.org/10.1145/3664816","title":"SEMScene: Semantic-Consistency Enhanced Multi-Level Scene Graph Matching for Image-Text Retrieval","display_name":"SEMScene: Semantic-Consistency Enhanced Multi-Level Scene Graph Matching for Image-Text Retrieval","publication_year":2024,"publication_date":"2024-05-11","ids":{"openalex":"https://openalex.org/W4396827020","doi":"https://doi.org/10.1145/3664816"},"language":"en","primary_location":{"id":"doi:10.1145/3664816","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664816","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664816","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/10.1145/3664816","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101496409","display_name":"Yuankun Liu","orcid":"https://orcid.org/0009-0009-3600-1586"},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuankun Liu","raw_affiliation_strings":["School of Computer Science and Technology, North University of China, Taiyuan, China"],"raw_orcid":"https://orcid.org/0009-0009-3600-1586","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, North University of China, Taiyuan, China","institution_ids":["https://openalex.org/I135714990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101473805","display_name":"Xiang Yuan","orcid":"https://orcid.org/0009-0003-4377-8031"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Yuan","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-4377-8031","affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100742023","display_name":"Haochen Li","orcid":"https://orcid.org/0000-0002-3197-4073"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haochen Li","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing China"],"raw_orcid":"https://orcid.org/0000-0002-3197-4073","affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042812101","display_name":"Zhijie Tan","orcid":"https://orcid.org/0000-0003-4934-1001"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijie Tan","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing China"],"raw_orcid":"https://orcid.org/0000-0003-4934-1001","affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073458635","display_name":"J.-B. Huang","orcid":"https://orcid.org/0000-0003-4337-7003"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsong Huang","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing China"],"raw_orcid":"https://orcid.org/0000-0003-4337-7003","affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingjie Xiao","orcid":"https://orcid.org/0000-0003-2027-0369"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjie Xiao","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing China"],"raw_orcid":"https://orcid.org/0000-0003-2027-0369","affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085128839","display_name":"Weiping Li","orcid":"https://orcid.org/0000-0003-2958-3097"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiping Li","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing China"],"raw_orcid":"https://orcid.org/0000-0003-2958-3097","affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059356240","display_name":"Tong Mo","orcid":"https://orcid.org/0000-0002-3564-4610"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Mo","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing China"],"raw_orcid":"https://orcid.org/0000-0002-3564-4610","affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0936,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77584527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"20","issue":"8","first_page":"1","last_page":"28"},"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":0.9986000061035156,"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":0.9907000064849854,"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":0.7610374689102173},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.6067262291908264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5723350644111633},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5408542156219482},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5113937258720398},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5087533593177795},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5054492950439453},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.47784873843193054},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3888165354728699},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33281970024108887},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2383286952972412},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13183638453483582}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610374689102173},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.6067262291908264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5723350644111633},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5408542156219482},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5113937258720398},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5087533593177795},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5054492950439453},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.47784873843193054},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3888165354728699},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33281970024108887},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2383286952972412},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13183638453483582},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664816","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664816","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664816","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:10.1145/3664816","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664816","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664816","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":[{"score":0.5199999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7998994922","display_name":null,"funder_award_id":"2023YFC3304902","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396827020.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W1861492603","https://openalex.org/W2077069816","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2506483933","https://openalex.org/W2602856279","https://openalex.org/W2745461083","https://openalex.org/W2962964995","https://openalex.org/W2963101956","https://openalex.org/W2963536419","https://openalex.org/W2964120214","https://openalex.org/W2964187781","https://openalex.org/W2988823324","https://openalex.org/W2998356391","https://openalex.org/W3010277541","https://openalex.org/W3035017890","https://openalex.org/W3035454331","https://openalex.org/W3035605030","https://openalex.org/W3037533539","https://openalex.org/W3037773948","https://openalex.org/W3090449556","https://openalex.org/W3118694826","https://openalex.org/W3175888430","https://openalex.org/W3190055600","https://openalex.org/W3197809352","https://openalex.org/W3201645700","https://openalex.org/W3202436960","https://openalex.org/W3203447128","https://openalex.org/W3207608362","https://openalex.org/W4205712089","https://openalex.org/W4210894218","https://openalex.org/W4214819138","https://openalex.org/W4225832925","https://openalex.org/W4284698859","https://openalex.org/W4292258164","https://openalex.org/W4295679074","https://openalex.org/W4304086159","https://openalex.org/W4312407537","https://openalex.org/W4323663038","https://openalex.org/W4382657968","https://openalex.org/W4390873421"],"related_works":["https://openalex.org/W1603736412","https://openalex.org/W1972035260","https://openalex.org/W4304185162","https://openalex.org/W2061685118","https://openalex.org/W3006282800","https://openalex.org/W1986106996","https://openalex.org/W4285012873","https://openalex.org/W2122517733","https://openalex.org/W4392007279","https://openalex.org/W4387129494"],"abstract_inverted_index":{"Image-text":[0],"retrieval,":[1],"a":[2,95,160],"fundamental":[3],"cross-modal":[4,20],"task,":[5],"performs":[6],"similarity":[7],"reasoning":[8],"for":[9,16,42,151,185],"images":[10,43],"and":[11,29,44,51,114,140,196],"texts.":[12],"The":[13],"primary":[14],"challenge":[15],"image-text":[17,178],"retrieval":[18],"is":[19,38],"semantic":[21,25,85,110,137],"heterogeneity,":[22],"where":[23],"the":[24,63,76,81,109,124,149,170,174,189],"features":[26,64],"of":[27,83,176,188],"visual":[28,113],"textual":[30,115],"modalities":[31],"are":[32],"rich":[33],"but":[34],"distinct.":[35],"Scene":[36,102],"graph":[37,56,71,126,144],"an":[39],"effective":[40,182],"representation":[41],"texts":[45],"as":[46],"it":[47],"explicitly":[48],"models":[49],"objects":[50],"their":[52],"relations.":[53],"Existing":[54],"scene":[55,70,116,125,143],"based":[57],"methods":[58],"have":[59],"not":[60],"fully":[61],"taken":[62],"regarding":[65],"various":[66],"granularities":[67],"implicit":[68],"in":[69,164],"into":[72],"consideration":[73],"(e.g.,":[74,87],"triplets),":[75],"inadequate":[77],"feature":[78,130],"matching":[79,131],"incurs":[80],"absence":[82],"non-trivial":[84],"information":[86],"inner":[88],"relations":[89],"among":[90],"triplets).":[91],"Therefore,":[92],"we":[93,128,158,180],"propose":[94,159],"S":[96],"emantic-Consistency":[97],"E":[98],"nhanced":[99],"M":[100],"ulti-Level":[101],"Graph":[103],"Matching":[104],"(SEMScene)":[105],"network,":[106],"which":[107],"exploits":[108],"relevance":[111],"between":[112],"graphs":[117],"from":[118],"fine-grained":[119],"to":[120,147,168,172],"coarse-grained.":[121],"Firstly,":[122],"under":[123],"representation,":[127],"perform":[129],"including":[132],"low-level":[133],"node":[134],"matching,":[135,139],"mid-level":[136,165],"triplet":[138],"high-level":[141],"holistic":[142],"matching.":[145,166],"Secondly,":[146],"enhance":[148],"semantic-consistency":[150,175],"object-fused":[152],"triplets":[153],"carrying":[154],"key":[155],"correlation":[156],"information,":[157],"dual-step":[161,190],"constraint":[162],"mechanism":[163],"Thirdly,":[167],"guide":[169],"model":[171],"learn":[173],"matched":[177],"pairs,":[179],"devise":[181],"loss":[183],"functions":[184],"each":[186],"stage":[187],"constraint.":[191],"Comprehensive":[192],"experiments":[193],"on":[194],"Flickr30K":[195],"MS-COCO":[197],"datasets":[198],"demonstrate":[199],"that":[200],"SEMScene":[201],"achieves":[202],"state-of-the-art":[203],"performances":[204],"with":[205],"significant":[206],"improvements.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}