{"id":"https://openalex.org/W4387968136","doi":"https://doi.org/10.1145/3581783.3611703","title":"Unlocking the Power of Cross-Dimensional Semantic Dependency for Image-Text Matching","display_name":"Unlocking the Power of Cross-Dimensional Semantic Dependency for Image-Text Matching","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968136","doi":"https://doi.org/10.1145/3581783.3611703"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611703","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5100342380","display_name":"Kun Zhang","orcid":"https://orcid.org/0000-0003-2140-2546"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kun Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616189","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-2839-8693"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036814758","display_name":"Bo Hu","orcid":"https://orcid.org/0000-0001-5508-5732"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Hu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076599775","display_name":"Mengxiao Zhu","orcid":"https://orcid.org/0000-0003-3596-5585"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxiao Zhu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023341829","display_name":"Zhendong Mao","orcid":"https://orcid.org/0000-0001-5739-8126"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Mao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100342380"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.0262,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.8900967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4828","last_page":"4837"},"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":0.9990000128746033,"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":0.9926000237464905,"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":0.783409059047699},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.6324894428253174},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6152693629264832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5771779417991638},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5739272236824036},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5593915581703186},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5295670628547668},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5032994151115417},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4761395752429962},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4670295715332031},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45954981446266174},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4520558714866638},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.4148905277252197},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41451552510261536},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3432005047798157},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3023715615272522},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12612682580947876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.783409059047699},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.6324894428253174},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6152693629264832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5771779417991638},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5739272236824036},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5593915581703186},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5295670628547668},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5032994151115417},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4761395752429962},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4670295715332031},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45954981446266174},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4520558714866638},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.4148905277252197},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41451552510261536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3432005047798157},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3023715615272522},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12612682580947876},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611703","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3841266055","display_name":null,"funder_award_id":"6222221","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7854910236","display_name":null,"funder_award_id":"62222212","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":43,"referenced_works":["https://openalex.org/W1560724230","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1957706851","https://openalex.org/W2131774270","https://openalex.org/W2187089797","https://openalex.org/W2277195237","https://openalex.org/W2745461083","https://openalex.org/W2964727037","https://openalex.org/W2965848243","https://openalex.org/W2982078236","https://openalex.org/W2997403743","https://openalex.org/W2997525715","https://openalex.org/W2998215884","https://openalex.org/W3010277541","https://openalex.org/W3035212740","https://openalex.org/W3035552787","https://openalex.org/W3091588028","https://openalex.org/W3094172275","https://openalex.org/W3108373531","https://openalex.org/W3111984153","https://openalex.org/W3118694826","https://openalex.org/W3155230099","https://openalex.org/W3175505770","https://openalex.org/W3175888430","https://openalex.org/W3177343494","https://openalex.org/W3211094189","https://openalex.org/W4206314411","https://openalex.org/W4210894218","https://openalex.org/W4224952037","https://openalex.org/W4283805294","https://openalex.org/W4283812943","https://openalex.org/W4285606316","https://openalex.org/W4304080167","https://openalex.org/W4304080357","https://openalex.org/W4304084117","https://openalex.org/W4304091788","https://openalex.org/W4312438350","https://openalex.org/W4312761738","https://openalex.org/W4323338501","https://openalex.org/W4360897523","https://openalex.org/W4386071757","https://openalex.org/W6600553734"],"related_works":["https://openalex.org/W2907506409","https://openalex.org/W3152143533","https://openalex.org/W2139549667","https://openalex.org/W4385572821","https://openalex.org/W2315716767","https://openalex.org/W2374902383","https://openalex.org/W2375695570","https://openalex.org/W4387489691","https://openalex.org/W2355975607","https://openalex.org/W2792318346"],"abstract_inverted_index":{"Image-text":[0],"matching,":[1],"as":[2],"a":[3,43,115,150],"fundamental":[4],"cross-modal":[5,55,106],"task,":[6],"bridges":[7],"vision":[8],"and":[9,33,125,145,159,177,194],"language.":[10],"The":[11],"key":[12],"challenge":[13],"lies":[14],"in":[15,65,133],"accurately":[16],"learning":[17,166],"the":[18,28,61,128,134,162,170,181],"semantic":[19,29,103,118,129,156],"similarity":[20,30],"of":[21,54,183],"these":[22],"two":[23],"heterogeneous":[24],"modalities.":[25],"To":[26,109],"determine":[27],"between":[31,131],"visual":[32],"textual":[34],"features,":[35],"existing":[36],"paradigm":[37],"typically":[38],"first":[39],"maps":[40],"them":[41],"into":[42],"d-dimensional":[44],"shared":[45,135],"representation":[46],"space,":[47,136],"then":[48],"independently":[49],"aggregates":[50],"all":[51],"dimensional":[52],"correspondences":[53],"features":[56],"to":[57,88,99,142,153,167],"reflect":[58],"it,":[59],"e.g.,":[60],"inner":[62],"product.":[63],"However,":[64],"this":[66,94,111],"paper,":[67],"we":[68,113],"are":[69,77,83],"motivated":[70],"by":[71],"an":[72],"insightful":[73],"finding":[74],"that":[75],"dimensions":[76,87,132,138],"not":[78],"mutually":[79],"independent,":[80],"but":[81],"there":[82],"intrinsic":[84,95],"dependencies":[85,130,141],"among":[86],"jointly":[89],"represent":[90],"latent":[91],"semantics.":[92],"Ignoring":[93],"information":[96],"probably":[97],"leads":[98],"suboptimal":[100],"aggregation":[101],"for":[102],"similarity,":[104],"impairing":[105],"matching":[107],"learning.":[108],"solve":[110],"issue,":[112],"propose":[114],"novel":[116],"cross-dimensional":[117],"dependency-aware":[119],"model":[120,171],"(called":[121],"X-Dim),":[122],"which":[123],"explicitly":[124],"adaptively":[126],"mines":[127],"enabling":[137],"with":[139],"joint":[140],"be":[143],"enhanced":[144],"utilized.":[146],"X-Dim":[147,184],"(1)":[148],"designs":[149],"generalized":[151],"framework":[152],"learn":[154],"dimensions'":[155],"dependency":[157],"degrees,":[158],"(2)":[160],"devises":[161],"adaptive":[163],"sparse":[164],"probabilistic":[165],"autonomously":[168],"make":[169],"capture":[172],"precise":[173],"dependencies.":[174],"Theoretical":[175],"analysis":[176],"extensive":[178],"experiments":[179],"demonstrate":[180],"superiority":[182],"over":[185],"state-of-the-art":[186],"methods,":[187],"achieving":[188],"5.9%-7.3%":[189],"rSum":[190],"improvements":[191],"on":[192],"Flickr30K":[193],"MS-COCO":[195],"benchmarks.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}