{"id":"https://openalex.org/W3206149424","doi":"https://doi.org/10.1145/3474085.3475567","title":"Exploring Graph-Structured Semantics for Cross-Modal Retrieval","display_name":"Exploring Graph-Structured Semantics for Cross-Modal Retrieval","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206149424","doi":"https://doi.org/10.1145/3474085.3475567","mag":"3206149424"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th 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/A5100433914","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-4477-5532"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017395798","display_name":"Leiting Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leiting Chen","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003262869","display_name":"Chuan Zhou","orcid":"https://orcid.org/0000-0001-7700-7188"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Zhou","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102014086","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0002-0940-4218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["AIQ, Abu Dhabi, UAE"],"affiliations":[{"raw_affiliation_string":"AIQ, Abu Dhabi, UAE","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100353741","display_name":"Xin Li","orcid":"https://orcid.org/0000-0001-8047-9610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["AIQ, Abu Dhabi, UAE"],"affiliations":[{"raw_affiliation_string":"AIQ, Abu Dhabi, UAE","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100433914"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":1.1528,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.80812092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4277","last_page":"4286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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":0.9864000082015991,"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":0.7924696207046509},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6223125457763672},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6118189692497253},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5946754217147827},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5865135788917542},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5731208324432373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5131862759590149},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4740604758262634},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4566343128681183},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4371717572212219},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42727047204971313},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3991406559944153},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3631531596183777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7924696207046509},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6223125457763672},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6118189692497253},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5946754217147827},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5865135788917542},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5731208324432373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131862759590149},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4740604758262634},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4566343128681183},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4371717572212219},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42727047204971313},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3991406559944153},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3631531596183777},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1523385540","https://openalex.org/W1662382123","https://openalex.org/W1686810756","https://openalex.org/W1832693441","https://openalex.org/W1949478088","https://openalex.org/W1964073652","https://openalex.org/W2007972815","https://openalex.org/W2013535308","https://openalex.org/W2025341678","https://openalex.org/W2030899956","https://openalex.org/W2038158923","https://openalex.org/W2049633694","https://openalex.org/W2052727801","https://openalex.org/W2070753207","https://openalex.org/W2071207147","https://openalex.org/W2099471712","https://openalex.org/W2100235303","https://openalex.org/W2106277773","https://openalex.org/W2119775030","https://openalex.org/W2138118304","https://openalex.org/W2170653751","https://openalex.org/W2184188583","https://openalex.org/W2216973458","https://openalex.org/W2326180695","https://openalex.org/W2574447816","https://openalex.org/W2605649771","https://openalex.org/W2608015370","https://openalex.org/W2613526370","https://openalex.org/W2745461083","https://openalex.org/W2765440071","https://openalex.org/W2787844696","https://openalex.org/W2799263800","https://openalex.org/W2949541494","https://openalex.org/W2950359962","https://openalex.org/W2954672622","https://openalex.org/W2963224792","https://openalex.org/W2964019343","https://openalex.org/W2964130424","https://openalex.org/W2964216321","https://openalex.org/W2966146145","https://openalex.org/W2967957126","https://openalex.org/W2997403460","https://openalex.org/W3010124057","https://openalex.org/W3035043849","https://openalex.org/W3035541121","https://openalex.org/W3092802919","https://openalex.org/W3093418233","https://openalex.org/W3096966254","https://openalex.org/W3151753041","https://openalex.org/W3152015664","https://openalex.org/W3173782971"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2081900870","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2183306018","https://openalex.org/W627697492","https://openalex.org/W4283320496","https://openalex.org/W4390871823","https://openalex.org/W4311555960"],"abstract_inverted_index":{"We":[0,209],"study":[1],"and":[2,40,101,122,141,176,204,228],"address":[3],"the":[4,11,31,64,76,79,99,113,133,174,178],"cross-modal":[5,105,154,207],"retrieval":[6],"problem":[7],"which":[8,156],"lies":[9,19],"at":[10,242],"heart":[12],"of":[13,33,45,115,198],"visual-textual":[14],"processing.":[15],"Its":[16],"major":[17],"challenge":[18],"in":[20,118],"how":[21],"to":[22,62,96,110,128,137,161,171,194],"effectively":[23],"learn":[24,63],"a":[25,91,146,164],"shared":[26],"multi-modal":[27],"feature":[28,130],"space":[29],"where":[30],"discrepancies":[32],"semantically":[34],"related":[35],"pairs,":[36],"such":[37],"as":[38,125],"images":[39],"texts,":[41],"are":[42],"minimized":[43],"regardless":[44],"their":[46],"modalities.":[47,183],"Most":[48],"current":[49],"methods":[50],"focus":[51],"on":[52,223],"reasoning":[53],"about":[54],"cross-modality":[55],"semantic":[56,126],"relations":[57],"within":[58,75,82],"individual":[59],"image-text":[60],"pair":[61],"common":[65,149],"representation.":[66],"However,":[67],"they":[68],"overlook":[69],"more":[70,139],"global,":[71],"structural":[72],"inter-pair":[73],"knowledge":[74],"dataset,":[77],"i.e.,":[78],"graph-structured":[80],"semantics":[81],"each":[83],"training":[84,199],"batch.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89],"introduce":[90],"graph-based,":[92],"semantic-constrained":[93],"learning":[94,151,167,203],"framework":[95],"comprehensively":[97],"explore":[98,112],"intra-":[100],"inter-modality":[102],"information":[103],"for":[104,153,201],"retrieval.":[106,208],"Our":[107,184,232],"idea":[108],"is":[109,157,169,192,240],"maximally":[111],"structures":[114,197],"labeled":[116],"data":[117,200],"graph":[119],"latent":[120],"space,":[121],"use":[123],"them":[124],"constraints":[127],"enforce":[129],"embeddings":[131],"from":[132],"semantically-matched":[134],"(image-text)":[135],"pairs":[136],"be":[138,235],"similar":[140],"vice":[142],"versa.":[143],"It":[144],"raises":[145],"novel":[147],"graph-constrained":[148],"embedding":[150],"paradigm":[152],"retrieval,":[155],"largely":[158],"under-explored":[159],"up":[160],"now.":[162],"Moreover,":[163],"GAN-based":[165],"dual":[166],"approach":[168],"used":[170],"further":[172],"improve":[173],"discriminability":[175],"model":[177,202],"joint":[179],"distribution":[180],"across":[181],"different":[182],"fully-equipped":[185],"approach,":[186],"called":[187],"Graph-constrained":[188],"Cross-modal":[189],"Retrieval":[190],"(GCR),":[191],"able":[193],"mine":[195],"intrinsic":[196],"enable":[205],"reliable":[206],"empirically":[210],"demonstrate":[211],"that":[212],"our":[213],"GCR":[214],"can":[215],"achieve":[216],"higher":[217],"accuracy":[218],"than":[219],"existing":[220],"state-of-the-art":[221],"approaches":[222],"Wikipedia,":[224],"NUS-WIDE-10K,":[225],"PKU":[226],"XMedia":[227],"Pascal":[229],"Sentence":[230],"datasets.":[231],"code":[233],"will":[234],"made":[236],"publicly":[237],"available.":[238],"Code":[239],"available":[241],"https://github.com/neoscheung/GCR.":[243]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}