{"id":"https://openalex.org/W4387967913","doi":"https://doi.org/10.1145/3581783.3612103","title":"Giving Text More Imagination Space for Image-text Matching","display_name":"Giving Text More Imagination Space for Image-text Matching","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387967913","doi":"https://doi.org/10.1145/3581783.3612103"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612103","doi":"https://doi.org/10.1145/3581783.3612103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612103","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612103","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612103","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079360792","display_name":"Xinfeng Dong","orcid":"https://orcid.org/0009-0001-6159-635X","observed_orcids":["https://orcid.org/0009-0001-6159-635X"]},"institutions":[{"id":"https://openalex.org/I28006308","display_name":"Shandong Normal University","ror":"https://ror.org/01wy3h363","country_code":"CN","type":"education","lineage":["https://openalex.org/I28006308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfeng Dong","raw_affiliation_strings":["Shandong Normal University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0001-6159-635X","affiliations":[{"raw_affiliation_string":"Shandong Normal University, Jinan, China","institution_ids":["https://openalex.org/I28006308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030947378","display_name":"Longfei Han","orcid":"https://orcid.org/0000-0003-2135-6228","observed_orcids":["https://orcid.org/0000-0003-2135-6228"]},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longfei Han","raw_affiliation_strings":["Beijing Technology and Business University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2135-6228","affiliations":[{"raw_affiliation_string":"Beijing Technology and Business University, Beijing, China","institution_ids":["https://openalex.org/I179026463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101954574","display_name":"Dingwen Zhang","orcid":"https://orcid.org/0000-0001-8369-8886","observed_orcids":["https://orcid.org/0000-0001-8369-8886"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingwen Zhang","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8369-8886","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418866","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-9121-5124","observed_orcids":["https://orcid.org/0000-0002-9121-5124"]},"institutions":[{"id":"https://openalex.org/I28006308","display_name":"Shandong Normal University","ror":"https://ror.org/01wy3h363","country_code":"CN","type":"education","lineage":["https://openalex.org/I28006308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["Shandong Normal University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-9121-5124","affiliations":[{"raw_affiliation_string":"Shandong Normal University, Jinan, China","institution_ids":["https://openalex.org/I28006308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012529382","display_name":"Junwei Han","orcid":"https://orcid.org/0000-0001-5545-7217","observed_orcids":["https://orcid.org/0000-0001-5545-7217"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junwei Han","raw_affiliation_strings":["Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5545-7217","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113755120","display_name":"Huaxiang Zhang","orcid":"https://orcid.org/0000-0001-6259-7533","observed_orcids":["https://orcid.org/0000-0001-6259-7533","https://orcid.org/0000-0002-0316-994X","https://orcid.org/0009-0006-5285-8545"]},"institutions":[{"id":"https://openalex.org/I28006308","display_name":"Shandong Normal University","ror":"https://ror.org/01wy3h363","country_code":"CN","type":"education","lineage":["https://openalex.org/I28006308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaxiang Zhang","raw_affiliation_strings":["Shandong Normal University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-6259-7533","affiliations":[{"raw_affiliation_string":"Shandong Normal University, Jinan, China","institution_ids":["https://openalex.org/I28006308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9727,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84906472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6359","last_page":"6368"},"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":9.999999747378752e-05,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/image-text-matching","display_name":"image-text matching","score":1.0},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7390000224113464},{"id":"https://openalex.org/keywords/action-refinement","display_name":"action refinement","score":0.6800000071525574},{"id":"https://openalex.org/keywords/clip","display_name":"CLIP","score":0.6930000185966492},{"id":"https://openalex.org/keywords/blip","display_name":"BLIP","score":0.8529999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343108057975769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5916633009910583},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.5805308818817139},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5620570182800293},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5409594178199768},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5370039343833923},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5107440948486328},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44778570532798767},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4406382739543915},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4406255781650543},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3421206474304199},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1665492057800293},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11651057004928589},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612103","doi":"https://doi.org/10.1145/3581783.3612103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612103","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612103","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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":{"id":"doi:10.1145/3581783.3612103","doi":"https://doi.org/10.1145/3581783.3612103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612103","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612103","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1645261029","display_name":null,"funder_award_id":"62176144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1763743730","display_name":null,"funder_award_id":"U1836216","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3117759162","display_name":null,"funder_award_id":"ZR2019ZD03","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3786892105","display_name":null,"funder_award_id":"62202015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5215801658","display_name":null,"funder_award_id":"ts20190924","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G62463823","display_name":null,"funder_award_id":"62076153","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387967913.pdf","grobid_xml":"https://content.openalex.org/works/W4387967913.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2795832645","https://openalex.org/W2936420065","https://openalex.org/W2962964995","https://openalex.org/W2967957126","https://openalex.org/W2987671777","https://openalex.org/W2994818707","https://openalex.org/W3005971801","https://openalex.org/W3010277541","https://openalex.org/W3034305926","https://openalex.org/W3035454331","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3035747010","https://openalex.org/W3091588028","https://openalex.org/W3092760908","https://openalex.org/W3126337491","https://openalex.org/W3126792443","https://openalex.org/W3135367836","https://openalex.org/W3168433561","https://openalex.org/W3176451698","https://openalex.org/W3177343494","https://openalex.org/W3184735396","https://openalex.org/W3207942052","https://openalex.org/W3211462570","https://openalex.org/W4206908526","https://openalex.org/W4214587494","https://openalex.org/W4221143402","https://openalex.org/W4226052928","https://openalex.org/W4226182655","https://openalex.org/W4281699561","https://openalex.org/W4283812943","https://openalex.org/W4296558679","https://openalex.org/W4304080188","https://openalex.org/W4304084117","https://openalex.org/W4311967393","https://openalex.org/W4312372711","https://openalex.org/W4312394134","https://openalex.org/W4312618696","https://openalex.org/W4312761738","https://openalex.org/W4312825288","https://openalex.org/W4313178921","https://openalex.org/W4313181088","https://openalex.org/W4313429809","https://openalex.org/W4382202923"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W4381094582","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1977906818","https://openalex.org/W1522139108","https://openalex.org/W2353528968","https://openalex.org/W2032776242"],"abstract_inverted_index":{"Image-text":[0],"matching":[1,12,79],"is":[2,60,68,119,143],"a":[3,25],"hot":[4],"topic":[5],"in":[6,57,65],"multi-modal":[7],"analysis.":[8],"The":[9,124,153],"existing":[10],"image-text":[11,78,122],"algorithms":[13],"focus":[14],"on":[15,115,166,173],"bridging":[16],"the":[17,22,39,46,53,58,69,77,82,95,101,111,132,147,157,162],"heterogeneity":[18,97],"gap":[19,98],"and":[20,52,99,138,149,159,171,179],"mapping":[21],"feature":[23],"into":[24],"common":[26],"space":[27],"under":[28,38],"strong":[29],"alignment":[30,41],"assumption.":[31],"However,":[32],"these":[33],"methods":[34],"have":[35],"unsatisfactory":[36],"performance":[37],"weak":[40,88],"scenario,":[42],"which":[43,118],"assumes":[44],"that":[45],"text":[47,59,112,136],"contains":[48],"more":[49],"abstract":[50],"information,":[51],"number":[54],"of":[55,84,151,161],"entities":[56],"always":[61],"fewer":[62],"than":[63],"objects":[64],"image.":[66],"This":[67],"first":[70],"time,":[71],"from":[72,81],"our":[73],"knowledge,":[74],"to":[75,92,109,130,145],"solve":[76],"problem":[80],"perspective":[83],"information":[85,102,134],"difference":[86],"with":[87],"alignment.":[89],"In":[90],"order":[91],"both":[93],"narrow":[94],"cross-modal":[96],"balance":[100],"discrepancy,":[103],"we":[104],"proposed":[105,163],"an":[106,139],"imagination":[107,125],"network":[108,126],"enrich":[110],"modality":[113],"based":[114,165],"pre-trained":[116,168],"framework,":[117],"helpful":[120],"for":[121,135],"matching.":[123],"utilizes":[127],"reinforcement":[128],"learning":[129],"enhance":[131],"semantic":[133],"modality,":[137],"action":[140],"refinement":[141],"strategy":[142],"designed":[144],"constrain":[146],"freedom":[148],"divergence":[150],"imagination.":[152],"experiment":[154],"results":[155],"show":[156],"superiority":[158],"generality":[160],"framework":[164],"two":[167,174],"models,":[169],"CLIP":[170],"BLIP":[172],"most":[175],"frequently-used":[176],"datasets":[177],"MSCOCO":[178],"Flickr30K.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}