{"id":"https://openalex.org/W3207608362","doi":"https://doi.org/10.1145/3474085.3475380","title":"Conceptual and Syntactical Cross-modal Alignment with Cross-level Consistency for Image-Text Matching","display_name":"Conceptual and Syntactical Cross-modal Alignment with Cross-level Consistency for Image-Text Matching","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3207608362","doi":"https://doi.org/10.1145/3474085.3475380","mag":"3207608362"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475380","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475380","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":"conference-paper","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/A5087623065","display_name":"Pengpeng Zeng","orcid":"https://orcid.org/0000-0002-0672-3790"},"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":"Pengpeng Zeng","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"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/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"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":"Lianli Gao","raw_affiliation_strings":["University of Electronic Science and\u00a0Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and\u00a0Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090700061","display_name":"Xinyu Lyu","orcid":"https://orcid.org/0000-0003-2479-8881"},"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":"Xinyu Lyu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"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/A5014477636","display_name":"Shuaiqi Jing","orcid":"https://orcid.org/0000-0001-6797-4238"},"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":"Shuaiqi Jing","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"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":"Jingkuan Song","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2205","last_page":"2213"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9922000169754028,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.988099992275238,"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":0.7375544905662537},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6658435463905334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5861569046974182},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5767810344696045},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5434333682060242},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.5130339860916138},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.46697545051574707},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.44239065051078796},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4408714473247528},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4303678274154663},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4243798553943634},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1951979696750641}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7375544905662537},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6658435463905334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5861569046974182},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5767810344696045},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5434333682060242},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.5130339860916138},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.46697545051574707},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.44239065051078796},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4408714473247528},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4303678274154663},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4243798553943634},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1951979696750641},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475380","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475380","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W1905882502","https://openalex.org/W2123442489","https://openalex.org/W2185175083","https://openalex.org/W2250539671","https://openalex.org/W2506483933","https://openalex.org/W2522148122","https://openalex.org/W2546696630","https://openalex.org/W2552579943","https://openalex.org/W2606473278","https://openalex.org/W2626778328","https://openalex.org/W2743355020","https://openalex.org/W2778100917","https://openalex.org/W2778940641","https://openalex.org/W2786585376","https://openalex.org/W2799263800","https://openalex.org/W2807941860","https://openalex.org/W2892880750","https://openalex.org/W2895902247","https://openalex.org/W2904291752","https://openalex.org/W2904910963","https://openalex.org/W2952688802","https://openalex.org/W2962856082","https://openalex.org/W2962964995","https://openalex.org/W2963101956","https://openalex.org/W2963499204","https://openalex.org/W2963536419","https://openalex.org/W2964121744","https://openalex.org/W2965848243","https://openalex.org/W2981582341","https://openalex.org/W2982078236","https://openalex.org/W2988823324","https://openalex.org/W2994818707","https://openalex.org/W3004349648","https://openalex.org/W3011702232","https://openalex.org/W3014442964","https://openalex.org/W3034984754","https://openalex.org/W3035454331","https://openalex.org/W3035497460","https://openalex.org/W3035520037","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3092779813","https://openalex.org/W3092820619","https://openalex.org/W3093044239","https://openalex.org/W3093272873","https://openalex.org/W3099677434","https://openalex.org/W3103953945","https://openalex.org/W3134735773","https://openalex.org/W4285620459","https://openalex.org/W4301156730","https://openalex.org/W6749537441","https://openalex.org/W6754778999"],"related_works":["https://openalex.org/W2377185541","https://openalex.org/W2378553216","https://openalex.org/W2462900308","https://openalex.org/W2169684272","https://openalex.org/W2171044983","https://openalex.org/W2096992842","https://openalex.org/W2362026785","https://openalex.org/W2914151043","https://openalex.org/W2619749483","https://openalex.org/W2358573072"],"abstract_inverted_index":{"Image-Text":[0],"Matching":[1,89],"(ITM)":[2],"is":[3,43,111,123,140],"a":[4,11,19,41,46,54,59,77,103,107,119,128],"fundamental":[5],"and":[6,79,100,172,174],"emerging":[7],"task,":[8],"which":[9,176],"plays":[10],"key":[12],"role":[13],"in":[14],"cross-modal":[15,95,109,121,147,154],"understanding.":[16],"It":[17],"remains":[18],"challenge":[20],"because":[21],"prior":[22],"works":[23],"mainly":[24],"focus":[25],"on":[26,164],"learning":[27],"fine-grained":[28,116],"(i.e.":[29],"coarse":[30],"and/or":[31],"phrase)":[32],"correspondence,":[33,117],"without":[34],"considering":[35],"the":[36,93,98,115,144,151],"syntactical":[37],"correspondence.":[38],"In":[39],"theory,":[40],"sentence":[42],"not":[44],"only":[45],"set":[47,60],"of":[48,58,61],"words":[49],"or":[50],"phrases":[51],"but":[52],"also":[53],"syntactic":[55,63,101,130],"structure,":[56],"consisting":[57],"basic":[62],"tuples":[64],"(i.e.(attribute)":[65],"object":[66],"-":[67,69],"predicate":[68],"(attribute)":[70],"subject).":[71],"Inspired":[72],"by":[73,90],"this,":[74],"we":[75],"propose":[76],"Conceptual":[78],"Syntactical":[80],"Cross-modal":[81],"Alignment":[82],"with":[83,102,184],"Cross-level":[84],"Consistency":[85],"(CSCC)":[86],"for":[87,113],"Image-text":[88],"simultaneously":[91],"exploring":[92,114],"multiple-level":[94],"alignments":[96],"across":[97],"concept":[99],"consistency":[104,145],"constraint.":[105],"Specifically,":[106],"conceptual-level":[108],"alignment":[110,122],"introduced":[112,141],"while":[118],"syntactical-level":[120],"proposed":[124],"to":[125,142],"explicitly":[126],"learn":[127],"high-level":[129],"similarity":[131],"function.":[132],"Moreover,":[133],"an":[134],"empirical":[135],"cross-level":[136],"consistent":[137],"attention":[138],"loss":[139],"maintain":[143],"between":[146],"attentions":[148],"obtained":[149],"from":[150],"above":[152],"two":[153,165],"alignments.":[155],"To":[156],"justify":[157],"our":[158,179],"method,":[159],"comprehensive":[160],"experiments":[161],"are":[162],"conducted":[163],"public":[166],"benchmark":[167],"datasets,":[168],"i.e.":[169],"MS-COCO":[170],"(1K":[171],"5K)":[173],"Flickr30K,":[175],"show":[177],"that":[178],"CSCC":[180],"outperforms":[181],"state-of-the-art":[182],"methods":[183],"fairly":[185],"competitive":[186],"improvements.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}