{"id":"https://openalex.org/W4415707693","doi":"https://doi.org/10.1109/icme59968.2025.11209993","title":"Enhancing Cross-modal Semantic Consistency via Key Token Alignment for Image-text Retrieval","display_name":"Enhancing Cross-modal Semantic Consistency via Key Token Alignment for Image-text Retrieval","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707693","doi":"https://doi.org/10.1109/icme59968.2025.11209993"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5109075449","display_name":"Huilong Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huilong Lin","raw_affiliation_strings":["Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102786488","display_name":"Yangtao Wang","orcid":"https://orcid.org/0000-0003-0927-4705"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangtao Wang","raw_affiliation_strings":["Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073389511","display_name":"Meie Fang","orcid":"https://orcid.org/0000-0003-4292-8889"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meie Fang","raw_affiliation_strings":["Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050542870","display_name":"Yanzhao Xie","orcid":"https://orcid.org/0000-0002-9274-2807"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanzhao Xie","raw_affiliation_strings":["Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392725","display_name":"Da Chen","orcid":"https://orcid.org/0000-0002-5062-0270"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da Chen","raw_affiliation_strings":["Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100723331","display_name":"Xiaocui Li","orcid":"https://orcid.org/0000-0002-5971-2331"},"institutions":[{"id":"https://openalex.org/I49934816","display_name":"Hunan University of Technology","ror":"https://ror.org/04j3vr751","country_code":"CN","type":"education","lineage":["https://openalex.org/I49934816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaocui Li","raw_affiliation_strings":["Hunan University of Technology and Business,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Hunan University of Technology and Business,Changsha,China","institution_ids":["https://openalex.org/I49934816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052138365","display_name":"Weilong Peng","orcid":"https://orcid.org/0000-0001-5820-889X"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weilong Peng","raw_affiliation_strings":["Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031450947","display_name":"Siyuan Chen","orcid":"https://orcid.org/0000-0003-0272-5841"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Chen","raw_affiliation_strings":["Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067384850","display_name":"Maobin Tang","orcid":"https://orcid.org/0009-0005-5448-4172"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maobin Tang","raw_affiliation_strings":["Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741315","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-8515-7773"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ping Li","raw_affiliation_strings":["The Hong Kong Polytechnic University,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Hong Kong,China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5109075449"],"corresponding_institution_ids":["https://openalex.org/I37987034"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33603478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8306000232696533,"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":0.8306000232696533,"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":0.06710000336170197,"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":0.04450000077486038,"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/redundancy","display_name":"Redundancy (engineering)","score":0.7664999961853027},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6455000042915344},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5914999842643738},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.569100022315979},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4560000002384186},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4099000096321106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8565000295639038},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7664999961853027},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6455000042915344},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5914999842643738},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5163000226020813},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4032999873161316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3984000086784363},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28279998898506165},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27790001034736633}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2185175083","https://openalex.org/W2962964995","https://openalex.org/W2988823324","https://openalex.org/W3118694826","https://openalex.org/W3175888430","https://openalex.org/W3188427387","https://openalex.org/W3203020760","https://openalex.org/W4312761738","https://openalex.org/W4362563560","https://openalex.org/W4386071498","https://openalex.org/W4386160421","https://openalex.org/W4393149647","https://openalex.org/W4402715976","https://openalex.org/W4402754254","https://openalex.org/W4403577365"],"related_works":[],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1,14],"(ITR)":[2],"plays":[3],"a":[4],"pivotal":[5],"role":[6],"in":[7],"advancing":[8],"intelligent":[9],"transportation":[10],"systems,":[11],"facilitating":[12],"efficient":[13],"and":[15,24,41,83,88,97,108,124,133,157],"utilization":[16],"of":[17,37,72,163,174],"multimedia":[18],"data":[19],"to":[20,46,101],"enhance":[21],"traffic":[22],"management":[23],"safety":[25],"significantly.":[26],"However,":[27],"existing":[28],"ITR":[29,170],"solutions":[30],"have":[31],"not":[32],"effectively":[33],"addressed":[34],"the":[35,70,78,120,143,160,167],"issues":[36],"image":[38,74,96,105,130],"patch":[39,75,106,131],"redundancy":[40,132,136],"text":[42,98,109,134],"word":[43,110,135],"redundancy,":[44],"leading":[45],"erroneous":[47],"image-text":[48,148],"matching.":[49],"In":[50],"this":[51,175],"paper,":[52],"we":[53],"propose":[54],"SCTA":[55,68,91,114,127,164],"that":[56],"enhances":[57],"cross-modal":[58],"semantic":[59,139,145],"consistency":[60,140],"via":[61],"key":[62,104],"token":[63,111],"alignment":[64,117],"for":[65],"ITR.":[66],"Firstly,":[67],"evaluates":[69],"importance":[71],"each":[73],"by":[76,118,141],"calculating":[77],"self-attention":[79],"scores":[80,85],"within":[81],"patches":[82,87],"cross-attention":[84],"between":[86,122,147],"words.":[89],"Secondly,":[90],"implements":[92],"aggregation":[93],"operations":[94],"on":[95,152],"separately,":[99],"aiming":[100],"generate":[102],"information-rich":[103],"embeddings":[107],"embeddings.":[112],"Finally,":[113],"completes":[115],"fine-grained":[116,169],"maximizing":[119],"similarity":[121],"patch-to-word":[123],"word-to-patch.":[125],"Therefore,":[126],"simultaneously":[128],"addresses":[129],"issues,":[137],"enhancing":[138],"aligning":[142],"core":[144],"information":[146],"pairs.":[149],"Extensive":[150],"experiments":[151],"multiple":[153],"datasets":[154],"including":[155],"Flickr30K":[156],"MS-COCO":[158],"verify":[159],"superior":[161],"performance":[162],"compared":[165],"with":[166],"SOTA":[168],"methods.":[171],"The":[172],"code":[173],"paper":[176],"is":[177],"released":[178],"at":[179],"GitHub:":[180],"https://github.com/ICME2025ITR/SCTA.":[181]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}