{"id":"https://openalex.org/W4414856480","doi":"https://doi.org/10.1109/tmm.2025.3618550","title":"Similarity Shuffled Criss-Cross Transformer With Angle Loss for Image-Text Matching","display_name":"Similarity Shuffled Criss-Cross Transformer With Angle Loss for Image-Text Matching","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414856480","doi":"https://doi.org/10.1109/tmm.2025.3618550"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3618550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3618550","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5078111299","display_name":"Jiali Chen","orcid":"https://orcid.org/0009-0003-8979-9153"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Chen","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China","College of Electronic and Information Engineering, Tongji University, Shanghai, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061219010","display_name":"Taiyi Su","orcid":"https://orcid.org/0000-0002-4357-1095"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taiyi Su","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China","College of Electronic and Information Engineering, Tongji University, Shanghai, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-4357-1095","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058982350","display_name":"Hanli Wang","orcid":"https://orcid.org/0000-0002-9999-4871"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanli Wang","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China","College of Electronic and Information Engineering, Tongji University, Shanghai, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-9999-4871","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032273272","display_name":"Zhangkai Ni","orcid":"https://orcid.org/0000-0003-3682-6288"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangkai Ni","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China","College of Electronic and Information Engineering, Tongji University, Shanghai, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-3682-6288","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":1.1177,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79640698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"9723","last_page":"9734"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9710000157356262,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9710000157356262,"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":0.9650999903678894,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9282000064849854,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.8296999931335449},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7149999737739563},{"id":"https://openalex.org/keywords/feature-matching","display_name":"Feature matching","score":0.5644999742507935},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5117999911308289},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4885999858379364},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4814000129699707},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.44020000100135803}],"concepts":[{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.8296999931335449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101000189781189},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7149999737739563},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.5644999742507935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5199000239372253},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5117999911308289},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4814000129699707},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3824000060558319},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30390000343322754},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.27230000495910645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3618550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3618550","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2125127483","display_name":null,"funder_award_id":"62371343","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3038806383","display_name":null,"funder_award_id":"2024-1-ZD-02","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1957706851","https://openalex.org/W2131774270","https://openalex.org/W2147238549","https://openalex.org/W2185175083","https://openalex.org/W2250539671","https://openalex.org/W2546696630","https://openalex.org/W2778100917","https://openalex.org/W2896457183","https://openalex.org/W2956018683","https://openalex.org/W2962964995","https://openalex.org/W2963125010","https://openalex.org/W2963467339","https://openalex.org/W2965809241","https://openalex.org/W2965848243","https://openalex.org/W2981586349","https://openalex.org/W2988823324","https://openalex.org/W2990571534","https://openalex.org/W2994818707","https://openalex.org/W2997003477","https://openalex.org/W2998215884","https://openalex.org/W2998356391","https://openalex.org/W3005971801","https://openalex.org/W3018388102","https://openalex.org/W3033740891","https://openalex.org/W3035454331","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3090449556","https://openalex.org/W3094172275","https://openalex.org/W3118694826","https://openalex.org/W3138516171","https://openalex.org/W3166898278","https://openalex.org/W3167480762","https://openalex.org/W3202436960","https://openalex.org/W4206314411","https://openalex.org/W4214493665","https://openalex.org/W4220899212","https://openalex.org/W4224281861","https://openalex.org/W4312761738","https://openalex.org/W4319663732","https://openalex.org/W4385245566","https://openalex.org/W4386071498","https://openalex.org/W4392152051","https://openalex.org/W4392678259","https://openalex.org/W4393170802","https://openalex.org/W4402753983"],"related_works":[],"abstract_inverted_index":{"Image-text":[0],"matching":[1],"aims":[2],"to":[3,65,96,145,160,188],"retrieve":[4,13],"images":[5],"from":[6,32,101],"the":[7,17,43,46,53,57,66,105,162,172,181],"guidance":[8],"of":[9,19,55,68,120,175],"textual":[10],"queries":[11],"or":[12],"text":[14],"expressions":[15],"with":[16,84,138],"help":[18],"images.":[20],"Existing":[21],"Transformer-based":[22],"methods":[23,183],"compute":[24],"attention":[25,133],"for":[26,87,107],"all":[27],"tokens":[28],"and":[29,61,166,177],"thus":[30],"suffer":[31],"redundant":[33,102],"information,":[34,103],"resulting":[35],"in":[36],"inadequate":[37],"focus":[38],"on":[39,171],"salient":[40,99,124],"features.":[41],"On":[42],"other":[44],"hand,":[45],"widely":[47],"adopted":[48],"bidirectional":[49],"ranking":[50],"loss":[51,86,157],"overlooks":[52],"importance":[54],"expanding":[56],"distance":[58],"between":[59,164],"positive":[60,72,165],"negative":[62,69,167],"samples,":[63],"leading":[64],"misclassification":[67],"samples":[70],"as":[71],"ones.":[73,129],"In":[74],"this":[75],"work,":[76],"we":[77],"propose":[78],"similarity":[79],"shuffled":[80],"criss-cross":[81,132,141],"Transformer":[82],"(SSCT)":[83],"angle":[85,156],"image-text":[88],"matching.":[89],"Specifically,":[90],"a":[91,131,139,154],"grouping-shuffling":[92,112],"operation":[93,113],"is":[94,143,158],"introduced":[95,159],"better":[97],"distinguish":[98],"features":[100,125],"bypassing":[104],"need":[106],"fully":[108],"connected":[109],"mapping.":[110],"The":[111],"establishes":[114],"channel":[115],"dependencies":[116],"across":[117],"different":[118],"groups":[119],"feature":[121],"representations,":[122],"enhancing":[123],"while":[126],"suppressing":[127],"unimportant":[128],"Then,":[130],"mechanism":[134],"that":[135,180],"equips":[136],"self-attention":[137],"novel":[140,155],"convolution":[142],"designed":[144],"make":[146],"isolated":[147],"information":[148],"cooperatively":[149],"express":[150],"integral":[151],"semantics.":[152],"Moreover,":[153],"expand":[161],"distances":[163],"samples.":[168],"Extensive":[169],"experiments":[170],"benchmark":[173],"datasets":[174],"MSCOCO":[176],"Flickr30K":[178],"demonstrate":[179],"proposed":[182],"achieve":[184],"superior":[185],"performances":[186],"compared":[187],"state-of-the-art":[189],"methods.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}