{"id":"https://openalex.org/W4405599224","doi":"https://doi.org/10.1109/tcsvt.2024.3520318","title":"SeaDATE: Remedy Dual-Attention Transformer With Semantic Alignment via Contrast Learning for Multimodal Object Detection","display_name":"SeaDATE: Remedy Dual-Attention Transformer With Semantic Alignment via Contrast Learning for Multimodal Object Detection","publication_year":2024,"publication_date":"2024-12-19","ids":{"openalex":"https://openalex.org/W4405599224","doi":"https://doi.org/10.1109/tcsvt.2024.3520318"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3520318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3520318","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5011601403","display_name":"Shuhan Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhan Dong","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052163069","display_name":"Weiying Xie","orcid":"https://orcid.org/0000-0001-8310-024X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiying Xie","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0001-8310-024X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Danian Yang","orcid":"https://orcid.org/0009-0004-8906-7830"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danian Yang","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0004-8906-7830","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067798266","display_name":"Yunsong Li","orcid":"https://orcid.org/0000-0002-0234-6270"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunsong Li","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-0234-6270","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090736129","display_name":"Jiaqing Zhang","orcid":"https://orcid.org/0009-0007-3111-1116"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqing Zhang","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0007-3111-1116","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100311535","display_name":"Jiayuan Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayuan Tian","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007285444","display_name":"Jie Lei","orcid":"https://orcid.org/0000-0003-0851-6565"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jie Lei","raw_affiliation_strings":["School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, Australia","School of Electrical and Data Engineering, University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0851-6565","affiliations":[{"raw_affiliation_string":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1873,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.89354964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"35","issue":"5","first_page":"4713","last_page":"4726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8507999777793884,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.8507999777793884,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8489000201225281,"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/T10028","display_name":"Topic Modeling","score":0.8011000156402588,"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":0.7071821689605713},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5484996438026428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.523191511631012},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.5070343017578125},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.43598923087120056},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4278997480869293},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.41007184982299805},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34206247329711914},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0878283679485321}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7071821689605713},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5484996438026428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.523191511631012},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5070343017578125},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.43598923087120056},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4278997480869293},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.41007184982299805},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34206247329711914},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0878283679485321},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3520318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3520318","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G5402131352","display_name":null,"funder_award_id":"62371365","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5457114622","display_name":null,"funder_award_id":"U24B20136","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5721138531","display_name":null,"funder_award_id":"62322117","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8508741111","display_name":"\u9762\u5411\u661f\u4e0a\u5b9e\u65f6\u5904\u7406\u7684\u9ad8\u5149\u8c31\u56fe\u50cf\u76ee\u6807\u68c0\u6d4b\u7b97\u6cd5\u7814\u7a76","funder_award_id":"62071360","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":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W2000284802","https://openalex.org/W2102605133","https://openalex.org/W2570343428","https://openalex.org/W2741620214","https://openalex.org/W2767290858","https://openalex.org/W2798991696","https://openalex.org/W2809795042","https://openalex.org/W2842511635","https://openalex.org/W2884367402","https://openalex.org/W2929607865","https://openalex.org/W2953471980","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963188557","https://openalex.org/W2963579094","https://openalex.org/W2963706010","https://openalex.org/W2981165461","https://openalex.org/W2987131085","https://openalex.org/W3008115128","https://openalex.org/W3018757597","https://openalex.org/W3035524453","https://openalex.org/W3036931590","https://openalex.org/W3043840704","https://openalex.org/W3100017393","https://openalex.org/W3101990647","https://openalex.org/W3116967329","https://openalex.org/W3122412340","https://openalex.org/W3152390103","https://openalex.org/W3155938136","https://openalex.org/W3159815144","https://openalex.org/W3169708801","https://openalex.org/W3180463990","https://openalex.org/W3197486099","https://openalex.org/W3198582484","https://openalex.org/W3212645988","https://openalex.org/W4213019189","https://openalex.org/W4220724622","https://openalex.org/W4224315825","https://openalex.org/W4308148751","https://openalex.org/W4317496152","https://openalex.org/W4319866558","https://openalex.org/W4321021766","https://openalex.org/W4321482183","https://openalex.org/W4362654659","https://openalex.org/W4364302321","https://openalex.org/W4366378409","https://openalex.org/W4382119107","https://openalex.org/W4383220251","https://openalex.org/W4384916907","https://openalex.org/W4385801610","https://openalex.org/W4385975752","https://openalex.org/W4390143978","https://openalex.org/W4390872346","https://openalex.org/W4391128309","https://openalex.org/W4394711494","https://openalex.org/W4401023960","https://openalex.org/W4401634204","https://openalex.org/W4401808679","https://openalex.org/W6714138976","https://openalex.org/W6750227808","https://openalex.org/W6753836424","https://openalex.org/W6754632766","https://openalex.org/W6756834165","https://openalex.org/W6781874425","https://openalex.org/W6841129745","https://openalex.org/W6845935626","https://openalex.org/W6858516133","https://openalex.org/W6869607566"],"related_works":["https://openalex.org/W2069592018","https://openalex.org/W2075740387","https://openalex.org/W2358990940","https://openalex.org/W2093931120","https://openalex.org/W2329812990","https://openalex.org/W2349116365","https://openalex.org/W3021708704","https://openalex.org/W2004231473","https://openalex.org/W2060895226","https://openalex.org/W2998542275"],"abstract_inverted_index":{"Multimodal":[0],"object":[1,45,97],"detection":[2,46,85,98,228],"leverages":[3],"diverse":[4],"modal":[5,131],"information":[6,121,168],"to":[7,16,19,71,170,223],"enhance":[8],"the":[9,23,41,49,82,128,150,192,213],"accuracy":[10,42],"and":[11,94,119,138,145,202,209,216],"robustness":[12],"of":[13,43,51,78,130,158,188,194],"detectors.":[14],"Due":[15],"its":[17],"ability":[18],"capture":[20],"long-range":[21],"dependencies,":[22],"Transformer":[24],"model":[25],"provides":[26],"a":[27,105,123,179],"powerful":[28],"mechanism":[29],"for":[30,160],"integrating":[31],"multimodal":[32,44,96,189],"features":[33,73,132,187],"during":[34],"feature":[35,53],"extraction.":[36],"This":[37],"capability":[38,70],"significantly":[39],"enhances":[40],"by":[47],"addressing":[48],"limitations":[50],"local":[52,118],"extraction":[54],"inherent":[55],"in":[56,84,197],"traditional":[57],"methods.":[58],"However,":[59],"current":[60],"methods":[61],"merely":[62],"stack":[63],"Transformer-guided":[64,151,195],"fusion":[65,129,152,196],"techniques":[66],"without":[67],"exploring":[68],"their":[69],"extract":[72],"at":[74,185],"various":[75],"depth":[76],"layers":[77],"network,":[79],"thus":[80],"limiting":[81],"improvements":[83],"performance.":[86,229],"In":[87],"this":[88],"paper,":[89],"we":[90,103,177],"introduce":[91],"an":[92],"accurate":[93],"efficient":[95],"method":[99,222],"named":[100],"SeaDATE.":[101],"Initially,":[102],"propose":[104],"novel":[106],"dual":[107,124],"attention":[108,125],"Feature":[109],"Fusion":[110],"(DTF)":[111],"module":[112,183],"that,":[113],"under":[114],"Transformer\u2019s":[115],"guidance,":[116],"integrates":[117],"global":[120],"through":[122],"mechanism,":[126],"strengthening":[127],"from":[133],"orthogonal":[134],"perspectives":[135],"using":[136],"spatial":[137],"channel":[139],"tokens.":[140],"Meanwhile,":[141],"our":[142,221],"theoretical":[143],"analysis":[144],"empirical":[146],"validation":[147],"demonstrate":[148],"that":[149],"method,":[153],"treating":[154],"images":[155],"as":[156],"sequences":[157],"pixels":[159],"fusion,":[161],"performs":[162],"better":[163],"on":[164,212],"shallow":[165],"features\u2019":[166],"detail":[167],"compared":[169],"deep":[171,199],"semantic":[172,200],"information.":[173,206],"To":[174],"address":[175],"this,":[176],"designed":[178],"contrastive":[180],"learning":[181,186],"(CL)":[182],"aimed":[184],"samples,":[190],"remedying":[191],"shortcomings":[193],"extracting":[198],"features,":[201],"effectively":[203],"utilizing":[204],"cross-modal":[205],"Extensive":[207],"experiments":[208],"ablation":[210],"studies":[211],"FLIR,":[214],"LLVIP,":[215],"M3FD":[217],"datasets":[218],"have":[219],"proven":[220],"be":[224],"effective,":[225],"achieving":[226],"state-of-the-art":[227]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}