{"id":"https://openalex.org/W4226200183","doi":"https://doi.org/10.1109/tmm.2022.3164787","title":"Knowing What it is: Semantic-Enhanced Dual Attention Transformer","display_name":"Knowing What it is: Semantic-Enhanced Dual Attention Transformer","publication_year":2022,"publication_date":"2022-04-05","ids":{"openalex":"https://openalex.org/W4226200183","doi":"https://doi.org/10.1109/tmm.2022.3164787"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3164787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3164787","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/A5073144816","display_name":"Yiwei Ma","orcid":"https://orcid.org/0000-0002-8744-3423"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Ma","raw_affiliation_strings":["Media Analytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-8744-3423","affiliations":[{"raw_affiliation_string":"Media Analytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084510895","display_name":"Jiayi Ji","orcid":"https://orcid.org/0000-0002-9956-6308"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Ji","raw_affiliation_strings":["Media Analytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-9956-6308","affiliations":[{"raw_affiliation_string":"Media Analytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059926864","display_name":"Xiaoshuai Sun","orcid":"https://orcid.org/0000-0003-3912-9306"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Sun","raw_affiliation_strings":["MediaAnalytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China","Institute of Artificial Intelligence, Xiamen University and Fujian Engineering Research Center of Trusted Artificial Intelligence Analysis and Application, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0003-3912-9306","affiliations":[{"raw_affiliation_string":"MediaAnalytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Xiamen University and Fujian Engineering Research Center of Trusted Artificial Intelligence Analysis and Application, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091531008","display_name":"Yiyi Zhou","orcid":"https://orcid.org/0000-0002-5110-4526"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyi Zhou","raw_affiliation_strings":["Media Analytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-5110-4526","affiliations":[{"raw_affiliation_string":"Media Analytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716576","display_name":"Yongjian Wu","orcid":"https://orcid.org/0000-0003-2007-6929"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjian Wu","raw_affiliation_strings":["Youtu Laboratory, Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu Laboratory, Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112601777","display_name":"Feiyue Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyue Huang","raw_affiliation_strings":["Youtu Laboratory, Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu Laboratory, Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["MediaAnalytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China","Institute of Artificial Intelligence, Xiamen University and Fujian Engineering Research Center of Trusted Artificial Intelligence Analysis and Application, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0001-9163-2932","affiliations":[{"raw_affiliation_string":"MediaAnalytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Xiamen University and Fujian Engineering Research Center of Trusted Artificial Intelligence Analysis and Application, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8427,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.9229874,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"3723","last_page":"3736"},"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":0.9962999820709229,"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":0.9952999949455261,"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":0.6871703267097473},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6353119611740112},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5167900323867798},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4666580855846405},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42510220408439636},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41278278827667236},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3628003001213074},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2057228684425354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6871703267097473},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6353119611740112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5167900323867798},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4666580855846405},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42510220408439636},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41278278827667236},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3628003001213074},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2057228684425354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3164787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3164787","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":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1271955826","display_name":"\u57fa\u4e8e\u5f31\u76d1\u7763\u5b66\u4e60\u7684\u673a\u8f7d\u5730/\u6d77\u5c0f\u76ee\u6807\u68c0\u6d4b\u7814\u7a76","funder_award_id":"62072387","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1787173488","display_name":"\u9762\u5411\u6df1\u5ea6\u5b66\u4e60\u7684\u5bf9\u6297\u653b\u9632\u6280\u672f\u7814\u7a76","funder_award_id":"62072389","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2785666877","display_name":null,"funder_award_id":"62002305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5284885812","display_name":null,"funder_award_id":"62176222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5670123517","display_name":null,"funder_award_id":"2019B1515120049","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G6075090814","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G6727647225","display_name":null,"funder_award_id":"62176226","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7272499820","display_name":null,"funder_award_id":"U21B2037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7779606772","display_name":null,"funder_award_id":"62176223","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8406165135","display_name":"\u9762\u5411\u56fe\u654f\u611f\u6df1\u5ea6\u5b66\u4e60\u7684\u7ed3\u6784\u5316\u8d85\u56fe\u7814\u7a76","funder_award_id":"62072386","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"},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":116,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W639708223","https://openalex.org/W1773149199","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2019370496","https://openalex.org/W2101105183","https://openalex.org/W2109255472","https://openalex.org/W2122710056","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2549139847","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2558834163","https://openalex.org/W2575842049","https://openalex.org/W2625940279","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2752782242","https://openalex.org/W2801271919","https://openalex.org/W2884585870","https://openalex.org/W2885013662","https://openalex.org/W2890531016","https://openalex.org/W2890718122","https://openalex.org/W2901988662","https://openalex.org/W2904452845","https://openalex.org/W2913618459","https://openalex.org/W2943885184","https://openalex.org/W2950212751","https://openalex.org/W2953388933","https://openalex.org/W2955058313","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963150162","https://openalex.org/W2963743213","https://openalex.org/W2963925437","https://openalex.org/W2964345214","https://openalex.org/W2965597639","https://openalex.org/W2966683369","https://openalex.org/W2966715458","https://openalex.org/W2981578638","https://openalex.org/W2981963155","https://openalex.org/W2981994675","https://openalex.org/W2982260276","https://openalex.org/W2982573303","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W3034552520","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3035497460","https://openalex.org/W3045147787","https://openalex.org/W3081217025","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3092738440","https://openalex.org/W3092767330","https://openalex.org/W3092867601","https://openalex.org/W3092878394","https://openalex.org/W3092879151","https://openalex.org/W3092903587","https://openalex.org/W3092992946","https://openalex.org/W3093200502","https://openalex.org/W3093340907","https://openalex.org/W3093344337","https://openalex.org/W3093374703","https://openalex.org/W3093385053","https://openalex.org/W3093394956","https://openalex.org/W3094950914","https://openalex.org/W3096609285","https://openalex.org/W3098391431","https://openalex.org/W3100183449","https://openalex.org/W3103651098","https://openalex.org/W3124149278","https://openalex.org/W3138516171","https://openalex.org/W3167939936","https://openalex.org/W3170494780","https://openalex.org/W3171087525","https://openalex.org/W3174377922","https://openalex.org/W3175824375","https://openalex.org/W3177318507","https://openalex.org/W3211490618","https://openalex.org/W3213165621","https://openalex.org/W3214326397","https://openalex.org/W4214604401","https://openalex.org/W4288329833","https://openalex.org/W6630875275","https://openalex.org/W6637242042","https://openalex.org/W6638742206","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6752083267","https://openalex.org/W6754944153","https://openalex.org/W6757902542","https://openalex.org/W6763643401","https://openalex.org/W6766904570","https://openalex.org/W6768853884","https://openalex.org/W6780226713","https://openalex.org/W6784094891","https://openalex.org/W6788135285","https://openalex.org/W6789705400","https://openalex.org/W6791353385","https://openalex.org/W6796931752","https://openalex.org/W6797399245","https://openalex.org/W6798837711","https://openalex.org/W6804142907"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W297543570"],"abstract_inverted_index":{"Attention":[0,63,116],"has":[1,86],"become":[2],"an":[3],"indispensable":[4],"component":[5],"of":[6,9,39,96,123,145,168,177],"the":[7,27,37,93,121,136,159,166,175],"models":[8,191],"various":[10],"multimedia":[11],"tasks":[12],"likeImage":[13],"Captioning(IC)":[14],"andVisual":[15],"Question":[16],"Answering(VQA).":[17],"However,":[18],"most":[19],"existing":[20],"attention":[21,60,105],"modules":[22],"are":[23,31,100,185,192],"designed":[24],"for":[25,48,53,69],"capturing":[26],"spatial":[28,124],"dependency,":[29],"and":[30,41,73,80,125,140,154,190],"still":[32],"insufficient":[33],"in":[34],"semantic":[35,78],"understanding,e.g.,":[36],"categories":[38],"objects":[40],"their":[42],"attributes,":[43],"which":[44,99,119],"is":[45],"also":[46,171,186],"critical":[47],"image":[49],"captioning.":[50],"To":[51,128,164],"compensate":[52],"this":[54],"defect,":[55],"we":[56,110,131,170],"propose":[57,112],"a":[58,113],"novel":[59,88],"module":[61],"termedChannel-wise":[62],"Block(CAB)":[64],"to":[65,90,174],"model":[66],"channel-wise":[67,97,126],"dependency":[68],"both":[70],"visual":[71,178],"modality":[72],"linguistic":[74],"modality,":[75],"thereby":[76],"improving":[77],"learning":[79],"multi-modal":[81],"reasoning":[82],"simultaneously.":[83],"Specifically,":[84],"CAB":[85],"two":[87],"designs":[89],"tackle":[91],"with":[92],"high":[94],"overhead":[95],"attention,":[98],"thereduction-reconstruction":[101],"block":[102],"structureand":[103],"thegating-based":[104],"prediction.":[106],"Based":[107],"on":[108,135,149,158],"CAB,":[109],"further":[111],"novelSemantic-enhanced":[114],"Dual":[115],"Transformer(termed":[117],"SDATR),":[118],"combines":[120],"merits":[122],"attentions.":[127],"validate":[129],"SDATR,":[130,169],"conduct":[132],"extensive":[133],"experiments":[134],"MS":[137],"COCO":[138,150],"dataset":[139],"yield":[141],"new":[142],"state-of-the-art":[143],"performance":[144,183],"134.5":[146],"CIDEr":[147,156],"score":[148,157],"Karpathy":[151],"test":[152],"split":[153],"136.0":[155],"official":[160],"online":[161],"testing":[162],"server.":[163],"examine":[165],"generalization":[167],"apply":[172],"it":[173],"task":[176],"question":[179],"answering,":[180],"where":[181],"superior":[182],"gains":[184],"witnessed.":[187],"The":[188],"code":[189],"publicly":[193],"available":[194],"athttps://github.com/xmu-xiaoma666/SDATR.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}