{"id":"https://openalex.org/W4285414077","doi":"https://doi.org/10.1109/tmm.2022.3190686","title":"Depth-Aware and Semantic Guided Relational Attention Network for Visual Question Answering","display_name":"Depth-Aware and Semantic Guided Relational Attention Network for Visual Question Answering","publication_year":2022,"publication_date":"2022-07-14","ids":{"openalex":"https://openalex.org/W4285414077","doi":"https://doi.org/10.1109/tmm.2022.3190686"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3190686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3190686","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/A5028184484","display_name":"Yuhang Liu","orcid":"https://orcid.org/0000-0002-2770-9330"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Liu","raw_affiliation_strings":["Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-2770-9330","affiliations":[{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323842","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0003-4488-0102"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-4488-0102","affiliations":[{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066682332","display_name":"Daowan Peng","orcid":"https://orcid.org/0000-0001-5208-3811"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daowan Peng","raw_affiliation_strings":["Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017626590","display_name":"Xian-Ling Mao","orcid":"https://orcid.org/0000-0001-6795-2311"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian-Ling Mao","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6795-2311","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113959977","display_name":"HE Zhi-yong","orcid":null},"institutions":[{"id":"https://openalex.org/I2800710378","display_name":"Naval University of Engineering","ror":"https://ror.org/056vyez31","country_code":"CN","type":"education","lineage":["https://openalex.org/I2800710378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong He","raw_affiliation_strings":["Naval University of Engineering, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naval University of Engineering, Wuhan, China","institution_ids":["https://openalex.org/I2800710378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693197","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0002-8629-4622"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0002-8629-4622","affiliations":[{"raw_affiliation_string":"Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3808,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.81323686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"5344","last_page":"5357"},"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":0.9958000183105469,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9940000176429749,"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/question-answering","display_name":"Question answering","score":0.8618292212486267},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7782495021820068},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6005924344062805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.583960235118866},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5668190717697144},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5073904395103455},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.4812997877597809},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.46314355731010437},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4537400007247925},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.4341363310813904},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35871344804763794},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2288932502269745},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15020403265953064}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8618292212486267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782495021820068},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6005924344062805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.583960235118866},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5668190717697144},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5073904395103455},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4812997877597809},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.46314355731010437},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4537400007247925},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4341363310813904},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35871344804763794},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2288932502269745},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15020403265953064},{"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:10.1109/tmm.2022.3190686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3190686","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/G1250004542","display_name":null,"funder_award_id":"61602197","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1915648697","display_name":null,"funder_award_id":"L1924068","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7118507406","display_name":"\u878d\u5165\u6982\u5ff5\u7684\u9ad8\u6548\u4e3b\u9898\u5206\u6790\u6846\u67b6\u4e0e\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61772076","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2277195237","https://openalex.org/W2622263826","https://openalex.org/W2745461083","https://openalex.org/W2883104598","https://openalex.org/W2896457183","https://openalex.org/W2904910963","https://openalex.org/W2916723116","https://openalex.org/W2949693283","https://openalex.org/W2962960377","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963383024","https://openalex.org/W2963518342","https://openalex.org/W2963521239","https://openalex.org/W2963717374","https://openalex.org/W2963981422","https://openalex.org/W2964072591","https://openalex.org/W2964138017","https://openalex.org/W2966683369","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2976187852","https://openalex.org/W2985775862","https://openalex.org/W2992049873","https://openalex.org/W2998631105","https://openalex.org/W3004349648","https://openalex.org/W3005881764","https://openalex.org/W3026441479","https://openalex.org/W3034472388","https://openalex.org/W3034649151","https://openalex.org/W3034787499","https://openalex.org/W3035160838","https://openalex.org/W3035497460","https://openalex.org/W3087975588","https://openalex.org/W3089709427","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3092767330","https://openalex.org/W3094800993","https://openalex.org/W3100770207","https://openalex.org/W3108319047","https://openalex.org/W3173220247","https://openalex.org/W3180638445","https://openalex.org/W3197035208","https://openalex.org/W3206617243","https://openalex.org/W4288286281","https://openalex.org/W4293205777","https://openalex.org/W4297749157","https://openalex.org/W4385245566","https://openalex.org/W6605121731","https://openalex.org/W6639102338","https://openalex.org/W6739622702","https://openalex.org/W6739901393","https://openalex.org/W6748270630","https://openalex.org/W6752083267","https://openalex.org/W6755207826","https://openalex.org/W6765591853","https://openalex.org/W6766261854","https://openalex.org/W6767211374"],"related_works":["https://openalex.org/W2964061310","https://openalex.org/W2231285690","https://openalex.org/W2963477107","https://openalex.org/W4390091918","https://openalex.org/W3093385053","https://openalex.org/W4389682534","https://openalex.org/W2553418567","https://openalex.org/W3045060014","https://openalex.org/W2138707363","https://openalex.org/W4390241396"],"abstract_inverted_index":{"Visual":[0],"relationship":[1],"understanding":[2],"plays":[3],"an":[4,157],"indispensable":[5],"role":[6],"in":[7,26,57,93,123,156],"grounded":[8],"language":[9],"tasks":[10],"like":[11,107],"visual":[12,55],"question":[13,85],"answering":[14],"(VQA),":[15],"which":[16],"often":[17],"requires":[18],"precisely":[19],"reasoning":[20],"about":[21],"relations":[22,96,153],"among":[23],"objects":[24,56,98,122,155],"depicted":[25],"the":[27,36,49,84,94,115,128,149,168,192],"given":[28],"question.":[29],"However,":[30],"prior":[31],"works":[32],"generally":[33],"suffer":[34],"from":[35],"deficiencies":[37],"as":[38,186],"follows,":[39],"(1)spatial-relation":[40],"inference":[41],"ambiguity,":[42],"it":[43,75],"is":[44,62,76,88],"challenging":[45],"to":[46,78,83,146,180],"accurately":[47],"estimate":[48],"distance":[50],"of":[51,54,91,97,118,121,154],"a":[52,63,80,89,103,119,139],"pair":[53,120],"2D":[58,67,130],"space":[59,125],"if":[60,86],"there":[61,87],"visual-overlap":[64],"between":[65],"their":[66],"bounding-boxes,":[68],"and":[69,136,172,182],"(2)":[70],"language-visual":[71,95],"relational":[72,162],"alignment":[73,92],"missing,":[74],"insufficient":[77],"generate":[79],"high-quality":[81],"answer":[82],"lack":[90],"during":[99],"fusion,":[100],"even":[101],"using":[102],"powerful":[104],"fusion":[105],"model":[106,114,141],"Transformer.":[108],"To":[109],"this":[110],"end,":[111],"we":[112],"first":[113],"spatial":[116,152],"relation":[117],"3D":[124,151],"by":[126],"augmenting":[127],"original":[129],"bounding-box":[131],"with":[132],"1D":[133],"depth":[134],"information,":[135],"then":[137],"propose":[138],"novel":[140],"namedDepth-awareSemanticGuided":[142],"RelationalAttention":[143],"Network":[144],"(DSGANet),":[145],"explicitly":[147],"exploit":[148],"formed":[150],"intra-/inter-modality":[158],"manner":[159],"for":[160],"precise":[161],"alignment.":[163],"Extensive":[164],"experiments":[165],"conducted":[166],"on":[167,191,196],"benchmarks":[169],"(VQA":[170],"v2.0":[171],"GQA)":[173],"demonstrate":[174],"DSGANet":[175],"achieves":[176],"competitive":[177],"performance":[178],"compared":[179],"pretrained":[181],"non-pretrained":[183],"models,":[184],"such":[185],"72.7%":[187],"vs.":[188],"74.6%":[189],"based":[190],"learned":[193],"grid":[194],"features":[195],"VQA":[197],"v2.0.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}