{"id":"https://openalex.org/W4312377093","doi":"https://doi.org/10.1109/tcsvt.2022.3229081","title":"Toward Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline","display_name":"Toward Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline","publication_year":2022,"publication_date":"2022-12-14","ids":{"openalex":"https://openalex.org/W4312377093","doi":"https://doi.org/10.1109/tcsvt.2022.3229081"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3229081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3229081","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/A5016042658","display_name":"Lichen Zhao","orcid":"https://orcid.org/0000-0002-5805-3194"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lichen Zhao","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072798214","display_name":"Daigang Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daigang Cai","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052709846","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0003-3516-0111"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035443556","display_name":"Lu Sheng","orcid":"https://orcid.org/0000-0002-8525-9163"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Sheng","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057619360","display_name":"Dong Xu","orcid":"https://orcid.org/0000-0002-4279-3542"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dong Xu","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Pok Fu Lam, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Pok Fu Lam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101702297","display_name":"Rui Zheng","orcid":"https://orcid.org/0009-0009-0831-880X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zheng","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114043002","display_name":"Yinjie Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinjie Zhao","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378187","display_name":"Lipeng Wang","orcid":"https://orcid.org/0000-0001-7129-434X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lipeng Wang","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076190354","display_name":"Xibo Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xibo Fan","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5016042658"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":2.4158,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.90521627,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"33","issue":"6","first_page":"2935","last_page":"2949"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9962999820709229,"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":0.9957000017166138,"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":0.7846556901931763},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7243834733963013},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6649946570396423},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5796562433242798},{"id":"https://openalex.org/keywords/grounded-theory","display_name":"Grounded theory","score":0.5374366044998169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5364696383476257},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5325334072113037},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5183073878288269},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5085097551345825},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4548128843307495},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4389188289642334},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.43863701820373535},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.4378577768802643},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38479724526405334},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3771861791610718},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14811527729034424},{"id":"https://openalex.org/keywords/qualitative-research","display_name":"Qualitative research","score":0.10611459612846375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7846556901931763},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7243834733963013},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6649946570396423},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5796562433242798},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.5374366044998169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5364696383476257},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5325334072113037},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5183073878288269},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5085097551345825},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4548128843307495},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4389188289642334},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.43863701820373535},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.4378577768802643},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38479724526405334},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3771861791610718},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14811527729034424},{"id":"https://openalex.org/C190248442","wikidata":"https://www.wikidata.org/wiki/Q839486","display_name":"Qualitative research","level":2,"score":0.10611459612846375},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2022.3229081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3229081","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":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3551653136","display_name":null,"funder_award_id":"2018AAA0101900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4932778843","display_name":null,"funder_award_id":"62006012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G522138796","display_name":null,"funder_award_id":"61906012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6078352744","display_name":null,"funder_award_id":"62132001","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/F4320322170","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W2190656909","https://openalex.org/W2251512949","https://openalex.org/W2319503556","https://openalex.org/W2463565445","https://openalex.org/W2560609797","https://openalex.org/W2560730294","https://openalex.org/W2594519801","https://openalex.org/W2950697717","https://openalex.org/W2963191264","https://openalex.org/W2963800628","https://openalex.org/W2964345214","https://openalex.org/W2966683369","https://openalex.org/W2966715458","https://openalex.org/W2976304245","https://openalex.org/W2981422075","https://openalex.org/W2982770724","https://openalex.org/W2988715931","https://openalex.org/W3035154952","https://openalex.org/W3091588028","https://openalex.org/W3095974555","https://openalex.org/W3107521863","https://openalex.org/W3133833192","https://openalex.org/W3138516171","https://openalex.org/W3140398265","https://openalex.org/W3166396011","https://openalex.org/W3175234951","https://openalex.org/W3178489527","https://openalex.org/W3179868941","https://openalex.org/W3181158454","https://openalex.org/W3182910454","https://openalex.org/W3188283811","https://openalex.org/W3188483917","https://openalex.org/W3193881886","https://openalex.org/W3194423521","https://openalex.org/W3203949114","https://openalex.org/W3204262622","https://openalex.org/W3206171352","https://openalex.org/W4205262979","https://openalex.org/W4212872366","https://openalex.org/W4214684415","https://openalex.org/W4226376247","https://openalex.org/W4249013746","https://openalex.org/W4288089799","https://openalex.org/W4298392976","https://openalex.org/W4312565984","https://openalex.org/W6639432524","https://openalex.org/W6682086655","https://openalex.org/W6687239747","https://openalex.org/W6719057275","https://openalex.org/W6746518932","https://openalex.org/W6766904570","https://openalex.org/W6769627184","https://openalex.org/W6791353385","https://openalex.org/W6798350552","https://openalex.org/W6798634944","https://openalex.org/W6810629022","https://openalex.org/W6810686960","https://openalex.org/W6840404596"],"related_works":["https://openalex.org/W2344367508","https://openalex.org/W2571988079","https://openalex.org/W2098629748","https://openalex.org/W2147884840","https://openalex.org/W4244608052","https://openalex.org/W2144528247","https://openalex.org/W4312050194","https://openalex.org/W3188088379","https://openalex.org/W2997255751","https://openalex.org/W656101134"],"abstract_inverted_index":{"Recently,":[0],"3D":[1,15,40,47,67,77,86,147,176],"vision-and-language":[2,12],"tasks":[3],"have":[4],"attracted":[5],"increasing":[6],"research":[7],"interest.":[8],"Compared":[9],"to":[10,28,51,81,150,173],"other":[11],"tasks,":[13],"the":[14,113,117,134,153,189,193,200],"visual":[16],"question":[17,69],"answering":[18,70],"(VQA)":[19],"task":[20,49,72],"is":[21,25],"less":[22],"exploited":[23],"and":[24,31,55,64,84,91,100,130,136,157,182,199],"more":[26,108],"susceptible":[27],"language":[29],"priors":[30],"co-reference":[32],"ambiguity.":[33],"Meanwhile,":[34],"a":[35,66,75,145],"couple":[36],"of":[37],"recently":[38],"proposed":[39,185],"VQA":[41,48,78,148,177],"datasets":[42,168,198],"do":[43],"not":[44,131],"well":[45,97],"support":[46],"due":[50],"their":[52],"limited":[53],"scale":[54],"annotation":[56],"methods.":[57],"In":[58],"this":[59],"work,":[60],"we":[61,111],"formally":[62],"define":[63],"address":[65],"grounded":[68,102,156],"(GQA)":[71],"by":[73],"collecting":[74],"new":[76,146,194],"dataset,":[79],"referred":[80],"as":[82,96,98],"flexible":[83],"explainable":[85,109,158],"GQA":[87],"(FE-3DGQA),":[88],"with":[89,121],"diverse":[90],"relatively":[92],"free-form":[93],"question-answer":[94],"pairs,":[95],"dense":[99],"completely":[101,154],"bounding":[103],"box":[104],"annotations.":[105],"To":[106],"achieve":[107],"answers,":[110],"label":[112],"objects":[114,127,138],"appeared":[115,129,132],"in":[116,133],"complex":[118],"QA":[119],"pairs":[120],"different":[122,180],"semantic":[123],"types,":[124],"including":[125],"answer-grounded":[126,140],"(both":[128],"questions),":[135],"contextual":[137],"for":[139],"objects.":[141],"We":[142],"also":[143,187],"propose":[144],"framework":[149,186],"effectively":[151,171],"predict":[152],"visually":[155],"answer.":[159],"Extensive":[160],"experiments":[161],"verify":[162],"that":[163],"our":[164,183],"newly":[165,184],"collected":[166],"benchmark":[167,195],"can":[169],"be":[170],"used":[172],"evaluate":[174],"various":[175],"methods":[178],"from":[179],"aspects":[181],"achieves":[188],"state-of-the-art":[190],"performance":[191],"on":[192],"dataset.":[196],"The":[197],"source":[201],"code":[202],"are":[203],"available":[204],"via":[205],"<uri":[206],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[207],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/zlccccc/3DVL_Codebase</uri>":[208],".":[209]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":3}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}