{"id":"https://openalex.org/W4378805076","doi":"https://doi.org/10.1109/tip.2023.3276570","title":"Weakly-Supervised 3D Spatial Reasoning for Text-Based Visual Question Answering","display_name":"Weakly-Supervised 3D Spatial Reasoning for Text-Based Visual Question Answering","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4378805076","doi":"https://doi.org/10.1109/tip.2023.3276570","pmid":"https://pubmed.ncbi.nlm.nih.gov/37256804"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3276570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3276570","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5103204990","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-3200-0270"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China","AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3200-0270","affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110947034","display_name":"Jinfa Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinfa Huang","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China","AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Peng Jin","orcid":"https://orcid.org/0000-0001-9287-6410"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Jin","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China","Peng Cheng Laboratory, Shenzhen, China","AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, China"],"raw_orcid":"https://orcid.org/0000-0001-9287-6410","affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008752777","display_name":"Guoli Song","orcid":"https://orcid.org/0000-0002-5452-3697"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoli Song","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5452-3697","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060958969","display_name":"Qi Wu","orcid":"https://orcid.org/0000-0003-3631-256X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["The University of Adelaide, North Terrace, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3631-256X","affiliations":[{"raw_affiliation_string":"The University of Adelaide, North Terrace, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100332984","display_name":"Jie Chen","orcid":"https://orcid.org/0000-0002-9765-4523"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Chen","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China","Peng Cheng Laboratory, Shenzhen, China","AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7654,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.9230117,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"3367","last_page":"3382"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9873999953269958,"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":0.8709166049957275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6418054699897766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5720148086547852},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.5694318413734436},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4867086708545685},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4250914752483368},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36919116973876953}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8709166049957275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6418054699897766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5720148086547852},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.5694318413734436},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4867086708545685},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4250914752483368},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36919116973876953}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3276570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3276570","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:37256804","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37256804","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G3229855046","display_name":null,"funder_award_id":"61972217","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3262489766","display_name":null,"funder_award_id":"62176249","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4768617711","display_name":null,"funder_award_id":"32071459","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5052683820","display_name":null,"funder_award_id":"2019B1515120049","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G5598344535","display_name":null,"funder_award_id":"62006133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G602081181","display_name":null,"funder_award_id":"2022ZD0118201","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7571408944","display_name":null,"funder_award_id":"62271465","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/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2157598322","https://openalex.org/W2158211626","https://openalex.org/W2204630158","https://openalex.org/W2250673545","https://openalex.org/W2506483933","https://openalex.org/W2549139847","https://openalex.org/W2745461083","https://openalex.org/W2884093133","https://openalex.org/W2890531016","https://openalex.org/W2896457183","https://openalex.org/W2902127656","https://openalex.org/W2951234442","https://openalex.org/W2954174912","https://openalex.org/W2962807621","https://openalex.org/W2962967746","https://openalex.org/W2964138343","https://openalex.org/W2965512000","https://openalex.org/W2966715458","https://openalex.org/W2979382951","https://openalex.org/W2982511464","https://openalex.org/W2986670728","https://openalex.org/W2988326850","https://openalex.org/W2997790735","https://openalex.org/W2998633559","https://openalex.org/W2998792609","https://openalex.org/W3004268082","https://openalex.org/W3004349648","https://openalex.org/W3034336960","https://openalex.org/W3034943799","https://openalex.org/W3043311956","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3093385053","https://openalex.org/W3100770207","https://openalex.org/W3106859150","https://openalex.org/W3108319047","https://openalex.org/W3110661548","https://openalex.org/W3112075608","https://openalex.org/W3115287481","https://openalex.org/W3121142147","https://openalex.org/W3121523901","https://openalex.org/W3125736290","https://openalex.org/W3136416617","https://openalex.org/W3173727695","https://openalex.org/W3179868941","https://openalex.org/W3181159501","https://openalex.org/W3197035208","https://openalex.org/W3203211567","https://openalex.org/W3205050305","https://openalex.org/W3205209899","https://openalex.org/W3207409917","https://openalex.org/W3211407386","https://openalex.org/W3214748320","https://openalex.org/W3215381707","https://openalex.org/W3215633354","https://openalex.org/W4214493665","https://openalex.org/W4221145616","https://openalex.org/W4280635869","https://openalex.org/W4283015291","https://openalex.org/W4287115696","https://openalex.org/W4288083516","https://openalex.org/W4312263373","https://openalex.org/W4312327212","https://openalex.org/W4312734855","https://openalex.org/W6620707391","https://openalex.org/W6683067110","https://openalex.org/W6685261749","https://openalex.org/W6753027577","https://openalex.org/W6754375721","https://openalex.org/W6755207826","https://openalex.org/W6766904570","https://openalex.org/W6780829533","https://openalex.org/W6786385858","https://openalex.org/W6787228247","https://openalex.org/W6796716886","https://openalex.org/W6801514204","https://openalex.org/W6803798748","https://openalex.org/W6804658932","https://openalex.org/W6810629022","https://openalex.org/W6839254850"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359","https://openalex.org/W2115758952"],"abstract_inverted_index":{"Text-based":[0],"Visual":[1],"Question":[2],"Answering":[3],"(TextVQA)":[4],"aims":[5],"to":[6,27,63,117,159],"produce":[7],"correct":[8],"answers":[9],"for":[10,134,152],"given":[11],"questions":[12,190],"about":[13],"the":[14,23,28,31,55,67,80,91,97,113,119,137,154,205,211],"images":[15,57],"with":[16],"multiple":[17],"scene":[18,88],"texts.":[19],"In":[20,104],"most":[21],"cases,":[22],"texts":[24,37,89],"naturally":[25],"attach":[26],"surface":[29],"of":[30,101,122,139,141,185,207],"objects.":[32,161],"Therefore,":[33],"spatial":[34,51,75,82,114,193],"reasoning":[35,76,115,194],"between":[36,84],"and":[38,58,87,99,173,187,197],"objects":[39,86,124],"is":[40],"crucial":[41],"in":[42,195],"TextVQA.":[43],"However,":[44],"existing":[45],"approaches":[46,77],"are":[47],"constrained":[48],"within":[49],"2D":[50,74],"information":[52,111],"learned":[53],"from":[54],"input":[56],"rely":[59],"on":[60,90,171,189,210],"transformer-based":[61],"architectures":[62],"reason":[64],"implicitly":[65],"during":[66],"fusion":[68],"process.":[69],"Under":[70],"this":[71,105],"setting,":[72],"these":[73],"cannot":[78],"distinguish":[79],"fine-grained":[81],"relations":[83],"visual":[85],"same":[92],"image":[93,213],"plane,":[94],"thereby":[95],"impairing":[96],"interpretability":[98],"performance":[100,170],"TextVQA":[102,172,196],"models.":[103],"paper,":[106],"we":[107,128,145,202],"introduce":[108],"3D":[109],"geometric":[110],"into":[112],"process":[116],"capture":[118],"contextual":[120],"knowledge":[121],"key":[123],"step-by-step.":[125],"Specifically,":[126],"(i)":[127],"propose":[129],"a":[130,147],"relation":[131],"prediction":[132],"module":[133,151],"accurately":[135],"locating":[136],"region":[138],"interest":[140],"critical":[142,160],"objects;":[143],"(ii)":[144],"design":[146],"depth-aware":[148],"attention":[149,157],"calibration":[150],"calibrating":[153],"OCR":[155],"tokens'":[156],"according":[158],"Extensive":[162],"experiments":[163],"show":[164],"that":[165,191],"our":[166,178,208],"method":[167],"achieves":[168],"state-of-the-art":[169],"ST-VQA":[174,198],"datasets.":[175],"More":[176],"encouragingly,":[177],"model":[179,209],"surpasses":[180],"others":[181],"by":[182],"clear":[183],"margins":[184],"5.7%":[186],"12.1%":[188],"involve":[192],"valid":[199],"split.":[200],"Besides,":[201],"also":[203],"verify":[204],"generalizability":[206],"text-based":[212],"captioning":[214],"task.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}