{"id":"https://openalex.org/W4313013044","doi":"https://doi.org/10.1109/tcsvt.2022.3231463","title":"Spatial-Semantic Collaborative Graph Network for Textbook Question Answering","display_name":"Spatial-Semantic Collaborative Graph Network for Textbook Question Answering","publication_year":2022,"publication_date":"2022-12-21","ids":{"openalex":"https://openalex.org/W4313013044","doi":"https://doi.org/10.1109/tcsvt.2022.3231463"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3231463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3231463","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/A5101851808","display_name":"Yaxian Wang","orcid":"https://orcid.org/0000-0003-3193-3658"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxian Wang","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-3193-3658","affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070094915","display_name":"Bifan Wei","orcid":"https://orcid.org/0000-0002-9732-3011"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bifan Wei","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361891","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-6004-0675"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-6004-0675","affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086407377","display_name":"Qika Lin","orcid":"https://orcid.org/0000-0001-5650-0600"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qika Lin","raw_affiliation_strings":["National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0001-5650-0600","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384144","display_name":"Lingling Zhang","orcid":"https://orcid.org/0000-0001-8136-8795"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingling Zhang","raw_affiliation_strings":["National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0001-8136-8795","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000446732","display_name":"Yaqiang Wu","orcid":"https://orcid.org/0000-0001-8830-8250"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqiang Wu","raw_affiliation_strings":["Lenovo Research, Beijing, China","School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8830-8250","affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3703,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.82383459,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"33","issue":"7","first_page":"3214","last_page":"3228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.996999979019165,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9817000031471252,"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":0.8196797370910645},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5669441223144531},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5543926954269409},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5357866287231445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.512486457824707},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4882374107837677},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4511052370071411},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4423127770423889},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4119873642921448},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15827065706253052}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8196797370910645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5669441223144531},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5543926954269409},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5357866287231445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.512486457824707},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4882374107837677},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4511052370071411},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4423127770423889},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4119873642921448},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15827065706253052},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2022.3231463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3231463","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":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1133573065","display_name":null,"funder_award_id":"62176207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2172843688","display_name":null,"funder_award_id":"62250009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2372956478","display_name":null,"funder_award_id":"2023-JC-YB-293","funder_id":"https://openalex.org/F4320336567","funder_display_name":"Natural Science Basic Research Program of Shaanxi Province"},{"id":"https://openalex.org/G3250154588","display_name":null,"funder_award_id":"62106190","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4303215675","display_name":null,"funder_award_id":"62192781","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4896784468","display_name":null,"funder_award_id":"62137002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6387986177","display_name":null,"funder_award_id":"61721002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7339645210","display_name":null,"funder_award_id":"62176209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7695114569","display_name":null,"funder_award_id":"2020AAA0108800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7758118313","display_name":"\u591a\u7a7a\u95f4\u878d\u5408\u4e0b\u7684\u5927\u5b66\u751f\u4e2a\u6027\u5316\u5b66\u4e60\u4e0e\u667a\u80fd\u6559\u80b2\u670d\u52a1\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61937001","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/F4320327609","display_name":"China Knowledge Centre for Engineering Sciences and Technology","ror":null},{"id":"https://openalex.org/F4320330193","display_name":"Chinese Academy of Engineering","ror":"https://ror.org/00z3yke57"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336567","display_name":"Natural Science Basic Research Program of Shaanxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1933349210","https://openalex.org/W1983419592","https://openalex.org/W2121406004","https://openalex.org/W2194775991","https://openalex.org/W2250564385","https://openalex.org/W2307512708","https://openalex.org/W2321533354","https://openalex.org/W2745461083","https://openalex.org/W2746097825","https://openalex.org/W2766732270","https://openalex.org/W2785325870","https://openalex.org/W2799088654","https://openalex.org/W2896457183","https://openalex.org/W2897899251","https://openalex.org/W2948433173","https://openalex.org/W2949431215","https://openalex.org/W2950382646","https://openalex.org/W2952688802","https://openalex.org/W2952938873","https://openalex.org/W2958360136","https://openalex.org/W2962959437","https://openalex.org/W2963420691","https://openalex.org/W2963907629","https://openalex.org/W2964015378","https://openalex.org/W2964042428","https://openalex.org/W2965373594","https://openalex.org/W2981165461","https://openalex.org/W3025102114","https://openalex.org/W3034999214","https://openalex.org/W3035106315","https://openalex.org/W3094172275","https://openalex.org/W3095789240","https://openalex.org/W3106250896","https://openalex.org/W3106278732","https://openalex.org/W3114632476","https://openalex.org/W3131251978","https://openalex.org/W3134134173","https://openalex.org/W3167387364","https://openalex.org/W3175787213","https://openalex.org/W3176186248","https://openalex.org/W3189092450","https://openalex.org/W3199573137","https://openalex.org/W3201541489","https://openalex.org/W4206337866","https://openalex.org/W4221138453","https://openalex.org/W4249573750","https://openalex.org/W4282936652","https://openalex.org/W4293584584","https://openalex.org/W4294558607","https://openalex.org/W4304015009","https://openalex.org/W4385262803","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6700872662","https://openalex.org/W6726873649","https://openalex.org/W6738893770","https://openalex.org/W6738964360","https://openalex.org/W6745915114","https://openalex.org/W6747837047","https://openalex.org/W6747899497","https://openalex.org/W6750227808","https://openalex.org/W6754778999","https://openalex.org/W6755207826","https://openalex.org/W6763837953","https://openalex.org/W6766673545","https://openalex.org/W6777837344","https://openalex.org/W6785652829","https://openalex.org/W6786291769","https://openalex.org/W6790838182","https://openalex.org/W6798222824"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","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"],"abstract_inverted_index":{"Textbook":[0],"Question":[1],"Answering":[2],"(TQA)":[3],"task":[4],"requires":[5],"answering":[6],"questions":[7],"by":[8,191,213],"reasoning":[9,190],"based":[10,164],"on":[11,165],"both":[12],"the":[13,25,28,33,56,67,74,76,87,96,106,127,137,145,159,166,172,175,206,215,230],"given":[14],"diagrams":[15,29],"and":[16,45,62,129,132,147,153,209,218,223],"text":[17,97,102,130,210,219],"context.":[18],"There":[19],"are":[20,30,226],"mainly":[21],"two":[22],"challenges":[23],"for":[24,53,73,120,188],"task.":[26],"First,":[27],"different":[31,43],"from":[32],"natural":[34],"images.":[35],"Similar":[36],"shapes":[37],"or":[38],"color":[39],"blocks":[40],"may":[41],"express":[42],"semantics":[44,98],"there":[46],"is":[47,92],"also":[48],"a":[49,83,101,114],"large":[50],"intra-topic":[51],"variation":[52],"diagrams.":[54],"Hence,":[55],"characteristics":[57],"of":[58,171,232],"visual":[59,64,151],"semantic":[60,148,161,211],"ambiguity":[61],"variable":[63],"appearance":[65],"make":[66],"diagram":[68,128,160,208,216],"understanding":[69,131],"more":[70,193],"challenging.":[71],"Second,":[72],"text,":[75],"specific":[77],"education":[78],"domain":[79],"with":[80,86],"terminologies":[81],"exists":[82],"great":[84],"gap":[85],"general":[88,107],"domain.":[89,108],"Therefore,":[90],"it":[91],"difficult":[93],"to":[94,156,204,228],"represent":[95],"effectively":[99],"using":[100],"encoder":[103,217],"pretrained":[104],"in":[105],"In":[109],"this":[110],"paper,":[111],"we":[112],"propose":[113,199],"Spatial-Semantic":[115],"Collaborative":[116],"Graph":[117,178],"Network":[118,179],"(SSCGN)":[119],"TQA":[121],"task,":[122],"which":[123],"can":[124,181],"help":[125,182],"enhance":[126,158,205],"facilitate":[133],"multimodal":[134],"reasoning.":[135],"Specifically,":[136],"Spatial-guided":[138],"Semantic":[139],"Enhancing":[140],"(SSE)":[141],"module":[142],"fully":[143],"exploits":[144],"spatial":[146,195],"relationships":[149],"between":[150],"objects":[152],"OCR":[154],"tokens":[155],"collaboratively":[157],"understanding.":[162],"Moreover,":[163],"semantically":[167],"enhanced":[168],"region":[169,186],"representations":[170,187,212],"SSE":[173],"module,":[174],"Fine-grained":[176],"Spatial-Aware":[177],"(FSA-GN)":[180],"obtain":[183],"richer":[184],"relation-aware":[185],"joint":[189],"capturing":[192],"fine-grained":[194],"relationships.":[196],"We":[197],"further":[198],"multiple":[200],"self-supervised":[201],"auxiliary":[202],"tasks":[203],"initial":[207],"pretraining":[214],"encoder.":[220],"Extensive":[221],"experiments":[222],"ablation":[224],"studies":[225],"conducted":[227],"validate":[229],"effectiveness":[231],"SSCGN.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}