{"id":"https://openalex.org/W3093385053","doi":"https://doi.org/10.1145/3394171.3413924","title":"Cascade Reasoning Network for Text-based Visual Question Answering","display_name":"Cascade Reasoning Network for Text-based Visual Question Answering","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093385053","doi":"https://doi.org/10.1145/3394171.3413924","mag":"3093385053"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413924","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5045085581","display_name":"Fen Liu","orcid":"https://orcid.org/0000-0001-8479-3770"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fen Liu","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101552980","display_name":"Guanghui Xu","orcid":"https://orcid.org/0000-0003-2910-9870"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanghui Xu","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"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":["University of Adelaide, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090234226","display_name":"Qing Du","orcid":"https://orcid.org/0000-0002-8411-6734"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Du","raw_affiliation_strings":["South China Univercity of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Univercity of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012128773","display_name":"Jia Wei","orcid":"https://orcid.org/0000-0002-2234-0378"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Jia","raw_affiliation_strings":["CVTE, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVTE, Guangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032352025","display_name":"Mingkui Tan","orcid":"https://orcid.org/0000-0001-8856-756X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingkui Tan","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4060","last_page":"4069"},"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":0.9972000122070312,"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":0.9916999936103821,"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":0.8932178616523743},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7927972078323364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6025833487510681},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5448659658432007},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.498981237411499},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4980051517486572},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4614940881729126},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40250861644744873},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10474807024002075}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8932178616523743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7927972078323364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6025833487510681},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5448659658432007},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.498981237411499},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4980051517486572},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4614940881729126},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40250861644744873},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10474807024002075}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413924","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W639708223","https://openalex.org/W1647671624","https://openalex.org/W1933349210","https://openalex.org/W2116341502","https://openalex.org/W2119717200","https://openalex.org/W2130942839","https://openalex.org/W2155027007","https://openalex.org/W2194775991","https://openalex.org/W2463565445","https://openalex.org/W2608030593","https://openalex.org/W2736601468","https://openalex.org/W2745461083","https://openalex.org/W2747329762","https://openalex.org/W2809273748","https://openalex.org/W2896902935","https://openalex.org/W2897870704","https://openalex.org/W2904910963","https://openalex.org/W2916723116","https://openalex.org/W2951619830","https://openalex.org/W2962824887","https://openalex.org/W2963206679","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963420691","https://openalex.org/W2963622213","https://openalex.org/W2963705779","https://openalex.org/W2963738360","https://openalex.org/W2963907629","https://openalex.org/W2963954913","https://openalex.org/W2964067226","https://openalex.org/W2964094751","https://openalex.org/W2966683369","https://openalex.org/W2970896726","https://openalex.org/W2979382951","https://openalex.org/W2981578638","https://openalex.org/W2981963155","https://openalex.org/W2995993311","https://openalex.org/W2997344006","https://openalex.org/W3004268082","https://openalex.org/W3004349648","https://openalex.org/W3029601968","https://openalex.org/W3034336960","https://openalex.org/W3034943799","https://openalex.org/W3037932933","https://openalex.org/W3082274269","https://openalex.org/W4214671568","https://openalex.org/W4297683907"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W297543570","https://openalex.org/W2964061310","https://openalex.org/W2231285690","https://openalex.org/W2963477107","https://openalex.org/W3093385053","https://openalex.org/W4390091918","https://openalex.org/W2553418567","https://openalex.org/W4389682534","https://openalex.org/W3045060014"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,57,93,96,101,110,113,147,150,162,168,178,189,192,202,210,214,227],"problem":[3],"of":[4,133,213,229],"text-based":[5],"visual":[6,15,26,37,82,97,185],"question":[7,16,217],"answering":[8,17],"(T-VQA)":[9],"in":[10,41,44,48,60,216],"this":[11],"paper.":[12],"Unlike":[13],"general":[14],"(VQA)":[18],"which":[19],"only":[20],"builds":[21],"connections":[22,179],"between":[23,92,182],"questions":[24,61,77],"and":[25,31,36,62,95,139,160,180,184],"contents,":[27],"T-VQA":[28,45,224],"requires":[29],"reading":[30],"reasoning":[32,142,211],"over":[33],"both":[34],"texts":[35,94,183],"concepts":[38],"that":[39,131],"appear":[40],"images.":[42],"Challenges":[43],"mainly":[46],"lie":[47],"three":[49,222],"aspects:":[50],"1)":[51],"It":[52],"is":[53,86,239],"difficult":[54,87],"to":[55,71,81,88,108,166,175,200],"understand":[56],"complex":[58],"logic":[59],"extract":[63],"specific":[64],"useful":[65],"information":[66,152],"from":[67],"rich":[68],"image":[69],"contents":[70],"answer":[72],"them;":[73],"2)":[74],"The":[75,172,236],"text-related":[76],"are":[78],"also":[79],"related":[80],"concepts,":[83],"but":[84],"it":[85],"capture":[89],"cross-modal":[90],"relationships":[91],"concepts;":[98],"3)":[99],"If":[100],"OCR":[102,193],"(optical":[103],"character":[104],"recognition)":[105],"system":[106],"fails":[107],"detect":[109],"target":[111],"text,":[112],"training":[114],"will":[115],"be":[116],"very":[117],"difficult.":[118],"To":[119,187],"address":[120],"these":[121],"issues,":[122],"we":[123,195],"propose":[124],"a":[125,134,140,156],"novel":[126],"Cascade":[127],"Reasoning":[128],"Network":[129],"(CRN)":[130],"consists":[132],"progressive":[135],"attention":[136,164],"module":[137],"(PAM)":[138],"multimodal":[141,151],"graph":[143],"(MRG)":[144],"module.":[145],"Specifically,":[146],"PAM":[148],"regards":[149],"fusion":[153,170],"operation":[154],"as":[155],"stepwise":[157],"encoding":[158],"process":[159],"uses":[161],"previous":[163],"results":[165],"guide":[167],"next":[169],"process.":[171],"MRG":[173],"aims":[174],"explicitly":[176],"model":[177,203,215],"interactions":[181],"concepts.":[186],"alleviate":[188],"dependence":[190],"on":[191,221],"system,":[194],"introduce":[196],"an":[197],"auxiliary":[198],"task":[199],"train":[201],"with":[204,233],"accurate":[205],"supervision":[206],"signals,":[207],"thereby":[208],"enhancing":[209],"ability":[212],"answering.":[218],"Extensive":[219],"experiments":[220],"popular":[223],"datasets":[225],"demonstrate":[226],"effectiveness":[228],"our":[230],"method":[231],"compared":[232],"SOTA":[234],"methods.":[235],"source":[237],"code":[238],"available":[240],"at":[241],"https://github.com/guanghuixu/CRN_tvqa.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}