{"id":"https://openalex.org/W4387968416","doi":"https://doi.org/10.1145/3581783.3612593","title":"Scene-text Oriented Visual Entailment: Task, Dataset and Solution","display_name":"Scene-text Oriented Visual Entailment: Task, Dataset and Solution","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968416","doi":"https://doi.org/10.1145/3581783.3612593"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612593","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-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/A5104992771","display_name":"N. Li","orcid":"https://orcid.org/0009-0003-0576-1773"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Nan Li","raw_affiliation_strings":["Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033158939","display_name":"Pijian Li","orcid":"https://orcid.org/0009-0005-1924-5248"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pijian Li","raw_affiliation_strings":["Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103177231","display_name":"Dongsheng Xu","orcid":"https://orcid.org/0009-0003-2481-5669"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Xu","raw_affiliation_strings":["Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015766803","display_name":"Wenye Zhao","orcid":"https://orcid.org/0009-0004-5482-6753"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenye Zhao","raw_affiliation_strings":["Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089123257","display_name":"Yi Cai","orcid":"https://orcid.org/0000-0002-1767-789X"},"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":"Yi Cai","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061381102","display_name":"Qingbao Huang","orcid":"https://orcid.org/0000-0001-7691-347X"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingbao Huang","raw_affiliation_strings":["Guangxi University & Guangxi Key Laboratory of Multimedia Communications and Network Technology, Nanning, China"],"affiliations":[{"raw_affiliation_string":"Guangxi University & Guangxi Key Laboratory of Multimedia Communications and Network Technology, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5104992771"],"corresponding_institution_ids":["https://openalex.org/I150807315"],"apc_list":null,"apc_paid":null,"fwci":0.2407,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53635318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5562","last_page":"5571"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9961000084877014,"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":0.9927999973297119,"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":0.8065901398658752},{"id":"https://openalex.org/keywords/textual-entailment","display_name":"Textual entailment","score":0.6746218204498291},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6448971629142761},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6236855983734131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6178130507469177},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4621255099773407},{"id":"https://openalex.org/keywords/logical-consequence","display_name":"Logical consequence","score":0.43875232338905334},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42157670855522156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8065901398658752},{"id":"https://openalex.org/C95318506","wikidata":"https://www.wikidata.org/wiki/Q6588467","display_name":"Textual entailment","level":3,"score":0.6746218204498291},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6448971629142761},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6236855983734131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6178130507469177},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4621255099773407},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.43875232338905334},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42157670855522156},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612593","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1380176761","display_name":null,"funder_award_id":"2020B0101100002","funder_id":"https://openalex.org/F4320323059","funder_display_name":"South China University of Technology"},{"id":"https://openalex.org/G1473307615","display_name":null,"funder_award_id":"2022GXNSFAA035627","funder_id":"https://openalex.org/F4320322768","funder_display_name":"Natural Science Foundation of Guangxi Province"},{"id":"https://openalex.org/G1477544716","display_name":null,"funder_award_id":"Guangdong","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2799848387","display_name":null,"funder_award_id":"62076100","funder_id":"https://openalex.org/F4320335795","funder_display_name":"Science and Technology Planning Project of Guangdong Province"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4572242254","display_name":null,"funder_award_id":"2020B0101100002","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4913122426","display_name":null,"funder_award_id":"2020B0101100002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5760752404","display_name":null,"funder_award_id":"Projects","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6268037997","display_name":null,"funder_award_id":"62276072, 62076100, and 62261003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6770297356","display_name":null,"funder_award_id":"62276072","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7020966827","display_name":null,"funder_award_id":"62076100","funder_id":"https://openalex.org/F4320323059","funder_display_name":"South China University of Technology"},{"id":"https://openalex.org/G7608752429","display_name":null,"funder_award_id":"Talent","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8189774080","display_name":null,"funder_award_id":"62076100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8586639432","display_name":null,"funder_award_id":"62076100","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8718620462","display_name":null,"funder_award_id":"2020B0101100002","funder_id":"https://openalex.org/F4320335795","funder_display_name":"Science and Technology Planning Project of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322768","display_name":"Natural Science Foundation of Guangxi Province","ror":null},{"id":"https://openalex.org/F4320323059","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320335795","display_name":"Science and Technology Planning Project of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1840435438","https://openalex.org/W1933349210","https://openalex.org/W2053317383","https://openalex.org/W2413794162","https://openalex.org/W2463955103","https://openalex.org/W2493916176","https://openalex.org/W2560674852","https://openalex.org/W2891012317","https://openalex.org/W2963717374","https://openalex.org/W2979382951","https://openalex.org/W2988326850","https://openalex.org/W3016970897","https://openalex.org/W3034336960","https://openalex.org/W3090449556","https://openalex.org/W3093272873","https://openalex.org/W3103934428","https://openalex.org/W3106859150","https://openalex.org/W3108319047","https://openalex.org/W3112075608","https://openalex.org/W3161801106","https://openalex.org/W3173803111","https://openalex.org/W3177430964","https://openalex.org/W3184784418","https://openalex.org/W3215381707","https://openalex.org/W4253067820","https://openalex.org/W4285191490","https://openalex.org/W4288055855","https://openalex.org/W4312336279","https://openalex.org/W4312802716","https://openalex.org/W4313184803"],"related_works":["https://openalex.org/W2169644218","https://openalex.org/W12963412","https://openalex.org/W2250460949","https://openalex.org/W3158371345","https://openalex.org/W3141423438","https://openalex.org/W2071098659","https://openalex.org/W2627035043","https://openalex.org/W4385571113","https://openalex.org/W2937401546","https://openalex.org/W2741782787"],"abstract_inverted_index":{"Visual":[0,75],"Entailment":[1,76],"(VE)":[2],"is":[3,148,189],"a":[4,16,69,101,132,158,163],"fine-grained":[5],"reasoning":[6,173],"task":[7,71,99],"aiming":[8],"to":[9,54,81,103,144,166],"predict":[10,82],"whether":[11,83],"the":[12,33,88,94,106,125,151,168],"image":[13,85],"semantically":[14,86],"entails":[15,40,87],"hypothesis":[17,58,90],"in":[18,191],"textual":[19],"form.Existing":[20],"studies":[21],"of":[22,35,57,137,153],"VE":[23],"only":[24],"focus":[25],"on":[26,93,127],"basic":[27],"visual":[28,97,122,172,182],"attributes":[29],"but":[30],"largely":[31],"overlook":[32],"importance":[34],"scene":[36,95,113,119,145,177],"text,":[37,114,120,146],"which":[38,78,147],"usually":[39],"rich":[41],"semantic":[42],"information":[43],"and":[44,51,110,121,140,171,181,194],"crucial":[45],"clues":[46],"(e.g.,":[47],"time,":[48],"place,":[49],"affiliation,":[50],"topic),":[52],"leading":[53],"superficial":[55],"design":[56],"or":[59],"incorrect":[60],"entailment":[61],"prediction.":[62],"To":[63],"fill":[64],"this":[65],"gap,":[66],"we":[67,129,156],"propose":[68],"new":[70],"called":[72],"scene-text":[73],"oriented":[74],"(STOVE),":[77],"requires":[79],"models":[80],"an":[84],"corresponding":[89],"designed":[91],"based":[92],"text-centered":[96],"information.STOVE":[98],"challenges":[100],"model":[102,167,188],"deeply":[104],"understand":[105],"interplay":[107],"between":[108,175],"language":[109],"images":[111,139],"containing":[112],"requiring":[115],"aligning":[116],"hypotheses":[117,142],"tokens,":[118,179],"contents.To":[123],"support":[124],"researches":[126],"STOVE,":[128],"further":[130],"collect":[131],"dataset":[133],"termed":[134],"TextVE,":[135],"consisting":[136],"23,864":[138],"47,728":[141],"related":[143],"constructed":[149],"with":[150],"strategy":[152],"minimizing":[154],"biases.Additionally,":[155],"present":[157],"baseline":[159],"named":[160],"MMTVE":[161],"applying":[162],"multimodal":[164],"transformer":[165],"spatial,":[169],"semantic,":[170],"relations":[174],"multiple":[176],"text":[178],"hypotheses,":[180],"features.Experimental":[183],"results":[184],"illustrate":[185],"that":[186],"our":[187],"effective":[190],"comprehending":[192],"STOVE":[193],"achieves":[195],"outstanding":[196],"performance.Our":[197],"codes":[198],"are":[199],"available":[200],"at":[201],"https://github.com/VISLANG-Lab/TextVE.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}