{"id":"https://openalex.org/W3126589408","doi":null,"title":"Improving Visual Reasoning by Exploiting The Knowledge in Texts.","display_name":"Improving Visual Reasoning by Exploiting The Knowledge in Texts.","publication_year":2021,"publication_date":"2021-02-09","ids":{"openalex":"https://openalex.org/W3126589408","mag":"3126589408"},"language":"en","primary_location":{"id":"mag:3126589408","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.04760","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2102.04760","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039442998","display_name":"Sahand Sharifzadeh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sahand Sharifzadeh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081679022","display_name":"Sina Moayed Baharlou","orcid":"https://orcid.org/0000-0003-0740-8570","observed_orcids":["https://orcid.org/0000-0003-0740-8570"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sina Moayed Baharlou","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0740-8570","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Martin Schmitt","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Schmitt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071144367","display_name":"Hinrich Sch\u00fctze","orcid":"https://orcid.org/0000-0001-9514-7934","observed_orcids":["https://orcid.org/0000-0001-9514-7934"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hinrich Sch\u00fctze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074808403","display_name":"Volker Tresp C","orcid":"https://orcid.org/0000-0001-9428-3686","observed_orcids":["https://orcid.org/0000-0001-9428-3686"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Volker Tresp","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9428-3686","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0017000000225380063,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00019999999494757503,"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/visual-reasoning","display_name":"visual reasoning","score":0.9769999980926514},{"id":"https://openalex.org/keywords/few-shot-image-classification","display_name":"few-shot image classification","score":0.7129999995231628},{"id":"https://openalex.org/keywords/relational-reasoning","display_name":"relational reasoning","score":0.7540000081062317},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.8009999990463257},{"id":"https://openalex.org/keywords/predicate-classification","display_name":"predicate classification","score":0.8529999852180481},{"id":"https://openalex.org/keywords/object-classification","display_name":"object classification","score":0.8560000061988831}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764906883239746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6716289520263672},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6245476007461548},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5388602018356323},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5054028034210205},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5005133152008057},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.49657613039016724},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46920910477638245},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4310985803604126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41567346453666687},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3694559335708618},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2849019169807434},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3126589408","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.04760","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3126589408","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.04760","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1529533208","https://openalex.org/W1686810756","https://openalex.org/W2068737686","https://openalex.org/W2085703353","https://openalex.org/W2108598243","https://openalex.org/W2127795553","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2295647632","https://openalex.org/W2579549467","https://openalex.org/W2591644541","https://openalex.org/W2604603079","https://openalex.org/W2624614404","https://openalex.org/W2626778328","https://openalex.org/W2769277182","https://openalex.org/W2827853180","https://openalex.org/W2886970679","https://openalex.org/W2887971674","https://openalex.org/W2896659472","https://openalex.org/W2903073381","https://openalex.org/W2962737704","https://openalex.org/W2962785943","https://openalex.org/W2963341956","https://openalex.org/W2963486920","https://openalex.org/W2963513598","https://openalex.org/W2963938081","https://openalex.org/W2964165364","https://openalex.org/W2970523217","https://openalex.org/W2982112268","https://openalex.org/W2987123286","https://openalex.org/W3023914348","https://openalex.org/W3030163527","https://openalex.org/W3108864070"],"related_works":["https://openalex.org/W3205821239","https://openalex.org/W4391931906","https://openalex.org/W3109771530","https://openalex.org/W3198299822","https://openalex.org/W2949231412","https://openalex.org/W2222350830","https://openalex.org/W7096923729","https://openalex.org/W3087664992","https://openalex.org/W2125263373","https://openalex.org/W2949419314"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,11,23,29,31,36,72],"new":[4],"framework":[5,25],"for":[6],"training":[7],"image-based":[8],"classifiers":[9],"from":[10,45,61,79],"combination":[12],"of":[13,64,67,86,101],"texts":[14],"and":[15,35,57,120],"images":[16,47],"with":[17,26,99],"very":[18],"few":[19],"labels.":[20],"We":[21,91],"consider":[22],"classification":[24,37,59],"three":[27],"modules:":[28],"backbone,":[30],"relational":[32,55],"reasoning":[33,56],"component,":[34],"component.":[38],"While":[39],"the":[40,54,58,84,87,96,102],"backbone":[41],"can":[42,52,106],"be":[43],"trained":[44],"unlabeled":[46],"by":[48],"self-supervised":[49],"learning,":[50],"we":[51,82,105],"fine-tune":[53],"components":[60],"external":[62],"sources":[63],"knowledge":[65,78,88],"instead":[66],"annotated":[68,103],"images.":[69],"By":[70],"proposing":[71],"transformer-based":[73],"model":[74],"that":[75],"creates":[76],"structured":[77],"textual":[80],"input,":[81],"enable":[83],"utilization":[85],"in":[89,112,117,122],"texts.":[90],"show":[92],"that,":[93],"compared":[94],"to":[95],"supervised":[97],"baselines":[98],"1%":[100],"images,":[104],"achieve":[107],"~8x":[108],"more":[109],"accurate":[110],"results":[111],"scene":[113],"graph":[114],"classification,":[115,119],"~3x":[116],"object":[118],"~1.5x":[121],"predicate":[123],"classification.":[124]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2021-02-15T00:00:00"}