{"id":"https://openalex.org/W4366459384","doi":"https://doi.org/10.3929/ethz-b-000653494","title":"Enhancing Textbooks with Visuals from the Web for Improved Learning","display_name":"Enhancing Textbooks with Visuals from the Web for Improved Learning","publication_year":2023,"publication_date":"2023-04-18","ids":{"openalex":"https://openalex.org/W4366459384","doi":"https://doi.org/10.3929/ethz-b-000653494"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2304.08931","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.08931","pdf_url":"https://arxiv.org/pdf/2304.08931","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.08931","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112584258","display_name":"Janvijay Singh","orcid":"https://orcid.org/0009-0000-0377-2610","observed_orcids":["https://orcid.org/0009-0000-0377-2610"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Singh, Janvijay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074912324","display_name":"Vil\u00e9m Zouhar","orcid":"https://orcid.org/0000-0001-9874-2069","observed_orcids":["https://orcid.org/0000-0001-9874-2069"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zouhar, Vil\u00e9m","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002316432","display_name":"Mrinmaya Sachan","orcid":"https://orcid.org/0000-0001-8787-8681","observed_orcids":["https://orcid.org/0000-0001-8787-8681"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sachan, Mrinmaya","raw_affiliation_strings":[],"raw_orcid":null,"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":true,"cited_by_count":0,"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":0.9413999915122986,"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":0.9413999915122986,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.012000000104308128,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.007899999618530273,"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/web-image-retrieval","display_name":"web image search","score":0.8429999947547913},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8730000257492065},{"id":"https://openalex.org/keywords/image-text-alignment","display_name":"image-text alignment","score":0.8769999742507935},{"id":"https://openalex.org/keywords/electronic-textbooks","display_name":"digital textbooks","score":0.7910000085830688},{"id":"https://openalex.org/keywords/educational-images","display_name":"educational images","score":0.4359999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7590510845184326},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6595233678817749},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.6435349583625793},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5989043116569519},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5898833870887756},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.541985809803009},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5244470238685608},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5043016672134399},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3993169963359833},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35126739740371704},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3253164291381836},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2304.08931","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.08931","pdf_url":"https://arxiv.org/pdf/2304.08931","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/653494","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/653494","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2304.08931","doi":"https://doi.org/10.48550/arxiv.2304.08931","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2304.08931","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.3929/ethz-b-000653494","doi":"https://doi.org/10.3929/ethz-b-000653494","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000653494","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.08931","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.08931","pdf_url":"https://arxiv.org/pdf/2304.08931","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality education","score":0.975600004196167,"id":"https://metadata.un.org/sdg/4"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366459384.pdf","grobid_xml":"https://content.openalex.org/works/W4366459384.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2135495419","https://openalex.org/W4406032893","https://openalex.org/W156899190","https://openalex.org/W4416037125","https://openalex.org/W124336032","https://openalex.org/W4389524503","https://openalex.org/W7125380444","https://openalex.org/W4399379327","https://openalex.org/W7124140355","https://openalex.org/W7067135639"],"abstract_inverted_index":{"Textbooks":[0],"are":[1,115,121],"one":[2],"of":[3,29,49,65,130,139,154],"the":[4,47,59,68,111,127,131,137],"main":[5],"mediums":[6],"for":[7,159],"delivering":[8],"high-quality":[9],"education":[10],"to":[11,38,52,92,146],"students.":[12],"In":[13,42],"particular,":[14],"explanatory":[15],"and":[16,26,73,87,125,157],"illustrative":[17],"visuals":[18,37],"play":[19],"a":[20,63,80,98,103],"key":[21],"role":[22],"in":[23,67,150],"retention,":[24],"comprehension":[25],"general":[27],"transfer":[28],"knowledge.":[30],"However,":[31],"many":[32],"textbooks":[33,55,140],"lack":[34],"these":[35],"interesting":[36],"support":[39],"student":[40],"learning.":[41],"this":[43,151],"paper,":[44],"we":[45,95,106],"investigate":[46],"effectiveness":[48],"vision-language":[50],"models":[51],"automatically":[53,118],"enhance":[54],"with":[56,141],"images":[57,91,114],"from":[58],"web.":[60],"We":[61,76,135],"collect":[62],"dataset":[64,138],"e-textbooks":[66],"math,":[69],"science,":[70],"social":[71],"science":[72],"business":[74],"domains.":[75],"then":[77],"set":[78],"up":[79],"text-image":[81],"matching":[82,99],"task":[83],"that":[84,108],"involves":[85],"retrieving":[86],"appropriately":[88],"assigning":[89],"web":[90],"textbooks,":[93],"which":[94],"frame":[96],"as":[97],"optimization":[100,132],"problem.":[101],"Through":[102],"crowd-sourced":[104],"evaluation,":[105],"verify":[107],"(1)":[109],"while":[110],"original":[112],"textbook":[113],"rated":[116],"higher,":[117],"assigned":[119],"ones":[120],"not":[122],"far":[123],"behind,":[124],"(2)":[126],"precise":[128],"formulation":[129],"problem":[133],"matters.":[134],"release":[136],"an":[142],"associated":[143],"image":[144],"bank":[145],"inspire":[147],"further":[148],"research":[149],"intersectional":[152],"area":[153],"computer":[155],"vision":[156],"NLP":[158],"education.":[160]},"counts_by_year":[],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2023-04-22T00:00:00"}