{"id":"https://openalex.org/W7166851441","doi":"https://doi.org/10.18653/v1/2026.findings-acl.614","title":"PedagogyBench: A Cognitive-Driven Benchmark for Multimodal Instructional Video Understanding","display_name":"PedagogyBench: A Cognitive-Driven Benchmark for Multimodal Instructional Video Understanding","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166851441","doi":"https://doi.org/10.18653/v1/2026.findings-acl.614"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.614","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.614","pdf_url":"https://aclanthology.org/2026.findings-acl.614.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.614.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139848859","display_name":"Xiaokang Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]},{"id":"https://openalex.org/I163151501","display_name":"Hangzhou Normal University","ror":"https://ror.org/014v1mr15","country_code":"CN","type":"education","lineage":["https://openalex.org/I163151501"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Jin","raw_affiliation_strings":["School of Computer Science and Technology , Zhejiang Normal University","Zhejiang Key Laboratory of Intelligent Education Technology and Application , Zhejiang Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Zhejiang Normal University","institution_ids":["https://openalex.org/I135237710","https://openalex.org/I163151501"]},{"raw_affiliation_string":"Zhejiang Key Laboratory of Intelligent Education Technology and Application , Zhejiang Normal University","institution_ids":["https://openalex.org/I135237710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139743872","display_name":"Jia Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Zhu","raw_affiliation_strings":["Zhejiang Key Laboratory of Intelligent Education Technology and Application , Zhejiang Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Key Laboratory of Intelligent Education Technology and Application , Zhejiang Normal University","institution_ids":["https://openalex.org/I135237710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139819168","display_name":"Jingjiang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]},{"id":"https://openalex.org/I163151501","display_name":"Hangzhou Normal University","ror":"https://ror.org/014v1mr15","country_code":"CN","type":"education","lineage":["https://openalex.org/I163151501"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjiang Liu","raw_affiliation_strings":["School of Computer Science and Technology , Zhejiang Normal University","Zhejiang Key Laboratory of Intelligent Education Technology and Application , Zhejiang Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Zhejiang Normal University","institution_ids":["https://openalex.org/I135237710","https://openalex.org/I163151501"]},{"raw_affiliation_string":"Zhejiang Key Laboratory of Intelligent Education Technology and Application , Zhejiang Normal University","institution_ids":["https://openalex.org/I135237710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139803884","display_name":"Yabing Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabing Shi","raw_affiliation_strings":["Zhejiang Key Laboratory of Intelligent Education Technology and Application , Zhejiang Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Key Laboratory of Intelligent Education Technology and Application , Zhejiang Normal University","institution_ids":["https://openalex.org/I135237710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139724401","display_name":"Jueqi Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jueqi Guan","raw_affiliation_strings":["Zhejiang Key Laboratory of Intelligent Education Technology and Application , Zhejiang Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Key Laboratory of Intelligent Education Technology and Application , Zhejiang Normal University","institution_ids":["https://openalex.org/I135237710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139786768","display_name":"Hao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["Tencent Financial Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Financial Technology","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139840636","display_name":"Pasquale De Meo","orcid":null},"institutions":[{"id":"https://openalex.org/I112862951","display_name":"University of Messina","ror":"https://ror.org/05ctdxz19","country_code":"IT","type":"education","lineage":["https://openalex.org/I112862951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pasquale De Meo","raw_affiliation_strings":["Department of Computer Science , University of Messina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Messina","institution_ids":["https://openalex.org/I112862951"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86174848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12621","last_page":"12647"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11516","display_name":"Visual and Cognitive Learning Processes","score":0.24079999327659607,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11516","display_name":"Visual and Cognitive Learning Processes","score":0.24079999327659607,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11935","display_name":"Literacy, Media, and Education","score":0.18549999594688416,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13071","display_name":"Digital Storytelling and Education","score":0.039900001138448715,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5141000151634216},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30570000410079956},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.26019999384880066},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.24300000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705299973487854},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5141000151634216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.436599999666214},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3165999948978424},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2483000010251999},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.24300000071525574},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.24150000512599945}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.614","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.614","pdf_url":"https://aclanthology.org/2026.findings-acl.614.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.614","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.614","pdf_url":"https://aclanthology.org/2026.findings-acl.614.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7573901414871216}],"awards":[{"id":"https://openalex.org/G3242285834","display_name":null,"funder_award_id":"62577050","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5413424198","display_name":null,"funder_award_id":"[2024]1","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166851441.pdf","grobid_xml":"https://content.openalex.org/works/W7166851441.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"video":[1,34],"understanding":[2,35],"benchmarks":[3],"mainly":[4],"emphasize":[5],"general":[6],"visual":[7,127],"recognition":[8],"and":[9,45,72],"reasoning,":[10],"but":[11,113],"do":[12],"not":[13],"adequately":[14],"capture":[15],"the":[16,59,78,85],"pedagogical":[17,38,91,117],"logic":[18],"embedded":[19],"in":[20,37],"instructional":[21,33],"videos.To":[22],"address":[23],"this":[24],"gap,":[25,104],"we":[26],"present":[27],"PedagogyBench,":[28],"a":[29,41,46,62,66,101],"multimodal":[30,96],"benchmark":[31],"for":[32],"grounded":[36,126],"cognition.We":[39],"introduce":[40],"pedagogy-driven":[42],"segmentation":[43],"strategy":[44],"dual-stream":[47],"semantic":[48],"injection":[49],"pipeline":[50],"that":[51],"combines":[52],"machine":[53],"pre-annotation":[54],"with":[55,69],"expert":[56],"refinement,":[57],"enabling":[58],"construction":[60],"of":[61,87],"dataset":[63],"organized":[64],"around":[65],"cognitive":[67,92],"pyramid":[68],"four":[70],"levels":[71],"20":[73],"fine-grained":[74],"tasks.We":[75],"further":[76],"propose":[77],"Cognitive":[79],"Fidelity":[80],"Score":[81],"(CFS)":[82],"to":[83],"measure":[84],"balance":[86],"model":[88],"performance":[89],"across":[90],"dimensions.Experiments":[93],"on":[94,110,115,121],"12":[95],"large":[97],"language":[98],"models":[99,106],"reveal":[100],"clear":[102],"generative":[103],"where":[105],"perform":[107],"relatively":[108],"well":[109],"discriminative":[111],"tasks":[112],"degrade":[114],"higher-order":[116],"diagnosis,":[118],"often":[119],"relying":[120],"parametric":[122],"memory":[123],"rather":[124],"than":[125],"perception.Project":[128],"resources":[129],"are":[130],"available":[131],"at":[132],"https://github.":[133],"com/Shallcom/PedagogyBench.":[134]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-02T00:00:00"}