{"id":"https://openalex.org/W4416932168","doi":"https://doi.org/10.1109/wacv61042.2026.00658","title":"Exploring Automated Recognition of Instructional Activity and Discourse from Multimodal Classroom Data","display_name":"Exploring Automated Recognition of Instructional Activity and Discourse from Multimodal Classroom Data","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416932168","doi":"https://doi.org/10.1109/wacv61042.2026.00658"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.00087","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ivo Bueno","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ivo Bueno","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruikun Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ruikun Hou","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057566592","display_name":"Babette B\u00fchler","orcid":"https://orcid.org/0000-0003-1679-4979"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Babette B\u00fchler","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036008938","display_name":"Tim F\u00fctterer","orcid":"https://orcid.org/0000-0001-5399-9557"},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim F\u00fctterer","raw_affiliation_strings":["University of Tübingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tübingen","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057770557","display_name":"James Drimalla","orcid":"https://orcid.org/0000-0001-7418-5245"},"institutions":[{"id":"https://openalex.org/I305130695","display_name":"Gordon College","ror":"https://ror.org/0364wpq06","country_code":"US","type":"education","lineage":["https://openalex.org/I305130695"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Drimalla","raw_affiliation_strings":["Gordon College"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gordon College","institution_ids":["https://openalex.org/I305130695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068112880","display_name":"Jonathan Foster","orcid":"https://orcid.org/0000-0002-9439-0884"},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan K. Foster","raw_affiliation_strings":["University at Albany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Albany","institution_ids":["https://openalex.org/I392282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081562360","display_name":"Peter Youngs","orcid":"https://orcid.org/0000-0002-1711-1749"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Youngs","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089332735","display_name":"Peter Gerjets","orcid":"https://orcid.org/0000-0003-1358-6779"},"institutions":[{"id":"https://openalex.org/I4210136238","display_name":"Leibniz-Institut f\u00fcr Wissensmedien","ror":"https://ror.org/03hv28176","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210136238"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Gerjets","raw_affiliation_strings":["Leibniz-Institut für Wissensmedien"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz-Institut für Wissensmedien","institution_ids":["https://openalex.org/I4210136238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086577266","display_name":"Ulrich Trautwein","orcid":"https://orcid.org/0000-0003-0647-0057"},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulrich Trautwein","raw_affiliation_strings":["University of Tübingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tübingen","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008809634","display_name":"Enkelejda Kasneci","orcid":"https://orcid.org/0000-0003-3146-4484"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Enkelejda Kasneci","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01741311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6806","last_page":"6817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.30709999799728394,"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":0.30709999799728394,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.14000000059604645,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.08550000190734863,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5245000123977661},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4837999939918518},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46389999985694885},{"id":"https://openalex.org/keywords/discourse-analysis","display_name":"Discourse analysis","score":0.45890000462532043},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.39480000734329224},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3785000145435333},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.3467999994754791}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6868000030517578},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5245000123977661},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4837999939918518},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46389999985694885},{"id":"https://openalex.org/C84389358","wikidata":"https://www.wikidata.org/wiki/Q1129466","display_name":"Discourse analysis","level":2,"score":0.45890000462532043},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4415000081062317},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4122999906539917},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34439998865127563},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3319999873638153},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C71611378","wikidata":"https://www.wikidata.org/wiki/Q5165191","display_name":"Contextual design","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2630000114440918}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.00087","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.00087","pdf_url":"https://arxiv.org/pdf/2512.00087","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.00087","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.00087","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.00087","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.00087","pdf_url":"https://arxiv.org/pdf/2512.00087","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Observation":[0],"of":[1,29,51,54,133,146],"classroom":[2,30,148],"interactions":[3],"can":[4],"provide":[5],"concrete":[6],"feedback":[7,157],"to":[8,22],"teachers,":[9],"but":[10],"current":[11],"methods":[12],"rely":[13],"on":[14,33,79,99],"manual":[15],"annotation,":[16],"which":[17],"is":[18],"resource-intensive":[19],"and":[20,37,56,75,93,107,116,137,150],"hard":[21],"scale.":[23],"This":[24],"work":[25],"explores":[26],"AI-driven":[27],"analysis":[28,149],"recordings,":[31],"focusing":[32],"multimodal":[34,70],"instructional":[35],"activity":[36,81],"discourse":[38,101],"recognition":[39],"as":[40],"a":[41,47,87,152],"foundation":[42,153],"for":[43,135,139,154],"actionable":[44],"feedback.":[45],"Using":[46],"densely":[48],"annotated":[49],"dataset":[50],"164":[52],"hours":[53],"video":[55,77,136],"68":[57],"lesson":[58],"transcripts,":[59,84],"we":[60,67,85,110],"design":[61],"parallel,":[62],"modality-specific":[63],"pipelines.":[64],"For":[65,83],"video,":[66],"evaluate":[68],"zero-shot":[69],"LLMs,":[71],"fine-tuned":[72,124],"vision\u2013language":[73],"models,":[74],"self-supervised":[76],"transformers":[78],"24":[80],"labels.":[82,102],"fine-tune":[86],"transformer-based":[88],"classifier":[89],"with":[90],"contextualized":[91],"inputs":[92],"compare":[94],"it":[95],"against":[96],"prompting-based":[97,128],"LLMs":[98],"19":[100],"To":[103],"handle":[104],"class":[105],"imbalance":[106],"multi-label":[108],"complexity,":[109],"apply":[111],"per-label":[112],"thresholding,":[113],"context":[114],"windows,":[115],"imbalance-aware":[117],"loss":[118],"functions.":[119],"The":[120],"results":[121,142],"show":[122],"that":[123],"models":[125],"consistently":[126],"outperform":[127],"approaches,":[129],"achieving":[130],"macro-F1":[131],"scores":[132],"0.577":[134],"0.460":[138],"transcripts.":[140],"These":[141],"demonstrate":[143],"the":[144],"feasibility":[145],"automated":[147],"establish":[151],"scalable":[155],"teacher":[156],"systems.":[158]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-12-03T00:00:00"}