{"id":"https://openalex.org/W7140368990","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443703","title":"Multi-Modal Transformer Network for Classroom Instruction Analysis","display_name":"Multi-Modal Transformer Network for Classroom Instruction Analysis","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W7140368990","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443703"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf67917.2025.11443703","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf67917.2025.11443703","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"Asilomar Conference on Signals, Systems and Computers (ACSSC)","issn_l":"1058-6393","issn":["1058-6393","2576-2303"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5041300663","display_name":"Matthew Korban","orcid":"https://orcid.org/0009-0008-4610-9390","observed_orcids":["https://orcid.org/0009-0008-4610-9390"]},"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":"Matthew Korban","raw_affiliation_strings":["University of Virginia,C.L. Brown Dept. of Electrical and Computer Engineering,Charlottesville,Virginia,22903"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,C.L. Brown Dept. of Electrical and Computer Engineering,Charlottesville,Virginia,22903","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032685001","display_name":"Chongyu He","orcid":null,"observed_orcids":[]},"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":"Chongyu He","raw_affiliation_strings":["University of Virginia,C.L. Brown Dept. of Electrical and Computer Engineering,Charlottesville,Virginia,22903"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,C.L. Brown Dept. of Electrical and Computer Engineering,Charlottesville,Virginia,22903","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081562360","display_name":"Peter A. Youngs","orcid":"https://orcid.org/0000-0002-1711-1749","observed_orcids":["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,Department of Curriculum, Instruction, and Special Education,Charlottesville,Virginia,22903"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,Department of Curriculum, Instruction, and Special Education,Charlottesville,Virginia,22903","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034452294","display_name":"Scott T. Acton","orcid":"https://orcid.org/0000-0003-3288-1255","observed_orcids":["https://orcid.org/0000-0003-3288-1255"]},"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":"Scott T. Acton","raw_affiliation_strings":["University of Virginia,C.L. Brown Dept. of Electrical and Computer Engineering,Charlottesville,Virginia,22903"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,C.L. Brown Dept. of Electrical and Computer Engineering,Charlottesville,Virginia,22903","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"969","last_page":"973"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3589000105857849,"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":0.3589000105857849,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.22169999778270721,"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/T11122","display_name":"Online Learning and Analytics","score":0.16750000417232513,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/multimodal-transformer","display_name":"multimodal transformer","score":0.9620000123977661},{"id":"https://openalex.org/keywords/background-suppression","display_name":"background suppression","score":0.6600000262260437},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.6269999742507935},{"id":"https://openalex.org/keywords/cross-modal-attention","display_name":"cross-modal attention","score":0.625},{"id":"https://openalex.org/keywords/k-12-classrooms","display_name":"K-12 classrooms","score":0.875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6047999858856201},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47600001096725464},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3043000102043152},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C32946077","wikidata":"https://www.wikidata.org/wiki/Q618079","display_name":"Network analysis","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2533999979496002},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.22390000522136688},{"id":"https://openalex.org/C88610354","wikidata":"https://www.wikidata.org/wiki/Q1813494","display_name":"Teaching method","level":2,"score":0.21549999713897705},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.21539999544620514},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2142000049352646}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf67917.2025.11443703","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf67917.2025.11443703","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"Asilomar Conference on Signals, Systems and Computers (ACSSC)","issn_l":"1058-6393","issn":["1058-6393","2576-2303"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.975600004196167}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2619082050","https://openalex.org/W2947476638","https://openalex.org/W2981851019","https://openalex.org/W2998702159","https://openalex.org/W4383219146","https://openalex.org/W4390950161","https://openalex.org/W4392827338","https://openalex.org/W4396215601","https://openalex.org/W4405429434","https://openalex.org/W4409423766","https://openalex.org/W4416310693"],"related_works":["https://openalex.org/W4416183368","https://openalex.org/W4416932168","https://openalex.org/W4396215601","https://openalex.org/W4417319679","https://openalex.org/W7208782854","https://openalex.org/W7166296438","https://openalex.org/W2941741019","https://openalex.org/W2982303227","https://openalex.org/W7160545478","https://openalex.org/W4390950161"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,12,19,31,69],"multimodal":[3,94],"transformer":[4,33],"for":[5,96],"automatic":[6],"classroom":[7,49],"activity":[8,27],"recognition":[9,86],"that":[10,80],"combines":[11],"background-suppressed":[13],"Vision":[14],"Transformer":[15],"video":[16,36,50,85,98],"model":[17],"with":[18],"BERT-based":[20],"transcript":[21,40,81],"encoder.":[22],"Each":[23],"modality":[24],"first":[25],"predicts":[26],"labels":[28],"independently,":[29],"and":[30,51,63,66,75],"cross-modal":[32,76],"then":[34],"refines":[35],"predictions":[37],"using":[38],"aligned":[39],"cues.":[41],"Evaluated":[42],"on":[43],"50":[44],"hours":[45],"of":[46,93],"real-world":[47],"K\u201312":[48],"audio,":[52],"our":[53],"framework":[54],"accurately":[55],"classifies":[56],"activities":[57],"such":[58],"as":[59],"lecture,":[60],"individual":[61],"work,":[62,65],"group":[64],"consistently":[67],"outperforms":[68],"strong":[70],"video-only":[71],"baseline.":[72],"Per-frame":[73],"F1":[74],"correlation":[77],"analyses":[78],"demonstrate":[79],"signals":[82],"substantially":[83],"boost":[84],"in":[87],"authentic":[88],"classrooms,":[89],"highlighting":[90],"the":[91],"value":[92],"context":[95],"educational":[97],"analytics.":[99]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-27T00:00:00"}
