{"id":"https://openalex.org/W3015326490","doi":"https://doi.org/10.1109/icassp40776.2020.9054407","title":"Multimodal Learning for Classroom Activity Detection","display_name":"Multimodal Learning for Classroom Activity Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015326490","doi":"https://doi.org/10.1109/icassp40776.2020.9054407","mag":"3015326490"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5100455135","display_name":"Hang Li","orcid":"https://orcid.org/0000-0002-3464-3245"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hang Li","raw_affiliation_strings":["TAL AI Lab, TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL AI Lab, TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110921685","display_name":"Yu Kang","orcid":"https://orcid.org/0000-0001-5196-0376"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Kang","raw_affiliation_strings":["TAL AI Lab, TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL AI Lab, TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061403523","display_name":"Wenbiao Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenbiao Ding","raw_affiliation_strings":["TAL AI Lab, TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL AI Lab, TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051317379","display_name":"Song Yang","orcid":"https://orcid.org/0000-0002-5385-1402"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Yang","raw_affiliation_strings":["TAL AI Lab, TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL AI Lab, TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101085314","display_name":"Songfan Yang","orcid":"https://orcid.org/0000-0002-3560-3624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songfan Yang","raw_affiliation_strings":["TAL AI Lab, TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL AI Lab, TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087905718","display_name":"Gale Yan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gale Yan Huang","raw_affiliation_strings":["TAL AI Lab, TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL AI Lab, TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014957271","display_name":"Zitao Liu","orcid":"https://orcid.org/0000-0003-0491-307X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zitao Liu","raw_affiliation_strings":["TAL AI Lab, TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL AI Lab, TAL Education Group, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100455135"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5071,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.95445428,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9234","last_page":"9238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9708999991416931,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9708999991416931,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9624000191688538,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9068999886512756,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6926299929618835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4165140986442566},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4134286046028137},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3411770462989807}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6926299929618835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4165140986442566},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4134286046028137},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3411770462989807}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W205886031","https://openalex.org/W1614298861","https://openalex.org/W1940872118","https://openalex.org/W1967503395","https://openalex.org/W2075997786","https://openalex.org/W2114509888","https://openalex.org/W2114925438","https://openalex.org/W2194775991","https://openalex.org/W2294813873","https://openalex.org/W2470765286","https://openalex.org/W2548272333","https://openalex.org/W2561127898","https://openalex.org/W2592667291","https://openalex.org/W2766191375","https://openalex.org/W2807708692","https://openalex.org/W2896538040","https://openalex.org/W2936252425","https://openalex.org/W2949636940","https://openalex.org/W2950577311","https://openalex.org/W2953008521","https://openalex.org/W2962788625","https://openalex.org/W2962959915","https://openalex.org/W2963403868","https://openalex.org/W2963470929","https://openalex.org/W3088852397","https://openalex.org/W3098374202","https://openalex.org/W4385245566","https://openalex.org/W6608354690","https://openalex.org/W6636510571","https://openalex.org/W6640362995","https://openalex.org/W6731026589","https://openalex.org/W6739901393","https://openalex.org/W6745415975","https://openalex.org/W6752099543","https://openalex.org/W6783568549","https://openalex.org/W6948532607"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Classroom":[0],"activity":[1],"detection":[2],"(CAD)":[3],"focuses":[4],"on":[5,34,97,171],"accurately":[6],"classifying":[7],"whether":[8],"the":[9,18,57,92,106,166],"teacher":[10],"or":[11],"student":[12],"is":[13,52,138,141,155,187],"speaking":[14],"and":[15,44,69,76,90,124,140,183],"recording":[16,99,147],"both":[17,74,122],"length":[19],"of":[20,168,195],"individual":[21],"utterances":[22],"during":[23],"a":[24,111],"class.":[25],"A":[26],"CAD":[27,51,58,152],"solution":[28,93],"helps":[29],"teachers":[30,68],"get":[31],"instant":[32],"feedback":[33],"their":[35],"pedagogical":[36],"instructions.":[37],"This":[38],"greatly":[39],"improves":[40],"educators\u2019":[41],"teaching":[42],"skills":[43],"hence":[45],"leads":[46],"to":[47,61,80,131,143,189],"students\u2019":[48],"achievement.":[49],"However,":[50],"very":[53],"challenging":[54],"because":[55],"(1)":[56],"model":[59],"needs":[60],"be":[62,81,88],"generalized":[63],"well":[64],"enough":[65],"for":[66],"different":[67,181],"students;":[70],"(2)":[71],"data":[72,179],"from":[73,177],"vocal":[75],"language":[77,125],"modalities":[78],"has":[79],"wisely":[82],"fused":[83],"so":[84],"that":[85],"they":[86],"can":[87],"complementary;":[89],"(3)":[91],"shouldn\u2019t":[94],"heavily":[95],"rely":[96],"additional":[98],"device.":[100],"In":[101],"this":[102],"paper,":[103],"we":[104],"address":[105],"above":[107],"challenges":[108],"by":[109],"using":[110],"novel":[112],"attention":[113,129,173],"based":[114,174],"neural":[115,175],"framework.":[116],"Our":[117,136],"framework":[118,137,154],"not":[119],"only":[120],"extracts":[121],"speech":[123],"information,":[126],"but":[127],"utilizes":[128],"mechanism":[130],"capture":[132],"long-term":[133],"semantic":[134],"dependence.":[135],"device-free":[139],"able":[142,188],"take":[144],"any":[145],"classroom":[146,178],"as":[148],"input.":[149],"The":[150,162],"proposed":[151],"learning":[153,172],"evaluated":[156],"in":[157,193],"two":[158],"real-world":[159],"education":[160],"applications.":[161],"experimental":[163],"results":[164],"demonstrate":[165],"benefits":[167],"our":[169,185],"approach":[170,186],"network":[176],"with":[180],"modalities,":[182],"show":[184],"outperform":[190],"state-of-the-art":[191],"baselines":[192],"terms":[194],"various":[196],"evaluation":[197],"metrics.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":11}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}