{"id":"https://openalex.org/W4408354718","doi":"https://doi.org/10.1109/icassp49660.2025.10887954","title":"Enhancing Teacher Classroom Behavior Descriptions: A Spatio-Temporal Graph-Based Method for Video Captioning","display_name":"Enhancing Teacher Classroom Behavior Descriptions: A Spatio-Temporal Graph-Based Method for Video Captioning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354718","doi":"https://doi.org/10.1109/icassp49660.2025.10887954"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100730776","display_name":"Ting Cai","orcid":"https://orcid.org/0000-0001-5926-9280"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Cai","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,Research Center for Artificial Intelligence and Smart Education,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,Research Center for Artificial Intelligence and Smart Education,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101254657","display_name":"Chengyang He","orcid":"https://orcid.org/0009-0001-8188-3516"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ChengYang He","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,Research Center for Artificial Intelligence and Smart Education,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,Research Center for Artificial Intelligence and Smart Education,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100928953","display_name":"Yu Xiong","orcid":"https://orcid.org/0000-0001-7879-3651"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Xiong","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,Research Center for Artificial Intelligence and Smart Education,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,Research Center for Artificial Intelligence and Smart Education,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I10535382"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.996399998664856,"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/T11439","display_name":"Video Analysis and Summarization","score":0.996399998664856,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9958000183105469,"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":0.9886999726295471,"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/closed-captioning","display_name":"Closed captioning","score":0.9311941266059875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7829203009605408},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5485886931419373},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4684455692768097},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3308091163635254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.330124169588089},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1834683120250702},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07272949814796448}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9311941266059875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829203009605408},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5485886931419373},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4684455692768097},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3308091163635254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.330124169588089},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1834683120250702},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07272949814796448}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2075545476","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2425121537","https://openalex.org/W2557264465","https://openalex.org/W2953461088","https://openalex.org/W2963150697","https://openalex.org/W2963524571","https://openalex.org/W2972281329","https://openalex.org/W3019301826","https://openalex.org/W3034221024","https://openalex.org/W3035365026","https://openalex.org/W3192261211","https://openalex.org/W3216659302","https://openalex.org/W4214692497","https://openalex.org/W4296899965","https://openalex.org/W4308217050","https://openalex.org/W4312535570","https://openalex.org/W4324334062","https://openalex.org/W4379375132","https://openalex.org/W4390874374","https://openalex.org/W6684090549"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Teacher":[0],"behavior":[1,30,36,67,115],"description":[2,37,116],"is":[3,38],"an":[4],"objective":[5],"record":[6],"of":[7,48,65,99,129],"teachers\u2019":[8],"behaviors":[9],"in":[10,68,87],"the":[11,46,52,62,88,96,112,127],"teaching":[12,21],"process,":[13],"aiming":[14],"to":[15,41,45],"provide":[16],"evidence":[17],"for":[18],"reflection":[19],"on":[20,34,110],"behavior.":[22],"Although":[23],"video":[24,56],"captioning":[25,57],"technology":[26],"can":[27],"automatically":[28],"generate":[29],"description,":[31],"existing":[32,55],"research":[33],"teacher":[35,66,114],"mostly":[39],"limited":[40],"case":[42],"studies":[43],"due":[44],"lack":[47],"relevant":[49],"datasets.":[50],"At":[51],"same":[53],"time,":[54],"methods":[58],"cannot":[59],"effectively":[60],"capture":[61],"dynamic":[63],"characteristics":[64],"real":[69],"classrooms.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"propose":[75],"a":[76],"novel":[77],"spatio-temporal":[78],"graph":[79],"neural":[80],"network":[81],"(STGN),":[82],"which":[83],"represents":[84],"teacher-student":[85],"interactions":[86],"spatial":[89],"domain":[90],"using":[91],"action":[92],"features":[93],"and":[94,119,124],"models":[95],"temporal":[97],"relationships":[98],"teachers":[100],"guided":[101],"by":[102],"contextual":[103],"information.":[104],"The":[105],"model":[106],"achieves":[107],"satisfactory":[108],"results":[109],"both":[111],"proprietary":[113],"(TBD)":[117],"dataset":[118],"two":[120],"public":[121],"datasets,":[122],"MSR-VTT":[123],"MSVD,":[125],"demonstrating":[126],"effectiveness":[128],"our":[130],"approach.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
