{"id":"https://openalex.org/W3035398717","doi":"https://doi.org/10.24963/ijcai.2020/95","title":"GestureDet: Real-time Student Gesture Analysis with Multi-dimensional Attention-based Detector","display_name":"GestureDet: Real-time Student Gesture Analysis with Multi-dimensional Attention-based Detector","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3035398717","doi":"https://doi.org/10.24963/ijcai.2020/95","mag":"3035398717"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/95","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/95","pdf_url":"https://www.ijcai.org/proceedings/2020/0095.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0095.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041006174","display_name":"Rui Zheng","orcid":"https://orcid.org/0000-0003-0391-2454"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University","Department of Computer Science and Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086524943","display_name":"Fei Jiang","orcid":"https://orcid.org/0000-0002-7685-0242"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Jiang","raw_affiliation_strings":["Shanghai Jiao Tong University","Department of Computer Science and Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108479221","display_name":"Ruimin Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruimin Shen","raw_affiliation_strings":["Shanghai Jiao Tong University","Department of Computer Science and Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"680","last_page":"686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9937999844551086,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/computer-science","display_name":"Computer science","score":0.8072071075439453},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.7441767454147339},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7104564905166626},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.6182795166969299},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5720899701118469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5579826831817627},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5142030715942383},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.45946407318115234},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.45294755697250366},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42387112975120544},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3916824460029602}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072071075439453},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7441767454147339},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7104564905166626},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.6182795166969299},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5720899701118469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5579826831817627},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5142030715942383},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.45946407318115234},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.45294755697250366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42387112975120544},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3916824460029602},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/95","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/95","pdf_url":"https://www.ijcai.org/proceedings/2020/0095.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/95","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/95","pdf_url":"https://www.ijcai.org/proceedings/2020/0095.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G6290008150","display_name":null,"funder_award_id":"2018M642019","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G8562762075","display_name":null,"funder_award_id":"61671290","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"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3035398717.pdf","grobid_xml":"https://content.openalex.org/works/W3035398717.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2102605133","https://openalex.org/W2570343428","https://openalex.org/W2612445135","https://openalex.org/W2630837129","https://openalex.org/W2883208628","https://openalex.org/W2884561390","https://openalex.org/W2924139770","https://openalex.org/W2938271999","https://openalex.org/W2963037989","https://openalex.org/W2963163009","https://openalex.org/W2963342610","https://openalex.org/W2963403868","https://openalex.org/W2963495494","https://openalex.org/W2963516811","https://openalex.org/W2964632911","https://openalex.org/W3106250896","https://openalex.org/W4297775537","https://openalex.org/W4309845474","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2066003895","https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2026258298","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W2805039731","https://openalex.org/W2989699735"],"abstract_inverted_index":{"Students\u2019":[0],"gestures,":[1],"hand-raising,":[2],"stand-up,":[3],"and":[4,13,20,36,95,120,144,150,160,185,198],"sleeping,":[5],"indicates":[6],"the":[7,52,77,106,109,126,130,153,157,168,183],"engagement":[8],"of":[9,26,54,108,187],"students":[10],"in":[11,34],"classrooms":[12],"partially":[14],"reflects":[15],"teaching":[16],"quality.":[17],"Therefore,":[18],"fast":[19],"automatically":[21],"recognizing":[22],"these":[23],"gestures":[24],"are":[25,123],"great":[27],"importance.":[28],"Due":[29],"to":[30,50,65,113,117,140,163],"limited":[31],"computational":[32],"resources":[33],"primary":[35],"secondary":[37],"schools,":[38],"we":[39,57,75,85],"propose":[40],"a":[41,59,73,87,142,175],"real-time":[42,94],"student":[43,195],"behavior":[44,68,196],"detector":[45],"based":[46],"on":[47,71,165,193,200,207],"light-weight":[48],"MobileNetV2-SSD":[49],"reduce":[51],"dependency":[53],"GPUs.":[55],"Firstly,":[56],"build":[58],"large-scale":[60],"corpus":[61],"from":[62],"real":[63,194],"schools":[64],"capture":[66],"various":[67],"gestures.":[69],"Based":[70],"such":[72],"corpus,":[74],"transfer":[76],"gesture":[78,97],"recognition":[79],"task":[80],"into":[81],"object":[82],"detections.":[83],"Secondly,":[84],"design":[86],"multi-dimensional":[88,100],"attention-based":[89],"detector,":[90],"named":[91],"GestureDet,":[92,188],"for":[93,125,147],"accurate":[96],"analysis.":[98],"The":[99],"attention":[101,116,132,155,170],"mechanisms":[102],"simultaneously":[103],"consider":[104],"all":[105],"dimensions":[107],"training":[110],"set,":[111],"aiming":[112],"pay":[114],"more":[115],"discriminative":[118,166],"features":[119],"samples":[121,173],"that":[122],"important":[124,172],"final":[127],"performance.":[128],"Specifically,":[129],"spatial":[131],"is":[133],"constructed":[134],"with":[135,174],"stacked":[136],"dilated":[137],"convolution":[138],"layers":[139],"generate":[141],"soft":[143],"learnable":[145],"mask":[146],"re-weighting":[148],"foreground":[149],"background":[151],"features;":[152,167],"channel":[154],"introduces":[156],"context":[158],"modeling":[159],"squeeze-and-excitation":[161],"module":[162],"focus":[164],"batch":[169],"discriminates":[171],"new":[176],"designed":[177],"reweight":[178],"strategy.":[179],"Experimental":[180],"results":[181],"demonstrate":[182],"effectiveness":[184],"versatility":[186],"which":[189],"achieves":[190],"75.2%":[191],"mAP":[192],"dataset,":[197],"74.5%":[199],"public":[201],"PASCAL":[202],"VOC":[203],"dataset":[204],"at":[205],"20fps":[206],"embedding":[208],"device":[209],"Nvidia":[210],"Jetson":[211],"TX2.":[212],"Code":[213],"will":[214],"be":[215],"made":[216],"publicly":[217],"available.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}