{"id":"https://openalex.org/W3023694819","doi":"https://doi.org/10.1145/3293353.3293398","title":"Dynamic Gesture Recognition with Pose-based CNN Features derived from videos using LSTM","display_name":"Dynamic Gesture Recognition with Pose-based CNN Features derived from videos using LSTM","publication_year":2018,"publication_date":"2018-12-18","ids":{"openalex":"https://openalex.org/W3023694819","doi":"https://doi.org/10.1145/3293353.3293398","mag":"3023694819"},"language":"en","primary_location":{"id":"doi:10.1145/3293353.3293398","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293353.3293398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing","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/A5020292736","display_name":"Kankana Roy","orcid":"https://orcid.org/0000-0003-1296-7748"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kankana Roy","raw_affiliation_strings":["Computational Vision Laboratory, Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Vision Laboratory, Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067927122","display_name":"Rajiv R. Sahay","orcid":"https://orcid.org/0000-0003-0820-0616"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajiv R. Sahay","raw_affiliation_strings":["Computational Vision Laboratory, Department of Electrical Engineering, Indian Institute of Technology Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Vision Laboratory, Department of Electrical Engineering, Indian Institute of Technology Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.2717553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":1.0,"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":1.0,"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":0.9995999932289124,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.8451051115989685},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8421285152435303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.765153706073761},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7585293054580688},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.7218592166900635},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.6847436428070068},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.6472815275192261},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5991789102554321},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.511139452457428},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4384578466415405},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.29990893602371216}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8451051115989685},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8421285152435303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.765153706073761},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7585293054580688},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.7218592166900635},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.6847436428070068},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.6472815275192261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5991789102554321},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.511139452457428},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4384578466415405},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29990893602371216},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3293353.3293398","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293353.3293398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1993014362","https://openalex.org/W1993666393","https://openalex.org/W1997025120","https://openalex.org/W2064675550","https://openalex.org/W2072419079","https://openalex.org/W2117539524","https://openalex.org/W2131747574","https://openalex.org/W2163605009","https://openalex.org/W2186222003","https://openalex.org/W2235034809","https://openalex.org/W2295038166","https://openalex.org/W2325939864","https://openalex.org/W2412782625","https://openalex.org/W2526468814","https://openalex.org/W2532999551","https://openalex.org/W2595328592","https://openalex.org/W2623012778","https://openalex.org/W2770472008","https://openalex.org/W2798498022","https://openalex.org/W2963192057","https://openalex.org/W2964184470","https://openalex.org/W2997426117","https://openalex.org/W3100876745","https://openalex.org/W4242177601","https://openalex.org/W4308222375"],"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":{"In":[0],"this":[1],"work,":[2],"we":[3],"address":[4],"the":[5,111],"problem":[6],"of":[7,110,117],"dynamic":[8,61,92],"gesture":[9,62,98,105],"recognition":[10],"using":[11,76,122],"a":[12,35,43],"pose":[13],"based":[14],"video":[15,23,77],"descriptor.":[16],"The":[17],"proposed":[18,112],"approach":[19],"takes":[20],"as":[21],"input":[22],"frames":[24,80],"and":[25,81,102,119],"extracts":[26],"pose-specific":[27],"image":[28],"regions":[29],"which":[30],"are":[31],"further":[32],"processed":[33],"by":[34,64],"pre-trained":[36],"Convolutional":[37],"Neural":[38],"Network":[39],"(CNN)":[40],"to":[41],"derive":[42],"pose-based":[44],"descriptor":[45],"for":[46,60,90,108],"each":[47],"frame.":[48],"A":[49],"Long":[50],"Short":[51],"Term":[52],"Memory":[53],"(LSTM)":[54],"network":[55],"is":[56],"trained":[57],"from":[58],"scratch":[59],"classification":[63],"learning":[65],"long-term":[66],"spatiotemporal":[67],"relations":[68],"among":[69],"features.":[70],"We":[71,94],"also":[72],"demonstrate":[73],"that":[74],"only":[75,123],"data":[78],"(RGB":[79],"optical":[82],"flow)":[83],"one":[84],"can":[85],"design":[86],"an":[87,115],"effective":[88],"model":[89],"recognizing":[91],"gestures.":[93],"utilize":[95],"ChaLearn":[96],"multi-modal":[97],"challenge":[99],"dataset":[100,106],"[13]":[101],"Cambridge":[103],"hand":[104],"[18]":[107],"evaluation":[109],"algorithm":[113],"achieving":[114],"accuracy":[116],"91.27%":[118],"96%":[120],"respectively":[121],"RGB":[124],"data.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}