{"id":"https://openalex.org/W4408024239","doi":"https://doi.org/10.1145/3708568.3708586","title":"Multi-scale Spatio-temporal Feature Fusion Module Based Posture Relative Aesthetic Assessment for AI Camera","display_name":"Multi-scale Spatio-temporal Feature Fusion Module Based Posture Relative Aesthetic Assessment for AI Camera","publication_year":2024,"publication_date":"2024-11-22","ids":{"openalex":"https://openalex.org/W4408024239","doi":"https://doi.org/10.1145/3708568.3708586"},"language":"en","primary_location":{"id":"doi:10.1145/3708568.3708586","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3708568.3708586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 6th International Conference on Video, Signal 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/A5109521416","display_name":"Ying Zhou","orcid":"https://orcid.org/0000-0002-0597-4950"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhou","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, School of Information and Communication Engineering, Communication University of China, Beijing, Beijing, China,"],"raw_orcid":"https://orcid.org/0000-0002-0597-4950","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, School of Information and Communication Engineering, Communication University of China, Beijing, Beijing, China,","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103216248","display_name":"Yana Zhang","orcid":"https://orcid.org/0000-0002-9287-3639"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yana Zhang","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, School of Information and Communication Engineering, Communication University of China, Beijing, Beijing, China,"],"raw_orcid":"https://orcid.org/0000-0002-9287-3639","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, School of Information and Communication Engineering, Communication University of China, Beijing, Beijing, China,","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiang Liu","orcid":"https://orcid.org/0009-0006-8626-6353"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Liu","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, School of Information and Communication Engineering, Communication University of China, Beijing, Beijing, China,"],"raw_orcid":"https://orcid.org/0009-0006-8626-6353","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, School of Information and Communication Engineering, Communication University of China, Beijing, Beijing, China,","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":null,"display_name":"Guoting Zhang","orcid":"https://orcid.org/0009-0007-2387-6792"},"institutions":[{"id":"https://openalex.org/I4210111085","display_name":"Academy of Broadcasting Science","ror":"https://ror.org/01z4nez64","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210111085"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoting Zhang","raw_affiliation_strings":["Academy of Broadcasting Science, National Radio and Television Administration, Beijing, Beijing, China,"],"raw_orcid":"https://orcid.org/0009-0007-2387-6792","affiliations":[{"raw_affiliation_string":"Academy of Broadcasting Science, National Radio and Television Administration, Beijing, Beijing, China,","institution_ids":["https://openalex.org/I4210111085"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42706379,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"105","last_page":"111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12994","display_name":"Infrared Thermography in Medicine","score":0.9804999828338623,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T12994","display_name":"Infrared Thermography in Medicine","score":0.9804999828338623,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9775999784469604,"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/T12015","display_name":"Photoacoustic and Ultrasonic Imaging","score":0.941100001335144,"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/computer-vision","display_name":"Computer vision","score":0.709956169128418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7021176815032959},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6959607601165771},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6054111123085022},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5597500205039978},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5265265703201294},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.46164005994796753},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.44617563486099243},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.417484849691391},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.37850531935691833},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15142083168029785},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.11586648225784302},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08175700902938843}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.709956169128418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7021176815032959},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6959607601165771},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6054111123085022},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5597500205039978},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5265265703201294},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.46164005994796753},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.44617563486099243},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.417484849691391},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.37850531935691833},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15142083168029785},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.11586648225784302},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08175700902938843},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3708568.3708586","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3708568.3708586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 6th International Conference on Video, Signal and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2300846932","https://openalex.org/W2603777577","https://openalex.org/W2910206816","https://openalex.org/W2963163009","https://openalex.org/W3081377345","https://openalex.org/W4210814507","https://openalex.org/W4285606417","https://openalex.org/W4309713922","https://openalex.org/W4362471799","https://openalex.org/W4385444101","https://openalex.org/W4386065622","https://openalex.org/W4390576755","https://openalex.org/W6688890991"],"related_works":["https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W3214791684","https://openalex.org/W3152170969","https://openalex.org/W2379054866","https://openalex.org/W2370195708","https://openalex.org/W1490651872","https://openalex.org/W2139242969"],"abstract_inverted_index":{"Photography":[0],"is":[1,42,59,75,90],"the":[2,21,49,63,72,107,119,137,149,159],"art":[3],"of":[4,48,66,139,155,161],"creating":[5],"durable":[6],"images":[7],"by":[8],"capturing":[9],"and":[10,84,118,129],"recording":[11],"light.":[12],"AI":[13],"cameras":[14],"incorporate":[15],"artificial":[16],"intelligence":[17],"technology":[18],"to":[19,38,44,51,61,113,125],"enhance":[20],"imaging":[22],"functionality.":[23],"The":[24,56,144],"existing":[25],"research":[26],"has":[27],"realized":[28],"\u201csmile":[29],"capture\u201d":[30],"based":[31,100],"on":[32,101],"facial":[33],"smile":[34],"detection.":[35],"When":[36],"turning":[37],"full":[39],"shots,":[40],"it":[41],"necessary":[43],"analyze":[45],"all":[46],"movements":[47,141],"subject":[50],"capture":[52],"a":[53,78,96],"beautiful":[54,79,97],"posture.":[55,68,163],"primary":[57],"problem":[58],"how":[60],"define":[62],"aesthetic":[64,87,103],"standard":[65],"human":[67,162],"In":[69],"this":[70,93],"paper,":[71],"stage":[73],"pose":[74,88],"defined":[76],"as":[77],"posture":[80],"in":[81,105,133,142,157],"performance":[82],"videos,":[83,134],"then":[85],"an":[86,153],"dataset":[89],"built.":[91],"Secondly,":[92],"paper":[94],"proposed":[95,150],"posture-determining":[98],"model":[99,151],"relative":[102],"assessment,":[104],"which":[106],"multi-scale":[108,120],"spatial":[109],"features":[110,122],"are":[111,123],"extracted":[112],"learn":[114],"fine-grained":[115],"global":[116],"information,":[117],"temporal":[121],"combined":[124],"perceive":[126],"both":[127],"short-term":[128],"long-term":[130],"motion":[131],"information":[132],"thereby":[135],"enhancing":[136],"learning":[138],"fine":[140],"videos.":[143],"experimental":[145],"results":[146],"show":[147],"that":[148],"reaches":[152],"accuracy":[154],"80.79%":[156],"judging":[158],"beauty":[160]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
