{"id":"https://openalex.org/W4386072496","doi":"https://doi.org/10.23919/mva57639.2023.10216167","title":"Hierarchical Spatio-Temporal Neural Network with Displacement Based Refinement for Monocular Head Pose Prediction","display_name":"Hierarchical Spatio-Temporal Neural Network with Displacement Based Refinement for Monocular Head Pose Prediction","publication_year":2023,"publication_date":"2023-07-23","ids":{"openalex":"https://openalex.org/W4386072496","doi":"https://doi.org/10.23919/mva57639.2023.10216167"},"language":"en","primary_location":{"id":"doi:10.23919/mva57639.2023.10216167","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/mva57639.2023.10216167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 18th International Conference on Machine Vision and Applications (MVA)","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/A5047557442","display_name":"Zhe Xu","orcid":"https://orcid.org/0000-0002-3921-7499"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Zhe Xu","raw_affiliation_strings":["Waseda University,Graduate School of Information, Production and Systems,Kitakyushu,Japan,808-0135"],"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of Information, Production and Systems,Kitakyushu,Japan,808-0135","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409808","display_name":"Yuan Li","orcid":"https://orcid.org/0000-0002-4462-6764"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuan Li","raw_affiliation_strings":["Waseda University,Graduate School of Information, Production and Systems,Kitakyushu,Japan,808-0135"],"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of Information, Production and Systems,Kitakyushu,Japan,808-0135","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341175","display_name":"Yuhong Li","orcid":"https://orcid.org/0009-0002-2866-774X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuhong Li","raw_affiliation_strings":["Waseda University,Graduate School of Information, Production and Systems,Kitakyushu,Japan,808-0135"],"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of Information, Production and Systems,Kitakyushu,Japan,808-0135","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033755910","display_name":"\u0421\u043e\u043d\u0433\u043b\u0438\u043d \u0414\u0443","orcid":"https://orcid.org/0000-0003-4937-2713"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songlin Du","raw_affiliation_strings":["Southeast University,Nanjing,China","Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Southeast University,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103206427","display_name":"Takeshi Ikenaga","orcid":"https://orcid.org/0000-0001-8338-8175"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Ikenaga","raw_affiliation_strings":["Waseda University,Graduate School of Information, Production and Systems,Kitakyushu,Japan,808-0135"],"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of Information, Production and Systems,Kitakyushu,Japan,808-0135","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047557442"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11448","display_name":"Face recognition and analysis","score":0.9998000264167786,"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/T11448","display_name":"Face recognition and analysis","score":0.9998000264167786,"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":0.9969000220298767,"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/T12290","display_name":"Human Motion and Animation","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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-science","display_name":"Computer science","score":0.8047146797180176},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6788303256034851},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.6751468181610107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6457432508468628},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5654102563858032},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5180561542510986},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.46920982003211975},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42743757367134094},{"id":"https://openalex.org/keywords/displacement","display_name":"Displacement (psychology)","score":0.4253042936325073},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37972313165664673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047146797180176},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6788303256034851},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.6751468181610107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6457432508468628},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5654102563858032},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5180561542510986},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.46920982003211975},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42743757367134094},{"id":"https://openalex.org/C107551265","wikidata":"https://www.wikidata.org/wiki/Q1458245","display_name":"Displacement (psychology)","level":2,"score":0.4253042936325073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37972313165664673},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/mva57639.2023.10216167","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/mva57639.2023.10216167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 18th International Conference on Machine Vision and Applications (MVA)","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":22,"referenced_works":["https://openalex.org/W572790999","https://openalex.org/W2039239232","https://openalex.org/W2047875689","https://openalex.org/W2139540805","https://openalex.org/W2153000018","https://openalex.org/W2294280715","https://openalex.org/W2957744218","https://openalex.org/W2963644257","https://openalex.org/W2964014798","https://openalex.org/W3009774321","https://openalex.org/W3080348805","https://openalex.org/W3109717189","https://openalex.org/W3128640141","https://openalex.org/W3183842024","https://openalex.org/W4220908650","https://openalex.org/W4221142137","https://openalex.org/W4304080460","https://openalex.org/W4312249545","https://openalex.org/W4327661965","https://openalex.org/W6682525577","https://openalex.org/W6745339246","https://openalex.org/W6781317771"],"related_works":["https://openalex.org/W2123263858","https://openalex.org/W3127959533","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4387967917","https://openalex.org/W200819717","https://openalex.org/W2392165555","https://openalex.org/W4307623796","https://openalex.org/W4394784820"],"abstract_inverted_index":{"Head":[0],"pose":[1,8,36],"prediction":[2,120],"aims":[3],"to":[4,43,48,90,113,117,147],"forecast":[5],"future":[6],"head":[7,35],"given":[9],"observed":[10],"sequence,":[11],"which":[12],"plays":[13],"an":[14,115],"increasingly":[15],"important":[16],"role":[17],"in":[18],"human":[19],"computer":[20],"interaction,":[21],"virtual":[22],"reality,":[23],"and":[24,71,86,138,175],"driver":[25],"monitoring.":[26],"However,":[27],"since":[28],"there":[29],"are":[30],"many":[31],"moving":[32],"possibilities,":[33],"current":[34],"works,":[37],"mainly":[38],"focusing":[39],"on":[40,134,171,177],"estimation,":[41],"fail":[42],"provide":[44],"sufficient":[45],"temporal":[46,87],"information":[47,83,88,104,136,143],"meet":[49],"the":[50,91,119,123,135,149,157],"high":[51],"demands":[52],"for":[53],"accurate":[54],"predictions.":[55],"This":[56],"paper":[57],"proposes":[58],"(A)":[59],"a":[60,65,73,106,164],"Spatio-Temporal":[61],"Encoder":[62],"(STE),":[63],"(B)":[64],"displacement":[66,97,103],"based":[67,98,133],"offset":[68,99,116],"generating":[69,100],"module,":[70],"(C)":[72],"time":[74,92,124,130],"step":[75,125,131],"feature":[76,126],"aggregation":[77,127],"module.":[78],"The":[79,96],"STE":[80],"extracts":[81,140],"spatial":[82],"via":[84],"Transformer":[85],"according":[89],"order":[93],"of":[94,169],"frames.":[95],"module":[101,128],"utilizes":[102],"through":[105],"frequency":[107],"domain":[108],"process":[109],"between":[110],"adjacent":[111],"frames":[112],"generate":[114],"refine":[118],"result.":[121],"Furthermore,":[122],"integrates":[129],"features":[132],"density":[137],"hierarchically":[139],"past":[141],"motion":[142,150],"as":[144],"prior":[145],"knowledge":[146],"capture":[148],"recurrence.":[151],"Extensive":[152],"experiments":[153],"have":[154],"shown":[155],"that":[156],"proposed":[158],"network":[159],"outperforms":[160],"related":[161],"methods,":[162],"achieving":[163],"Mean":[165],"Absolute":[166],"Error":[167],"(MAE)":[168],"4.5865\u00b0":[170],"simple":[172],"background":[173,179],"sequences":[174],"7.1325\u00b0":[176],"complex":[178],"sequences.":[180]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}