{"id":"https://openalex.org/W4321020751","doi":"https://doi.org/10.1109/fg57933.2023.10042731","title":"Video Inference for Human Mesh Recovery with Vision Transformer","display_name":"Video Inference for Human Mesh Recovery with Vision Transformer","publication_year":2023,"publication_date":"2023-01-05","ids":{"openalex":"https://openalex.org/W4321020751","doi":"https://doi.org/10.1109/fg57933.2023.10042731"},"language":"en","primary_location":{"id":"doi:10.1109/fg57933.2023.10042731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg57933.2023.10042731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)","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/A5053657112","display_name":"Hanbyel Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hanbyel Cho","raw_affiliation_strings":["School of Electrical Engineering, KAIST,South Korea","School of Electrical Engineering, KAIST, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081141535","display_name":"Jaesung Ahn","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I3130020584","display_name":"International Graduate School of English","ror":"https://ror.org/0181xpd52","country_code":"KR","type":"education","lineage":["https://openalex.org/I3130020584"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaesung Ahn","raw_affiliation_strings":["Kim Jaechul Graduate School of AI, KAIST,South Korea","Kim Jaechul Graduate School of AI, KAIST, South Korea"],"affiliations":[{"raw_affiliation_string":"Kim Jaechul Graduate School of AI, KAIST,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Kim Jaechul Graduate School of AI, KAIST, South Korea","institution_ids":["https://openalex.org/I3130020584","https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033296849","display_name":"Yooshin Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yooshin Cho","raw_affiliation_strings":["School of Electrical Engineering, KAIST,South Korea","School of Electrical Engineering, KAIST, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100606266","display_name":"Junmo Kim","orcid":"https://orcid.org/0000-0002-7174-7932"},"institutions":[{"id":"https://openalex.org/I3130020584","display_name":"International Graduate School of English","ror":"https://ror.org/0181xpd52","country_code":"KR","type":"education","lineage":["https://openalex.org/I3130020584"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junmo Kim","raw_affiliation_strings":["School of Electrical Engineering, KAIST,South Korea","School of Electrical Engineering, KAIST, South Korea","Kim Jaechul Graduate School of AI, KAIST, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Kim Jaechul Graduate School of AI, KAIST, South Korea","institution_ids":["https://openalex.org/I3130020584","https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053657112"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.7379,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71343929,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11227","display_name":"Diabetic Foot Ulcer Assessment and Management","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/kinematics","display_name":"Kinematics","score":0.7444010972976685},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.717888593673706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6793268322944641},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6252354383468628},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6046841144561768},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5965681076049805},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5615707635879517},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5555906295776367},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4638208746910095},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4346122145652771},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0873805582523346}],"concepts":[{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.7444010972976685},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717888593673706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6793268322944641},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6252354383468628},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6046841144561768},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5965681076049805},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5615707635879517},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5555906295776367},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4638208746910095},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4346122145652771},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0873805582523346},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg57933.2023.10042731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg57933.2023.10042731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2101032778","https://openalex.org/W2137591992","https://openalex.org/W2194775991","https://openalex.org/W2483862638","https://openalex.org/W2554247908","https://openalex.org/W2559085405","https://openalex.org/W2612690371","https://openalex.org/W2612706635","https://openalex.org/W2797184202","https://openalex.org/W2797515701","https://openalex.org/W2895748257","https://openalex.org/W2950635152","https://openalex.org/W2962754033","https://openalex.org/W2962896489","https://openalex.org/W2963907666","https://openalex.org/W2963995996","https://openalex.org/W2964084369","https://openalex.org/W2964318832","https://openalex.org/W2971856312","https://openalex.org/W2972662547","https://openalex.org/W2975420824","https://openalex.org/W2978956737","https://openalex.org/W2981514602","https://openalex.org/W2981637078","https://openalex.org/W2994220412","https://openalex.org/W3034448411","https://openalex.org/W3034581612","https://openalex.org/W3035191304","https://openalex.org/W3035551320","https://openalex.org/W3035581100","https://openalex.org/W3053462477","https://openalex.org/W3098612954","https://openalex.org/W3107471220","https://openalex.org/W3107880069","https://openalex.org/W3110022498","https://openalex.org/W3126541466","https://openalex.org/W3174980830","https://openalex.org/W3175199633","https://openalex.org/W3202431232","https://openalex.org/W4293363567","https://openalex.org/W4385245566","https://openalex.org/W6687483927","https://openalex.org/W6743229011"],"related_works":["https://openalex.org/W2789522126","https://openalex.org/W2066693961","https://openalex.org/W2368363778","https://openalex.org/W122584421","https://openalex.org/W4244295168","https://openalex.org/W2753351751","https://openalex.org/W4206178588","https://openalex.org/W4287635093","https://openalex.org/W3094491777","https://openalex.org/W3214715529"],"abstract_inverted_index":{"Human":[0,46],"Mesh":[1,47],"Recovery":[2,48],"(HMR)":[3],"from":[4,75],"an":[5,79],"image":[6,80,107],"is":[7,35,69,108],"a":[8,65,89,126,142],"challenging":[9],"problem":[10],"because":[11],"of":[12,16],"the":[13,17,84,116,132],"inherent":[14],"ambiguity":[15],"task.":[18],"Existing":[19],"HMR":[20],"methods":[21],"utilized":[22],"either":[23],"temporal":[24,59],"information":[25],"or":[26],"kinematic":[27,61,97],"relationships":[28],"to":[29],"achieve":[30],"higher":[31],"accuracy,":[32],"but":[33],"there":[34],"no":[36],"method":[37,140],"using":[38,71,112,125],"both.":[39],"Hence,":[40],"we":[41,87],"propose":[42],"\u201cVideo":[43],"Inference":[44],"for":[45],"with":[49],"Vision":[50,113],"Transformer":[51],"(HMR-ViT)\u201d":[52],"that":[53,95,138],"can":[54],"take":[55],"into":[56],"account":[57],"both":[58],"and":[60,115,119,134],"information.":[62],"In":[63],"HMR-ViT,":[64],"Temporal-kinematic":[66],"Feature":[67],"Image":[68],"constructed":[70],"feature":[72,85,106],"vectors":[73],"obtained":[74],"video":[76],"frames":[77],"by":[78],"encoder.":[81],"When":[82],"generating":[83],"image,":[86],"use":[88],"Channel":[90],"Rearranging":[91],"Matrix":[92],"(CRM)":[93],"so":[94],"similar":[96],"features":[98],"could":[99],"be":[100],"located":[101],"spatially":[102],"close":[103],"together.":[104],"The":[105],"then":[109],"further":[110],"encoded":[111],"Transformer,":[114],"SMPL":[117],"pose":[118],"shape":[120],"parameters":[121],"are":[122],"finally":[123],"inferred":[124],"regression":[127],"network.":[128],"Extensive":[129],"evaluation":[130],"on":[131],"3DPW":[133],"Human3.6M":[135],"datasets":[136],"indicates":[137],"our":[139],"achieves":[141],"competitive":[143],"performance":[144],"in":[145],"HMR.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}