{"id":"https://openalex.org/W7138392753","doi":"https://doi.org/10.1609/aaai.v40i13.38050","title":"Attentive Keypoint Identification: Progressive Spatiotemporal Refinement for Video-based Human Pose Estimation","display_name":"Attentive Keypoint Identification: Progressive Spatiotemporal Refinement for Video-based Human Pose Estimation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138392753","doi":"https://doi.org/10.1609/aaai.v40i13.38050"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i13.38050","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38050","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i13.38050","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129722807","display_name":"Sifan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sifan Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129693808","display_name":"Haipeng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haipeng Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129720155","display_name":"Yingda Lyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingda Lyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100777508","display_name":"Shaojing Fan","orcid":"https://orcid.org/0000-0002-7744-1133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaojing Fan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129682684","display_name":"Zhigang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhigang Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129728194","display_name":"Zhenguang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenguang Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068056273","display_name":"Yingying Jiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingying Jiao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5129722807"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76882923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"10754","last_page":"10762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9815999865531921,"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":0.9815999865531921,"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":0.0044999998062849045,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.0034000000450760126,"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/discriminative-model","display_name":"Discriminative model","score":0.73089998960495},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6236000061035156},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.490200012922287},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4796000123023987},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.4749999940395355},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.44350001215934753},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.36579999327659607},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3425000011920929}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8274999856948853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910000085830688},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.73089998960495},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6236000061035156},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5748000144958496},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.44350001215934753},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i13.38050","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38050","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i13.38050","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38050","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7096686363220215,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video-based":[0],"human":[1,34],"pose":[2,58],"estimation":[3],"has":[4],"vast":[5],"applications":[6],"such":[7],"as":[8,21],"action":[9],"recognition,":[10],"sports":[11],"analytics,":[12],"and":[13,28,57,79,86,137,182],"crime":[14],"detection.":[15],"However,":[16],"this":[17],"task":[18],"is":[19],"challenging":[20,52],"it":[22],"involves":[23],"interpreting":[24],"both":[25,76],"spatial":[26,68,84,122],"context":[27],"temporal":[29,87,152],"dynamics":[30],"to":[31,64,75,91,93,119],"accurately":[32],"localize":[33],"anatomical":[35],"keypoints":[36],"in":[37,51,98,180],"video":[38],"sequences.":[39],"Current":[40],"approaches,":[41],"often":[42],"based":[43],"on":[44,187],"attention":[45,74],"mechanisms,":[46],"perform":[47],"well":[48],"but":[49],"struggle":[50],"scenarios":[53],"like":[54],"rapid":[55,103],"motion":[56],"occlusion.":[59],"We":[60],"attribute":[61],"these":[62,107],"failures":[63],"two":[65],"fundamental":[66],"limitations:":[67],"uniformity,":[69],"where":[70],"models":[71],"indiscriminately":[72],"assign":[73],"joint-relevant":[77,135],"features":[78,136,166],"background":[80],"clutter,":[81],"thereby":[82],"introducing":[83],"noise;":[85],"rigidity,":[88],"an":[89],"inability":[90],"adapt":[92],"large":[94],"joint":[95],"displacements,":[96],"resulting":[97],"severe":[99],"feature":[100],"misalignment":[101],"during":[102],"motion.":[104],"To":[105],"overcome":[106],"challenges,":[108],"we":[109,125,155],"introduce":[110,156],"PSTPose,":[111],"a":[112,127,138,157,198],"novel":[113],"progressive":[114],"spatiotemporal":[115],"refinement":[116],"framework.":[117],"Specifically,":[118],"address":[120],"the":[121,151],"uniformity":[123],"problem,":[124,154],"propose":[126],"Discriminative":[128],"Feature":[129,139],"Enhancement":[130],"(DFE)":[131],"module":[132,143,162],"that":[133,144,163,195],"emphasizes":[134],"Cluster":[140],"Grouping":[141],"(FCG)":[142],"forms":[145],"compact,":[146],"semantically":[147],"meaningful":[148],"regions.":[149],"For":[150],"rigidity":[153],"Deformable":[158],"Spatiotemporal":[159],"Fusion":[160],"(DSF)":[161],"adaptively":[164],"aligns":[165],"across":[167],"consecutive":[168],"frames":[169],"via":[170],"deformation-aware":[171],"sampling.":[172],"This":[173],"design":[174],"ensures":[175],"robust":[176],"keypoint":[177],"localization,":[178],"particularly":[179],"cluttered":[181],"dynamic":[183],"scenes.":[184],"Extensive":[185],"experiments":[186],"three":[188],"large-scale":[189],"benchmarks,":[190],"PoseTrack2017,":[191],"PoseTrack2018,":[192],"PoseTrack21,":[193],"demonstrate":[194],"PSTPose":[196],"establishes":[197],"new":[199],"state-of-the-art.":[200]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}