{"id":"https://openalex.org/W7137975944","doi":"https://doi.org/10.1609/aaai.v40i9.37631","title":"Skeletons Speak Louder than Text: A Motion-Aware Pretraining Paradigm for Video-Based Person Re-Identification","display_name":"Skeletons Speak Louder than Text: A Motion-Aware Pretraining Paradigm for Video-Based Person Re-Identification","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137975944","doi":"https://doi.org/10.1609/aaai.v40i9.37631"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i9.37631","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37631","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37631/41593","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37631/41593","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091755668","display_name":"Rifen Lin","orcid":"https://orcid.org/0009-0002-6005-3131"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rifen Lin","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129693155","display_name":"Alex Jinpeng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Alex Jinpeng Wang","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087799311","display_name":"Jiawei Mo","orcid":"https://orcid.org/0000-0002-1043-5353"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Mo","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129747618","display_name":"Min Li","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Li","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"9","first_page":"6970","last_page":"6978"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.7340999841690063,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.7340999841690063,"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":0.12070000171661377,"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"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.04430000111460686,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6539000272750854},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5712000131607056},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5275999903678894},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4251999855041504},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4077000021934509},{"id":"https://openalex.org/keywords/analogy","display_name":"Analogy","score":0.3709999918937683},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3698999881744385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6567000150680542},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6539000272750854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.609499990940094},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5712000131607056},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5275999903678894},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4251999855041504},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36010000109672546},{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.28349998593330383},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2720000147819519},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2720000147819519},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.26579999923706055},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i9.37631","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37631","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37631/41593","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.v40i9.37631","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37631","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37631/41593","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137975944.pdf","grobid_xml":"https://content.openalex.org/works/W7137975944.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"pretraining":[1,66,198],"has":[2],"revolutionized":[3],"visual":[4,110,158],"understanding,":[5],"but":[6],"its":[7],"impact":[8],"on":[9,20,169],"video-based":[10],"person":[11],"re-identification":[12],"(ReID)":[13],"remains":[14],"underexplored.":[15],"Existing":[16],"approaches":[17],"often":[18],"rely":[19],"video-text":[21],"pairs,":[22],"yet":[23],"suffer":[24],"from":[25,58,151],"two":[26],"fundamental":[27],"limitations:":[28],"(1)":[29],"lack":[30],"of":[31],"genuine":[32],"multimodal":[33,129,207],"pretraining,":[34],"and":[35,109,134,154,196],"(2)":[36],"text":[37],"poorly":[38],"captures":[39],"fine-grained":[40],"temporal":[41,149],"motion\u2014an":[42],"essential":[43],"cue":[44],"for":[45,68,78,200],"distinguishing":[46],"identities":[47],"in":[48,206],"video.":[49],"In":[50,98,115],"this":[51],"work,":[52],"we":[53,73,102,119,138],"take":[54],"a":[55,81,90,121,140,203],"bold":[56],"departure":[57],"text-based":[59],"paradigms":[60],"by":[61],"introducing":[62],"the":[63,99,116],"first":[64,100],"skeleton-driven":[65],"framework":[67],"ReID.":[69],"To":[70],"achieve":[71],"this,":[72],"propose":[74,139],"Contrastive":[75],"Skeleton-Image":[76],"Pretraining":[77],"ReID":[79,172,184],"(CSIP-ReID),":[80],"novel":[82],"two-stage":[83],"method":[84],"that":[85,147,163],"leverages":[86],"skeleton":[87,108,152],"sequences":[88],"as":[89],"spatiotemporally":[91],"informative":[92],"modality":[93],"aligned":[94],"with":[95],"video":[96,171],"frames.":[97],"stage,":[101,118],"employ":[103],"contrastive":[104],"learning":[105],"to":[106,127,182],"align":[107],"features":[111],"at":[112],"sequence":[113],"level.":[114],"second":[117],"introduce":[120],"dynamic":[122],"Prototype":[123],"Fusion":[124],"Updater":[125],"(PFU)":[126],"refine":[128],"identity":[130],"prototypes,":[131],"fusing":[132],"motion":[133],"appearance":[135],"cues.":[136],"Moreover,":[137,177],"Skeleton":[141],"Guided":[142],"Temporal":[143],"Modeling":[144],"(SGTM)":[145],"module":[146],"distills":[148],"cues":[150],"data":[153],"integrates":[155],"them":[156],"into":[157],"features.":[159],"Extensive":[160],"experiments":[161],"demonstrate":[162],"CSIP-ReID":[164,192],"achieves":[165],"new":[166,204],"state-of-the-art":[167],"results":[168],"standard":[170],"benchmarks":[173],"(MARS,":[174],"LS-VID,":[175],"iLIDS-VID).":[176],"it":[178],"exhibits":[179],"strong":[180],"generalization":[181],"skeleton-only":[183],"tasks":[185],"(BIWI,":[186],"IAS),":[187],"significantly":[188],"outperforming":[189],"previous":[190],"methods.":[191],"pioneers":[193],"an":[194],"annotation-free":[195],"motion-aware":[197],"paradigm":[199],"ReID,":[201],"opening":[202],"frontier":[205],"representation":[208],"learning.":[209]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}
