{"id":"https://openalex.org/W4414360621","doi":"https://doi.org/10.24963/ijcai.2025/137","title":"SeqPose: An End-to-End Framework to Unify Single-frame and Video-based RGB Category-Level Pose Estimation","display_name":"SeqPose: An End-to-End Framework to Unify Single-frame and Video-based RGB Category-Level Pose Estimation","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360621","doi":"https://doi.org/10.24963/ijcai.2025/137"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/137","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5016989631","display_name":"Yuzhu Ji","orcid":"https://orcid.org/0000-0003-3589-3884"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuzhu Ji","raw_affiliation_strings":["School of Computer Science and Technology, Guangdong University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Guangdong University of Technology, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079553762","display_name":"Mingshan Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingshan Sun","raw_affiliation_strings":["CVTE Research, China"],"affiliations":[{"raw_affiliation_string":"CVTE Research, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101997806","display_name":"Jianyang Shi","orcid":"https://orcid.org/0000-0002-9151-6058"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyang Shi","raw_affiliation_strings":["Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064594384","display_name":"Xiaoke Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoke Jiang","raw_affiliation_strings":["International Digital Economy Academy (IDEA), China"],"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy (IDEA), China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329232","display_name":"Yiqun Zhang","orcid":"https://orcid.org/0000-0002-0328-987X"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqun Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Guangdong University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Guangdong University of Technology, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100458457","display_name":"Haijun Zhang","orcid":"https://orcid.org/0000-0002-1648-0227"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijun Zhang","raw_affiliation_strings":["Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5016989631"],"corresponding_institution_ids":["https://openalex.org/I139024713"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26792941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1224","last_page":"1232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.998199999332428,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.998199999332428,"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":0.9955000281333923,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/pose","display_name":"Pose","score":0.8238999843597412},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5105999708175659},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49950000643730164},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.49720001220703125},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.47749999165534973},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45719999074935913},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4397999942302704},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.42980000376701355}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8238999843597412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267000079154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7056999802589417},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5443999767303467},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5105999708175659},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.49720001220703125},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.39480000734329224},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3937999904155731},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/137","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Category-level":[0],"object":[1,33],"pose":[2,76,136,159],"estimation":[3,160],"is":[4,113,139,170],"a":[5,124,135],"longstanding":[6],"and":[7,14,25,50,73,88,94,105,120,131,165],"fundamental":[8],"task":[9],"crucial":[10],"for":[11],"augmented":[12],"reality":[13],"robotic":[15],"manipulation":[16],"applications.":[17,63],"Existing":[18],"RGB-based":[19,157],"approaches":[20,60],"struggle":[21],"with":[22,156],"multi-stage":[23],"settings":[24],"heavily":[26],"rely":[27],"on":[28,162],"off-the-shelf":[29],"techniques,":[30],"such":[31],"as":[32,91],"detectors,":[34],"depth":[35,89],"estimators,":[36],"non-differentiable":[37],"NOCS":[38],"shape":[39],"alignment,":[40],"etc.":[41],"Extra":[42],"dependencies":[43],"lead":[44],"to":[45,100,115],"the":[46,52,56,71,85,117,142,163],"accumulation":[47],"of":[48,58,80,126],"errors":[49],"complicate":[51],"whole":[53],"pipeline,":[54],"limiting":[55],"deployment":[57],"these":[59],"in":[61],"practical":[62],"This":[64],"paper":[65],"streamlined":[66],"an":[67],"end-to-end":[68],"framework":[69],"unifying":[70],"single-frame":[72],"video-based":[74],"category-level":[75],"estimation.":[77],"Specifically,":[78],"instead":[79],"explicitly":[81],"introducing":[82],"extra":[83],"dependencies,":[84],"DINOv2":[86],"encoder":[87],"decoder,":[90],"robust":[92],"semantic":[93,104],"geometric":[95,106],"prior":[96],"extractors,":[97],"are":[98],"leveraged":[99],"produce":[101],"intra-frame":[102,132],"hierarchical":[103],"features.":[107,133],"A":[108],"spatial-temporal":[109],"sparse":[110],"query":[111,129],"network":[112],"developed":[114],"model":[116,151],"implicit":[118,127],"correspondence":[119],"inter-frame":[121],"correlations":[122],"between":[123],"set":[125],"3D":[128],"anchors":[130],"Finally,":[134],"prediction":[137],"head":[138],"employed":[140],"using":[141],"bipartite":[143],"matching":[144],"algorithm.":[145],"Experimental":[146],"results":[147],"demonstrate":[148],"that":[149],"our":[150],"achieves":[152],"state-of-the-art":[153],"performance":[154],"compared":[155],"categorical":[158],"methods":[161],"REAL275":[164],"CAMERA25":[166],"datasets.":[167],"Our":[168],"code":[169],"available":[171],"at":[172],"https://andrewchiyz.github.io/vision.3dv.seqpose/.":[173]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}