{"id":"https://openalex.org/W4403780755","doi":"https://doi.org/10.1145/3664647.3681131","title":"VoCAPTER: Voting-based Pose Tracking for Category-level Articulated Object via Inter-frame Priors","display_name":"VoCAPTER: Voting-based Pose Tracking for Category-level Articulated Object via Inter-frame Priors","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780755","doi":"https://doi.org/10.1145/3664647.3681131"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681131","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5011780655","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0003-1610-6056"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I2802624667","display_name":"Hefei Institutes of Physical Science","ror":"https://ror.org/046n57345","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Hefei Institute of Physical Science, Chinese Academy of Sciences, University of Science and Technology of China, & Astribot Inc, HeFei, AnHui, China"],"affiliations":[{"raw_affiliation_string":"Hefei Institute of Physical Science, Chinese Academy of Sciences, University of Science and Technology of China, & Astribot Inc, HeFei, AnHui, China","institution_ids":["https://openalex.org/I2802624667","https://openalex.org/I19820366","https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108818350","display_name":"Z. Y. Han","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zean Han","raw_affiliation_strings":["Department of Mathematics, Chinese University of Hong Kong, New Territories, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Chinese University of Hong Kong, New Territories, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101454332","display_name":"Yan Zhong","orcid":"https://orcid.org/0000-0003-0005-2620"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhong","raw_affiliation_strings":["School of Mathematical Sciences, National Engineering Research Center of Visual Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, National Engineering Research Center of Visual Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023229450","display_name":"Qiaojun Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiaojun Yu","raw_affiliation_strings":["Department of Computer Science, Shanghai Jiao Tong University, ShangHai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Shanghai Jiao Tong University, ShangHai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101768802","display_name":"Xingyu Wu","orcid":"https://orcid.org/0000-0002-8204-6197"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xingyu Wu","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106720660","display_name":"Xue Wang","orcid":"https://orcid.org/0009-0006-9991-0419"},"institutions":[{"id":"https://openalex.org/I2802624667","display_name":"Hefei Institutes of Physical Science","ror":"https://ror.org/046n57345","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Wang","raw_affiliation_strings":["Hefei Institute of Physical Science, Chinese Academy Sciences, HeFei, AnHui, China"],"affiliations":[{"raw_affiliation_string":"Hefei Institute of Physical Science, Chinese Academy Sciences, HeFei, AnHui, China","institution_ids":["https://openalex.org/I2802624667"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047334112","display_name":"Rujing Wang","orcid":"https://orcid.org/0000-0001-9534-3425"},"institutions":[{"id":"https://openalex.org/I2802624667","display_name":"Hefei Institutes of Physical Science","ror":"https://ror.org/046n57345","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rujing Wang","raw_affiliation_strings":["Hefei Institute of Physical Science, Chinese Academy Sciences, HeFei, AnHui, China"],"affiliations":[{"raw_affiliation_string":"Hefei Institute of Physical Science, Chinese Academy Sciences, HeFei, AnHui, China","institution_ids":["https://openalex.org/I2802624667"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5011780655"],"corresponding_institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I2802624667"],"apc_list":null,"apc_paid":null,"fwci":1.3978,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82216922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8942","last_page":"8951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9970999956130981,"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/computer-vision","display_name":"Computer vision","score":0.7049972414970398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6936455965042114},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.6924961805343628},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6864480376243591},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6160986423492432},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5602723956108093},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5601903796195984},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5056924819946289},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4724222421646118},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.44171959161758423},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10371723771095276},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.07816565036773682}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7049972414970398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6936455965042114},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.6924961805343628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6864480376243591},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6160986423492432},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5602723956108093},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5601903796195984},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5056924819946289},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4724222421646118},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.44171959161758423},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10371723771095276},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.07816565036773682},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681131","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2046346382","https://openalex.org/W2161168419","https://openalex.org/W2889784867","https://openalex.org/W2946305700","https://openalex.org/W2963892972","https://openalex.org/W3035131925","https://openalex.org/W3035624836","https://openalex.org/W3091357794","https://openalex.org/W3151772196","https://openalex.org/W3159812989","https://openalex.org/W3174822420","https://openalex.org/W3190988267","https://openalex.org/W3202538459","https://openalex.org/W4206522166","https://openalex.org/W4220668680","https://openalex.org/W4226321491","https://openalex.org/W4226376247","https://openalex.org/W4281482294","https://openalex.org/W4312893019","https://openalex.org/W4312923690","https://openalex.org/W4313031313","https://openalex.org/W4313033364","https://openalex.org/W4386003392","https://openalex.org/W4386066076","https://openalex.org/W4386066287","https://openalex.org/W4386075519","https://openalex.org/W4387359812","https://openalex.org/W4387968151","https://openalex.org/W4388934137","https://openalex.org/W4391070084","https://openalex.org/W4391216149","https://openalex.org/W4393159789","https://openalex.org/W4394625728"],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3142333283","https://openalex.org/W3122088529","https://openalex.org/W3041320102","https://openalex.org/W2111669074","https://openalex.org/W2085259108","https://openalex.org/W3123087812","https://openalex.org/W2810129309"],"abstract_inverted_index":{"Articulated":[0,52],"objects":[1],"are":[2],"common":[3],"in":[4,160,188],"our":[5,120],"daily":[6],"life.":[7],"However,":[8],"current":[9,70],"category-level":[10,34],"articulation":[11,136],"pose":[12,38,103,109,147,190],"works":[13],"mostly":[14],"focus":[15],"on":[16,20],"predicting":[17],"9D":[18,37,76],"poses":[19,60,77],"statistical":[21],"point":[22,99],"cloud":[23],"observations.":[24],"In":[25],"this":[26,198],"paper,":[27],"we":[28,44,93,180],"deal":[29],"with":[30],"the":[31,69,73,79,97,102,150,156,161,202,215],"problem":[32],"of":[33,40,87,158,183,192,204],"online":[35],"robust":[36,117],"tracking":[39,104,137,191],"articulated":[41,193],"objects,":[42],"where":[43],"propose":[45],"VoCAPTER,":[46],"a":[47,116,134],"novel":[48],"3D":[49],"Voting-based":[50],"Category-level":[51],"object":[53],"Pose":[54],"TrackER.":[55],"Our":[56],"VoCAPTER":[57,159],"efficiently":[58],"updates":[59],"between":[61,91],"adjacent":[62],"frames":[63],"by":[64,83,95],"utilizing":[65],"partial":[66],"observations":[67],"from":[68,78],"frame":[71],"and":[72,164,174,186,211],"estimated":[74],"per-part":[75],"previous":[80],"frame.":[81],"Specifically,":[82],"incorporating":[84],"prior":[85],"knowledge":[86],"continuous":[88],"motion":[89],"relationships":[90],"frames,":[92],"begin":[94],"canonicalizing":[96],"input":[98],"cloud,":[100],"casting":[101],"task":[105],"as":[106,142],"an":[107],"inter-frame":[108],"increment":[110],"estimation":[111],"challenge.":[112],"Subsequently,":[113],"to":[114,124,172],"obtain":[115],"pose-tracking":[118],"algorithm,":[119,138],"main":[121],"idea":[122],"is":[123,131],"leverage":[125],"SE(3)-invariant":[126],"features":[127],"during":[128],"motion.":[129],"This":[130],"achieved":[132],"through":[133],"voting-based":[135],"which":[139,167],"identifies":[140],"keyframes":[141],"reference":[143],"states":[144],"for":[145],"accurate":[146],"updating":[148],"throughout":[149],"entire":[151],"video":[152],"sequence.":[153],"We":[154,195],"evaluate":[155],"performance":[157],"synthetic":[162],"dataset":[163],"real-world":[165],"scenarios,":[166],"demonstrates":[168],"VoCAPTER's":[169,184],"generalization":[170],"ability":[171],"diverse":[173],"complicated":[175],"scenes.":[176],"Through":[177],"these":[178],"experiments,":[179],"provide":[181],"evidence":[182],"superiority":[185],"robustness":[187],"multi-frame":[189],"objects.":[194],"believe":[196],"that":[197],"work":[199],"can":[200],"facilitate":[201],"progress":[203],"various":[205],"fields,":[206],"including":[207],"robotics,":[208],"embodied":[209],"intelligence,":[210],"augmented":[212],"reality.":[213],"All":[214],"codes":[216],"will":[217],"be":[218],"made":[219],"publicly":[220],"available.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}