{"id":"https://openalex.org/W4380480166","doi":"https://doi.org/10.1109/tmm.2023.3284598","title":"CatTrack: Single-Stage Category-Level 6D Object Pose Tracking via Convolution and Vision Transformer","display_name":"CatTrack: Single-Stage Category-Level 6D Object Pose Tracking via Convolution and Vision Transformer","publication_year":2023,"publication_date":"2023-06-13","ids":{"openalex":"https://openalex.org/W4380480166","doi":"https://doi.org/10.1109/tmm.2023.3284598"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3284598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3284598","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5084793792","display_name":"Sheng Yu","orcid":"https://orcid.org/0009-0002-0709-1024"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Yu","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-0709-1024","affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078047051","display_name":"Di\u2010Hua Zhai","orcid":"https://orcid.org/0000-0001-8653-8626"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di-Hua Zhai","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, China","Yangtze Delta Region Academy, Beijing Institute of Technology, Jiaxing, China"],"raw_orcid":"https://orcid.org/0000-0001-8653-8626","affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Yangtze Delta Region Academy, Beijing Institute of Technology, Jiaxing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064231378","display_name":"Yuanqing Xia","orcid":"https://orcid.org/0000-0002-5977-4911"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanqing Xia","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5977-4911","affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092153381","display_name":"Dong Li","orcid":"https://orcid.org/0009-0004-6523-6900"},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Li","raw_affiliation_strings":["China Unicom Research Institute, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-6523-6900","affiliations":[{"raw_affiliation_string":"China Unicom Research Institute, Beijing, China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088857350","display_name":"Shiqi Zhao","orcid":"https://orcid.org/0009-0006-2508-7108"},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiqi Zhao","raw_affiliation_strings":["China Unicom Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Unicom Research Institute, Beijing, China","institution_ids":["https://openalex.org/I6507939"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7445,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.72350162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"26","issue":null,"first_page":"1665","last_page":"1680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9980999827384949,"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":0.9980999827384949,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9952999949455261,"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":0.9911999702453613,"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/computer-science","display_name":"Computer science","score":0.8211377859115601},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7767051458358765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7763301134109497},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.7091735601425171},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5630755424499512},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.526717483997345},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5103628039360046},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.46108052134513855},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43606263399124146},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.427828311920166},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.3150033950805664}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8211377859115601},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7767051458358765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7763301134109497},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7091735601425171},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5630755424499512},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.526717483997345},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5103628039360046},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.46108052134513855},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43606263399124146},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.427828311920166},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.3150033950805664}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3284598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3284598","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G148761407","display_name":null,"funder_award_id":"62173035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6584182289","display_name":null,"funder_award_id":"61803033","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7007940310","display_name":null,"funder_award_id":"61836001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":90,"referenced_works":["https://openalex.org/W1526868886","https://openalex.org/W1991544872","https://openalex.org/W2012804028","https://openalex.org/W2053138020","https://openalex.org/W2119414364","https://openalex.org/W2124386111","https://openalex.org/W2154118921","https://openalex.org/W2177478906","https://openalex.org/W2200124539","https://openalex.org/W2207670488","https://openalex.org/W2280057228","https://openalex.org/W2416144529","https://openalex.org/W2470394683","https://openalex.org/W2600447016","https://openalex.org/W2604236302","https://openalex.org/W2768879211","https://openalex.org/W2781064046","https://openalex.org/W2786036844","https://openalex.org/W2790194629","https://openalex.org/W2797394534","https://openalex.org/W2885546722","https://openalex.org/W2942079888","https://openalex.org/W2962783853","https://openalex.org/W2963150697","https://openalex.org/W2963177347","https://openalex.org/W2963188159","https://openalex.org/W2963300314","https://openalex.org/W2963319519","https://openalex.org/W2963323244","https://openalex.org/W2963756608","https://openalex.org/W2963892972","https://openalex.org/W2964226622","https://openalex.org/W2964249569","https://openalex.org/W2972392244","https://openalex.org/W2981378444","https://openalex.org/W2989915422","https://openalex.org/W2990211277","https://openalex.org/W2998787775","https://openalex.org/W3009086056","https://openalex.org/W3034597466","https://openalex.org/W3034986117","https://openalex.org/W3035022492","https://openalex.org/W3035355652","https://openalex.org/W3091357794","https://openalex.org/W3095753995","https://openalex.org/W3096609285","https://openalex.org/W3101415077","https://openalex.org/W3101708136","https://openalex.org/W3106842734","https://openalex.org/W3107992529","https://openalex.org/W3110501021","https://openalex.org/W3129901004","https://openalex.org/W3130138602","https://openalex.org/W3131500599","https://openalex.org/W3133557228","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3151772196","https://openalex.org/W3163945288","https://openalex.org/W3168649818","https://openalex.org/W3171125843","https://openalex.org/W3171516518","https://openalex.org/W3174635123","https://openalex.org/W3180720907","https://openalex.org/W3190988267","https://openalex.org/W3196328566","https://openalex.org/W3199947443","https://openalex.org/W3202459445","https://openalex.org/W3202538459","https://openalex.org/W3203003533","https://openalex.org/W3204554907","https://openalex.org/W3205986419","https://openalex.org/W3212622989","https://openalex.org/W3212953023","https://openalex.org/W3214586131","https://openalex.org/W4213019189","https://openalex.org/W4214493665","https://openalex.org/W4214759957","https://openalex.org/W4226322645","https://openalex.org/W4281482294","https://openalex.org/W4312753915","https://openalex.org/W4312950730","https://openalex.org/W6747827861","https://openalex.org/W6760424586","https://openalex.org/W6763422710","https://openalex.org/W6774358873","https://openalex.org/W6784333009","https://openalex.org/W6785665406","https://openalex.org/W6788135285","https://openalex.org/W6805147364"],"related_works":["https://openalex.org/W2946083937","https://openalex.org/W2798721181","https://openalex.org/W4386075737","https://openalex.org/W2951583186","https://openalex.org/W4299867837","https://openalex.org/W2088028039","https://openalex.org/W4382141741","https://openalex.org/W3165753266","https://openalex.org/W1968783203","https://openalex.org/W4206633503"],"abstract_inverted_index":{"In":[0,56],"the":[1,18,37,82,85,93,98,132,138,151,167,184,194],"current":[2],"research,":[3],"many":[4],"researchers":[5,34],"have":[6,35,162,181],"focused":[7],"on":[8],"instance-level":[9],"pose":[10,40,49,69,77,90,196],"tracking,":[11],"which":[12],"requires":[13],"a":[14,62,124,144],"3D":[15],"model":[16],"of":[17,135,155,186,197],"object":[19,39,76,99,156],"in":[20,27,75,104,158,174],"advance,":[21],"making":[22],"it":[23,191],"challenging":[24],"to":[25,88,111,130,149,166,176,192],"apply":[26],"practice.":[28],"To":[29,119],"address":[30],"this":[31,57,120],"limitation,":[32],"some":[33],"proposed":[36],"category-level":[38,48,67],"tracking":[41,50,70,78],"method.":[42],"Achieving":[43],"accurate":[44],"and":[45,101,115,153,170,188],"speedy":[46],"monocular":[47,66],"is":[51,80],"an":[52],"essential":[53],"research":[54],"goal.":[55],"article,":[58],"we":[59,109,122,142,180],"propose":[60,123,143],"CatTrack,":[61],"new":[63,145],"single-stage":[64],"keypoints-based":[65],"multi-object":[68],"network.":[71],"A":[72],"significant":[73],"issue":[74],"tasks":[79],"utilizing":[81],"information":[83,103,114,127,134],"from":[84,137],"previous":[86,139],"frame":[87,106],"guide":[89],"estimation":[91],"for":[92],"next":[94],"frame.":[95,140],"However,":[96],"as":[97],"poses":[100],"camera":[102],"each":[105],"are":[107],"different,":[108],"need":[110],"remove":[112],"irrelevant":[113],"emphasize":[116],"useful":[117],"features.":[118],"end,":[121],"transformer-based":[125],"temporal":[126],"capture":[128],"module":[129,148],"leverage":[131],"position":[133],"keypoints":[136,157],"Furthermore,":[141,179],"keypoint":[146],"matching":[147,154],"enable":[150],"grouping":[152],"complex":[159],"scenes.":[160],"We":[161],"successfully":[163,189],"applied":[164,190],"CatTrack":[165,187],"Objectron":[168],"dataset":[169],"achieved":[171],"superior":[172],"results":[173],"comparison":[175],"existing":[177],"methods.":[178],"also":[182],"evaluated":[183],"generalization":[185],"track":[193],"6D":[195],"unseen":[198],"real-world":[199],"objects.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}