{"id":"https://openalex.org/W4409155141","doi":"https://doi.org/10.1109/tpami.2025.3558237","title":"Towards Real-World Aerial Vision Guidance With Categorical 6D Pose Tracker","display_name":"Towards Real-World Aerial Vision Guidance With Categorical 6D Pose Tracker","publication_year":2025,"publication_date":"2025-04-04","ids":{"openalex":"https://openalex.org/W4409155141","doi":"https://doi.org/10.1109/tpami.2025.3558237","pmid":"https://pubmed.ncbi.nlm.nih.gov/40184292"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3558237","doi":"https://doi.org/10.1109/tpami.2025.3558237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3558237","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","doyens","jufo-3","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.04377","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055922003","display_name":"Jingtao Sun","orcid":"https://orcid.org/0000-0001-5087-1304","observed_orcids":["https://orcid.org/0000-0001-5087-1304"]},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingtao Sun","raw_affiliation_strings":["College of Electrical and Information Engineering, National Engineering Research Centre for Robot Visual Perception and Control, Hunan University, Changsha, China","College of Electrical and Information Engineering and the National Engineering Research Centre for Robot Visual Perception and Control, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-5087-1304","affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering, National Engineering Research Centre for Robot Visual Perception and Control, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Electrical and Information Engineering and the National Engineering Research Centre for Robot Visual Perception and Control, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025640070","display_name":"Yaonan Wang","orcid":"https://orcid.org/0000-0002-0519-6458","observed_orcids":["https://orcid.org/0000-0002-0519-6458"]},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaonan Wang","raw_affiliation_strings":["College of Electrical and Information Engineering, National Engineering Research Centre for Robot Visual Perception and Control, Hunan University, Changsha, China","College of Electrical and Information Engineering and the National Engineering Research Centre for Robot Visual Perception and Control, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-0519-6458","affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering, National Engineering Research Centre for Robot Visual Perception and Control, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Electrical and Information Engineering and the National Engineering Research Centre for Robot Visual Perception and Control, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103232173","display_name":"Danwei Wang","orcid":"https://orcid.org/0000-0003-3400-0079","observed_orcids":["https://orcid.org/0000-0003-3400-0079"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Danwei Wang","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","School of Electrical and Electronic Engineering, Nanyang Technological University, SG, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3400-0079","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, SG, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.7661,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66034422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"47","issue":"7","first_page":"6055","last_page":"6072"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.3862000107765198,"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":0.3862000107765198,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.22679999470710754,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.2134999930858612,"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/category-level-pose-estimation","display_name":"category-level pose estimation","score":0.847000002861023},{"id":"https://openalex.org/keywords/keypoint-matching","display_name":"feature point matching","score":0.6850000023841858},{"id":"https://openalex.org/keywords/frame-difference","display_name":"frame difference","score":0.7160000205039978}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7937877178192139},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7464417815208435},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6196591854095459},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5629779100418091},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.4841045141220093},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.4363161623477936},{"id":"https://openalex.org/C2983761899","wikidata":"https://www.wikidata.org/wiki/Q604674","display_name":"Robot vision","level":4,"score":0.4251975417137146},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.336844265460968},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.22677761316299438},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19345134496688843},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.169195294380188}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tpami.2025.3558237","doi":"https://doi.org/10.1109/tpami.2025.3558237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3558237","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","doyens","jufo-3","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40184292","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40184292","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:2401.04377","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.04377","pdf_url":"https://arxiv.org/pdf/2401.04377","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/218188","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/218188","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},{"id":"doi:10.48550/arxiv.2401.04377","doi":"https://doi.org/10.48550/arxiv.2401.04377","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.04377","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.04377","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.04377","pdf_url":"https://arxiv.org/pdf/2401.04377","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G6432497039","display_name":null,"funder_award_id":"62293515","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W2012804028","https://openalex.org/W2100249329","https://openalex.org/W2280057228","https://openalex.org/W2342759786","https://openalex.org/W2595763608","https://openalex.org/W2798390501","https://openalex.org/W2909314588","https://openalex.org/W2963177347","https://openalex.org/W2963188159","https://openalex.org/W2987346479","https://openalex.org/W2994412884","https://openalex.org/W3009086056","https://openalex.org/W3034597466","https://openalex.org/W3035466700","https://openalex.org/W3037854993","https://openalex.org/W3044157743","https://openalex.org/W3091357794","https://openalex.org/W3107992529","https://openalex.org/W3111598592","https://openalex.org/W3115851871","https://openalex.org/W3130138602","https://openalex.org/W3131230508","https://openalex.org/W3133557228","https://openalex.org/W3151772196","https://openalex.org/W3163945288","https://openalex.org/W3166285241","https://openalex.org/W3167454939","https://openalex.org/W3190988267","https://openalex.org/W3193686508","https://openalex.org/W3199947443","https://openalex.org/W3202459445","https://openalex.org/W3202538459","https://openalex.org/W3204319309","https://openalex.org/W3205986419","https://openalex.org/W3206934897","https://openalex.org/W3214778407","https://openalex.org/W4200604336","https://openalex.org/W4205105995","https://openalex.org/W4206522166","https://openalex.org/W4226321491","https://openalex.org/W4226322645","https://openalex.org/W4280589974","https://openalex.org/W4281482294","https://openalex.org/W4312266040","https://openalex.org/W4312453532","https://openalex.org/W4312604533","https://openalex.org/W4312630861","https://openalex.org/W4312735552","https://openalex.org/W4312877043","https://openalex.org/W4319996466","https://openalex.org/W4380480166","https://openalex.org/W4385245566","https://openalex.org/W4385834350","https://openalex.org/W4386066287","https://openalex.org/W4386075656","https://openalex.org/W4386075917","https://openalex.org/W4386320409","https://openalex.org/W4388266322","https://openalex.org/W4388666680","https://openalex.org/W4388934137","https://openalex.org/W4389665706","https://openalex.org/W4390570319","https://openalex.org/W4390872210","https://openalex.org/W4390872672","https://openalex.org/W4390873077","https://openalex.org/W4390873315","https://openalex.org/W4390873470","https://openalex.org/W4390873560","https://openalex.org/W4390873690","https://openalex.org/W4390874575","https://openalex.org/W6779163297","https://openalex.org/W7133185337"],"related_works":["https://openalex.org/W2318398720","https://openalex.org/W2072007712","https://openalex.org/W2928162577","https://openalex.org/W2118030816","https://openalex.org/W2081400338","https://openalex.org/W2013269986","https://openalex.org/W2068241324","https://openalex.org/W4406524917","https://openalex.org/W590253240","https://openalex.org/W2095314401"],"abstract_inverted_index":{"Tracking":[0],"the":[1,20,107,110,141,156,171],"object":[2],"6-DoF":[3,34,67],"pose":[4,35,68],"is":[5,198],"crucial":[6],"for":[7,28],"various":[8],"downstream":[9],"robot":[10,22],"tasks":[11],"and":[12,50,52,75,113,122],"real-world":[13,21,191],"applications.":[14,194],"In":[15],"this":[16],"paper,":[17],"we":[18,61],"investigate":[19],"task":[23],"of":[24,109,159,173],"aerial":[25,29,143,160,192],"vision":[26,144],"guidance":[27,145],"robotics":[30,161],"manipulation,":[31],"utilizing":[32],"category-level":[33,66],"tracking.":[36],"Aerial":[37],"conditions":[38],"inevitably":[39],"introduce":[40,63],"special":[41],"challenges,":[42],"such":[43],"as":[44,135],"rapid":[45],"viewpoint":[46],"changes":[47],"in":[48,59,92,190],"pitch":[49],"roll":[51],"inter-frame":[53,82,111],"differences.":[54],"To":[55],"support":[56],"these":[57],"challenges":[58],"task,":[60],"first":[62],"a":[64,87,93,100,128,136],"robust":[65],"tracker":[69,72],"(Robust6DoF).":[70],"This":[71],"leverages":[73],"shape":[74,115],"temporal":[76,119],"prior":[77],"knowledge":[78],"to":[79,104,139,153],"explore":[80],"optimal":[81],"keypoint":[83],"pairs,":[84],"generated":[85],"under":[86],"priori":[88],"structural":[89,157],"adaptive":[90],"supervision":[91],"coarse-to-fine":[94],"manner.":[95],"Notably,":[96],"our":[97,174,181],"Robust6DoF":[98,182],"employs":[99],"Spatial-Temporal":[101],"Augmentation":[102],"module":[103],"deal":[105],"with":[106,184],"problems":[108],"differences":[112],"intra-class":[114],"variations":[116],"through":[117],"both":[118],"dynamic":[120],"filtering":[121],"shape-similarity":[123],"filtering.":[124],"We":[125],"further":[126],"present":[127],"Pose-Aware":[129],"Discrete":[130],"Servo":[131],"strategy":[132],"(PAD-Servo),":[133],"serving":[134],"decoupling":[137],"approach":[138],"implement":[140],"final":[142],"task.":[146],"It":[147],"contains":[148],"two":[149],"servo":[150],"action":[151],"policies":[152],"better":[154],"accommodate":[155],"properties":[158],"manipulation.":[162],"Exhaustive":[163],"experiments":[164],"on":[165],"four":[166],"well-known":[167],"public":[168],"benchmarks":[169],"demonstrate":[170],"superiority":[172],"Robust6DoF.":[175,201],"Real-world":[176],"tests":[177],"directly":[178],"verify":[179],"that":[180],"along":[183],"PAD-Servo":[185],"can":[186],"be":[187],"readily":[188],"used":[189],"robotic":[193],"The":[195],"project":[196],"homepage":[197],"released":[199],"at":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}