{"id":"https://openalex.org/W4414458957","doi":"https://doi.org/10.1109/tcsvt.2025.3613733","title":"Diff-COPE: Diffusion-Based Category-Level 6D Object Pose Estimation","display_name":"Diff-COPE: Diffusion-Based Category-Level 6D Object Pose Estimation","publication_year":2025,"publication_date":"2025-09-24","ids":{"openalex":"https://openalex.org/W4414458957","doi":"https://doi.org/10.1109/tcsvt.2025.3613733"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3613733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3613733","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5083390694","display_name":"Yingbo Tang","orcid":"https://orcid.org/0009-0001-1657-256X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingbo Tang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-1657-256X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044898133","display_name":"Zhiqiang Cao","orcid":"https://orcid.org/0000-0003-1801-3363"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Cao","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1801-3363","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055132525","display_name":"Peiyu Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiyu Guan","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1909-1953","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069171230","display_name":"Xurong Gong","orcid":"https://orcid.org/0009-0001-9017-1342"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xurong Gong","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-9017-1342","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mengyao Wang","orcid":"https://orcid.org/0009-0004-5334-4568"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyao Wang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-5334-4568","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073958329","display_name":"Junzhi Yu","orcid":"https://orcid.org/0000-0002-6347-572X"},"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":"Junzhi Yu","raw_affiliation_strings":["Department of Advanced Manufacturing and Robotics, BIC-ESAT, College of Engineering, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6347-572X","affiliations":[{"raw_affiliation_string":"Department of Advanced Manufacturing and Robotics, BIC-ESAT, College of Engineering, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7779,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75727714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"36","issue":"3","first_page":"3556","last_page":"3572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9958000183105469,"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":0.9958000183105469,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9951000213623047,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.987500011920929,"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/pose","display_name":"Pose","score":0.6753000020980835},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5705000162124634},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5688999891281128},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.522599995136261},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.519599974155426},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.499099999666214},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.4869000017642975},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41920000314712524},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4180999994277954}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7620000243186951},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6753000020980835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.631600022315979},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6062999963760376},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5705000162124634},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5688999891281128},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.522599995136261},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.519599974155426},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4002000093460083},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3382999897003174},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.33799999952316284},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29910001158714294},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C86369673","wikidata":"https://www.wikidata.org/wiki/Q1203659","display_name":"Simultaneous localization and mapping","level":4,"score":0.27399998903274536},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.257999986410141},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3613733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3613733","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G385482257","display_name":null,"funder_award_id":"62473362","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4523770373","display_name":null,"funder_award_id":"62303456","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4683116516","display_name":null,"funder_award_id":"CJGJZD20230724092300002","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2128019145","https://openalex.org/W2194775991","https://openalex.org/W2560023338","https://openalex.org/W2963150697","https://openalex.org/W2963892972","https://openalex.org/W2964054038","https://openalex.org/W2988766935","https://openalex.org/W3034597466","https://openalex.org/W3035398346","https://openalex.org/W3045003611","https://openalex.org/W3090584485","https://openalex.org/W3107992529","https://openalex.org/W3119574651","https://openalex.org/W3141954417","https://openalex.org/W3163945288","https://openalex.org/W3202459445","https://openalex.org/W3202538459","https://openalex.org/W4226321491","https://openalex.org/W4226409831","https://openalex.org/W4285233964","https://openalex.org/W4312296985","https://openalex.org/W4312497550","https://openalex.org/W4312604533","https://openalex.org/W4312933868","https://openalex.org/W4385245566","https://openalex.org/W4386075656","https://openalex.org/W4386076238","https://openalex.org/W4386320409","https://openalex.org/W4390872210","https://openalex.org/W4390872672","https://openalex.org/W4390873470","https://openalex.org/W4390874213","https://openalex.org/W4392223601","https://openalex.org/W4400726600","https://openalex.org/W4402623738","https://openalex.org/W4402716422","https://openalex.org/W4405785669","https://openalex.org/W4411528087","https://openalex.org/W4413145170","https://openalex.org/W7133249402"],"related_works":[],"abstract_inverted_index":{"Category-level":[0],"6D":[1],"object":[2,68,112,126],"pose":[3,69,215],"estimation":[4,70],"has":[5],"gained":[6],"increasing":[7],"attention":[8,201],"in":[9],"applications":[10],"of":[11,83,104,118,233],"robotic":[12],"manipulation,":[13],"augmented":[14],"reality,":[15],"and":[16,138,208,226],"scene":[17],"understanding,":[18],"due":[19],"to":[20,23,25,86,94,110,152,178],"its":[21],"ability":[22,82],"generalize":[24],"unseen":[26],"instances":[27,56,120],"within":[28,164],"the":[29,38,52,80,124,149,161,165,185,192,203,213,220,223,231],"same":[30,166],"category.":[31,167],"However,":[32],"existing":[33,95],"methods":[34],"struggle":[35],"with":[36,191],"handling":[37],"intra-class":[39],"shape":[40,47,163],"variations":[41],"as":[42,48],"they":[43],"either":[44],"adopt":[45],"mean":[46,162],"priors,":[49],"or":[50],"build":[51],"associations":[53],"among":[54],"different":[55,119],"without":[57],"explicit":[58],"category-shared":[59],"information.":[60,146],"To":[61],"address":[62],"this":[63,169],"problem,":[64],"a":[65,88,102,134,139,171,199],"novel":[66],"category-level":[67],"method":[71,100],"based":[72],"on":[73,123,144,219],"diffusion":[74,84,136],"model":[75,85],"is":[76,176,206],"proposed,":[77],"which":[78,211],"utilize":[79],"generative":[81],"refine":[87],"sparse":[89],"categorical":[90,116],"representation.":[91,182],"In":[92],"contrast":[93],"dense":[96],"correspondence-based":[97],"methods,":[98],"our":[99],"employs":[101],"set":[103],"keypoints":[105,129],"provided":[106],"by":[107,121],"learnable":[108],"queries":[109],"represent":[111],"shape,":[113],"enabling":[114],"better":[115],"representation":[117],"focusing":[122],"representative":[125],"components.":[127],"The":[128],"are":[130],"then":[131],"refined":[132],"through":[133],"forward":[135],"process":[137,142],"reverse":[140],"denoising":[141],"conditioned":[143],"category":[145],"This":[147],"allows":[148],"flexible":[150],"adaption":[151],"various":[153],"instances,":[154],"especially":[155],"for":[156],"those":[157],"that":[158],"deviate":[159],"from":[160,188,195],"On":[168],"basis,":[170],"geometric-semantic":[172],"feature":[173,181,205],"fusion":[174],"module":[175],"presented":[177],"enhance":[179],"keypoint":[180,204],"By":[183],"integrating":[184],"geometric":[186],"information":[187],"point":[189],"cloud":[190],"high-level":[193],"semantics":[194],"RGB":[196],"image":[197],"using":[198],"two-branch":[200],"mechanism,":[202],"enriched":[207],"deeply":[209],"combined,":[210],"facilitates":[212],"subsequent":[214],"estimation.":[216],"Extensive":[217],"experiments":[218],"REAL275":[221],"dataset,":[222,225],"CAMERA25":[224],"real-world":[227],"complex":[228],"scenarios":[229],"demonstrated":[230],"effectiveness":[232],"proposed":[234],"method.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}