{"id":"https://openalex.org/W4417003212","doi":"https://doi.org/10.1109/tnnls.2025.3626567","title":"Chain-of-Detection: Enhancing Cross-Granularity Robotic Perception for Object Manipulation","display_name":"Chain-of-Detection: Enhancing Cross-Granularity Robotic Perception for Object Manipulation","publication_year":2025,"publication_date":"2025-12-04","ids":{"openalex":"https://openalex.org/W4417003212","doi":"https://doi.org/10.1109/tnnls.2025.3626567","pmid":"https://pubmed.ncbi.nlm.nih.gov/41343333"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3626567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3626567","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5047923687","display_name":"Tianrun Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrun Xu","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013839754","display_name":"Haichuan Gao","orcid":"https://orcid.org/0000-0002-5161-5326"},"institutions":[{"id":"https://openalex.org/I4210100976","display_name":"BOE Technology Group (China)","ror":"https://ror.org/01cwwvj38","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210100976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haichuan Gao","raw_affiliation_strings":["Beijing QianJue Technology Company Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing QianJue Technology Company Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210100976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079315983","display_name":"Changlin Chen","orcid":"https://orcid.org/0000-0002-1862-2807"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changlin Chen","raw_affiliation_strings":["Department of Precision Machinery and Precision Instrumentation, Institute of Humanoid Robots, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Precision Machinery and Precision Instrumentation, Institute of Humanoid Robots, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330844","display_name":"Yuxuan Li","orcid":"https://orcid.org/0000-0003-0611-0764"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Li","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102714724","display_name":"Shiyuan Xu","orcid":"https://orcid.org/0000-0001-9076-1695"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shiyuan Xu","raw_affiliation_strings":["School of Computing and Data Science, The University of Hong Kong, Pokfulam, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-9076-1695","affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, The University of Hong Kong, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048321911","display_name":"Shangqi Guo","orcid":"https://orcid.org/0000-0003-3181-6881"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangqi Guo","raw_affiliation_strings":["Department of Precision Instruments, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3181-6881","affiliations":[{"raw_affiliation_string":"Department of Precision Instruments, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100352754","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0003-4813-2494"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4813-2494","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5558,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85979433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"37","issue":"4","first_page":"1919","last_page":"1933"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.633899986743927,"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":0.633899986743927,"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":0.13169999420642853,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.06120000034570694,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7325999736785889},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.565500020980835},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5446000099182129},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5368000268936157},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5343999862670898},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4738999903202057},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4505999982357025},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3955000042915344},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.34779998660087585}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7325999736785889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7232999801635742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7129999995231628},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5709999799728394},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.565500020980835},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5446000099182129},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5368000268936157},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5343999862670898},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35600000619888306},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.34779998660087585},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.34709998965263367},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.30469998717308044},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29750001430511475},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3626567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3626567","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:41343333","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41343333","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,"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 neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5220867262","display_name":null,"funder_award_id":"62176133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5406755495","display_name":null,"funder_award_id":"TSI-617560","funder_id":"https://openalex.org/F4320308258","funder_display_name":"Qualcomm"}],"funders":[{"id":"https://openalex.org/F4320308258","display_name":"Qualcomm","ror":"https://ror.org/002zrf773"},{"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"robotic":[1,154,186],"perception,":[2],"cross-granularity":[3,181],"object":[4,29,164],"detection":[5,19,30,60,83,182],"is":[6,190,199],"essential":[7],"for":[8,134,158,162],"identifying":[9],"and":[10,31,45,137,166,183,195],"localizing":[11],"targets":[12],"at":[13,193,201],"varying":[14],"levels":[15],"of":[16,65,151,177],"detail.":[17],"Traditional":[18],"methods":[20],"often":[21],"struggle":[22],"to":[23,38,62,91,126],"bridge":[24],"the":[25,63,75,117,132,175,196],"gap":[26],"between":[27],"coarse":[28,89],"fine-grained":[32,59,92,108,129],"component":[33],"localization,":[34],"limiting":[35],"their":[36],"ability":[37],"associate":[39],"parts,":[40],"such":[41],"as":[42],"a":[43,85],"cup":[44],"its":[46],"handle.":[47],"Vision-language":[48],"models":[49],"(VLMs),":[50],"while":[51],"effective":[52],"in":[53,58,84,106,153,169,179],"spatial":[54],"reasoning,":[55],"face":[56],"challenges":[57],"due":[61],"scarcity":[64],"annotated":[66],"datasets.":[67],"To":[68,110],"address":[69],"these":[70],"issues,":[71],"we":[72,97,114],"first":[73],"propose":[74],"chain-of-detection":[76],"(CoD)":[77],"framework,":[78],"which":[79],"focuses":[80],"on":[81],"guiding":[82],"step-by-step":[86],"manner":[87],"from":[88],"recognition":[90],"localization.":[93],"During":[94],"this":[95,112],"process,":[96],"observe":[98],"that":[99,144],"existing":[100],"detectors":[101],"still":[102],"lack":[103],"sufficient":[104],"capability":[105],"recognizing":[107],"components.":[109],"overcome":[111],"limitation,":[113],"further":[115],"combine":[116],"CoD":[118,178,197],"framework":[119],"with":[120],"Monte":[121],"Carlo":[122],"tree":[123],"search":[124],"(MCTS)":[125],"automatically":[127],"generate":[128],"datasets,":[130],"eliminating":[131],"need":[133],"manual":[135],"labeling":[136],"significantly":[138],"improving":[139],"detector":[140],"performance.":[141],"Experiments":[142],"show":[143],"our":[145],"approach":[146],"achieves":[147],"an":[148],"average":[149],"improvement":[150],"17.31%":[152],"manipulation":[155],"success":[156],"rates":[157],"common":[159],"objects,":[160],"51.39%":[161],"larger":[163],"operations,":[165],"about":[167],"50%":[168],"simulated":[170],"environments.":[171],"These":[172],"results":[173],"demonstrate":[174],"effectiveness":[176],"advancing":[180],"enhancing":[184],"precise":[185],"manipulation.":[187],"The":[188],"implementation":[189],"publicly":[191],"available":[192],"https://github.com/tinnel123666888/CoD":[194],"dataset":[198],"released":[200],"https://huggingface.co/datasets/tinnel123/CoD_dataset.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2025-12-04T00:00:00"}