{"id":"https://openalex.org/W4408353833","doi":"https://doi.org/10.1109/icassp49660.2025.10890042","title":"Enhancing 6D Pose Estimation with Cross-modal Fusion Network and Density-peak Keypoint Localization","display_name":"Enhancing 6D Pose Estimation with Cross-modal Fusion Network and Density-peak Keypoint Localization","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353833","doi":"https://doi.org/10.1109/icassp49660.2025.10890042"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100461475","display_name":"Liming Zhang","orcid":"https://orcid.org/0000-0002-1605-2441"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liming Zhang","raw_affiliation_strings":["Shenzhen Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404130","display_name":"Qing Li","orcid":"https://orcid.org/0000-0002-7930-2145"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["Shenzhen Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059772660","display_name":"Zhenhong Chen","orcid":"https://orcid.org/0009-0005-2440-6261"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhong Chen","raw_affiliation_strings":["Shenzhen Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chuan Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuan Yan","raw_affiliation_strings":["George Mason University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Mason University","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaojiang Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojiang Peng","raw_affiliation_strings":["Shenzhen Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University","institution_ids":["https://openalex.org/I4210152380"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9976999759674072,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9976999759674072,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9936000108718872,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9922999739646912,"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/modal","display_name":"Modal","score":0.6240774393081665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6193100810050964},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5957038402557373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5500725507736206},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.45402792096138},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4537031352519989},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.44930440187454224},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41071173548698425},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35460418462753296},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09986981749534607},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07753822207450867}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6240774393081665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6193100810050964},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5957038402557373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5500725507736206},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.45402792096138},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4537031352519989},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.44930440187454224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41071173548698425},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35460418462753296},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09986981749534607},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07753822207450867},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":29,"referenced_works":["https://openalex.org/W132147841","https://openalex.org/W1505952289","https://openalex.org/W1969868017","https://openalex.org/W2067191022","https://openalex.org/W2130459697","https://openalex.org/W2165835468","https://openalex.org/W2555618208","https://openalex.org/W2753858160","https://openalex.org/W2962888833","https://openalex.org/W2963177347","https://openalex.org/W2963188159","https://openalex.org/W2984844508","https://openalex.org/W3034986117","https://openalex.org/W3035355652","https://openalex.org/W3179923621","https://openalex.org/W3195696128","https://openalex.org/W3197271168","https://openalex.org/W4224931253","https://openalex.org/W4312670700","https://openalex.org/W4313046728","https://openalex.org/W4320036970","https://openalex.org/W4327571420","https://openalex.org/W4390872355","https://openalex.org/W4390873425","https://openalex.org/W4392903769","https://openalex.org/W6637131181","https://openalex.org/W6782262041","https://openalex.org/W6853666707","https://openalex.org/W6858049653"],"related_works":["https://openalex.org/W2123263858","https://openalex.org/W3127959533","https://openalex.org/W4387967917","https://openalex.org/W4387968151","https://openalex.org/W4386925306","https://openalex.org/W3132124459","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2152662039"],"abstract_inverted_index":{"Current":[0],"dual-fusion":[1],"models":[2],"for":[3,112],"6D":[4,119],"pose":[5,120],"estimation":[6,121],"often":[7],"lead":[8],"to":[9,76,87],"increased":[10],"computational":[11,73],"complexity":[12],"and":[13,42,68,79,106],"risk":[14],"of":[15,20,48],"overfitting":[16,43,89],"with":[17],"the":[18,59,81,110],"addition":[19,69],"more":[21],"networks.":[22],"To":[23],"address":[24],"this,":[25],"we":[26,95],"propose":[27],"a":[28,97],"Cross-modal":[29,50],"Fusion":[30,51],"Network":[31],"(CFN),":[32],"which":[33,64],"extracts":[34],"robust":[35],"dual-modal":[36],"features":[37],"while":[38],"reducing":[39],"computation":[40],"energy":[41,74],"risks.":[44],"The":[45],"CFN":[46,126],"consists":[47],"multiple":[49,91,118],"Modules":[52],"(CFM),":[53],"featuring":[54],"two":[55],"key":[56],"components:":[57],"1)":[58],"Spiking-based":[60],"Cross-Attention":[61],"Block":[62,84],"(SCA),":[63],"utilizes":[65],"only":[66],"mask":[67],"operations,":[70],"significantly":[71,128],"lowering":[72],"compared":[75],"traditional":[77],"self-attention;":[78],"2)":[80],"Specificity":[82],"Preserving":[83],"(SPB),":[85],"designed":[86],"mitigate":[88],"from":[90],"CFM":[92],"layers.":[93],"Additionally,":[94],"introduce":[96],"density-peak":[98],"keypoint":[99],"localization":[100],"(DKL)":[101],"method":[102,127],"that":[103,124],"resists":[104],"noise":[105],"sparse":[107],"data,":[108],"eliminating":[109],"need":[111],"iterative":[113],"processes.":[114],"Extensive":[115],"experiments":[116],"on":[117],"benchmarks":[122],"demonstrate":[123],"our":[125],"outperforms":[129],"existing":[130],"state-of-the-art":[131],"approaches.":[132]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}