{"id":"https://openalex.org/W4416749035","doi":"https://doi.org/10.1109/iros60139.2025.11245817","title":"GraspMamba: A Mamba-based Language-driven Grasp Detection Framework with Hierarchical Feature Learning","display_name":"GraspMamba: A Mamba-based Language-driven Grasp Detection Framework with Hierarchical Feature Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749035","doi":"https://doi.org/10.1109/iros60139.2025.11245817"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11245817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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/A5027949822","display_name":"Huy Hoang Nguyen","orcid":"https://orcid.org/0000-0001-7025-8654"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Huy Hoang Nguyen","raw_affiliation_strings":["AIT Austrian Institute of Technology GmbH,Austria"],"affiliations":[{"raw_affiliation_string":"AIT Austrian Institute of Technology GmbH,Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113975723","display_name":"An Vuong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"An Vuong","raw_affiliation_strings":["MBZUAI,Department of Computer Vision,UAE"],"affiliations":[{"raw_affiliation_string":"MBZUAI,Department of Computer Vision,UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101706488","display_name":"Anh Gia-Tuan Nguyen","orcid":"https://orcid.org/0000-0003-3606-4199"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anh Nguyen","raw_affiliation_strings":["University of Liverpool,Department of Computer Science,UK"],"affiliations":[{"raw_affiliation_string":"University of Liverpool,Department of Computer Science,UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089444805","display_name":"Ian Reid","orcid":"https://orcid.org/0000-0001-7790-6423"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ian Reid","raw_affiliation_strings":["MBZUAI,Department of Computer Vision,UAE"],"affiliations":[{"raw_affiliation_string":"MBZUAI,Department of Computer Vision,UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056525701","display_name":"Minh Nhat Vu","orcid":"https://orcid.org/0000-0003-0692-8830"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Minh Nhat Vu","raw_affiliation_strings":["TU Wien,Automation & Control Institute,Austria"],"affiliations":[{"raw_affiliation_string":"TU Wien,Automation & Control Institute,Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027949822"],"corresponding_institution_ids":["https://openalex.org/I132118926"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48258092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15808","last_page":"15815"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9645000100135803,"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":0.9645000100135803,"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":0.007499999832361937,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.0044999998062849045,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.8525999784469604},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7077999711036682},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5885000228881836},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5662999749183655},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.36390000581741333},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3628000020980835},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.3467999994754791}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.8525999784469604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7878999710083008},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674000263214111},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7077999711036682},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5885000228881836},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5662999749183655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4510999917984009},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41440001130104065},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.36390000581741333},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32839998602867126},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.30630001425743103},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11245817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1892339738","https://openalex.org/W2036637075","https://openalex.org/W2076363786","https://openalex.org/W2552579943","https://openalex.org/W2736762515","https://openalex.org/W2962789679","https://openalex.org/W2962821282","https://openalex.org/W2962875890","https://openalex.org/W2963033241","https://openalex.org/W2964120214","https://openalex.org/W3035198432","https://openalex.org/W3091619233","https://openalex.org/W3130885760","https://openalex.org/W3138516171","https://openalex.org/W3186077919","https://openalex.org/W3201312429","https://openalex.org/W3204876017","https://openalex.org/W3207187156","https://openalex.org/W3212847756","https://openalex.org/W4210316419","https://openalex.org/W4280533594","https://openalex.org/W4285102324","https://openalex.org/W4285149223","https://openalex.org/W4312310776","https://openalex.org/W4323065888","https://openalex.org/W4327545837","https://openalex.org/W4383108836","https://openalex.org/W4387092545","https://openalex.org/W4388407473","https://openalex.org/W4388918482","https://openalex.org/W4389667112","https://openalex.org/W4389667691","https://openalex.org/W4390873312","https://openalex.org/W4390874575","https://openalex.org/W4392646392","https://openalex.org/W4399114390","https://openalex.org/W4399154429","https://openalex.org/W4399563339","https://openalex.org/W4399618753","https://openalex.org/W4401413802","https://openalex.org/W4401415287","https://openalex.org/W4401416363","https://openalex.org/W4402660140","https://openalex.org/W4402702930","https://openalex.org/W4402727730","https://openalex.org/W4402899258","https://openalex.org/W4403791510","https://openalex.org/W4404520349","https://openalex.org/W4405078890","https://openalex.org/W4405785249","https://openalex.org/W4405786915","https://openalex.org/W4407168289","https://openalex.org/W4409262789","https://openalex.org/W4409365576","https://openalex.org/W4409367296","https://openalex.org/W4413146579","https://openalex.org/W4413925207","https://openalex.org/W4415797492"],"related_works":[],"abstract_inverted_index":{"Grasp":[0],"detection":[1,41,82],"is":[2],"a":[3,37,109],"fundamental":[4],"robotic":[5,118],"task":[6,21],"critical":[7],"to":[8,51,84],"the":[9,61,71,78],"success":[10],"of":[11,60,73],"many":[12],"industrial":[13],"applications.":[14],"However,":[15],"current":[16],"language-driven":[17,39],"models":[18],"for":[19],"this":[20],"often":[22],"struggle":[23],"with":[24,48],"cluttered":[25],"images,":[26],"lengthy":[27],"textual":[28,65],"descriptions,":[29],"or":[30],"slow":[31],"inference":[32,98,123],"speed.":[33,124],"We":[34,112],"introduce":[35],"GraspMamba,":[36],"new":[38],"grasp":[40,81],"method":[42],"that":[43,103],"employs":[44],"hierarchical":[45],"feature":[46],"fusion":[47,72],"Mamba":[49],"vision":[50,86],"tackle":[52],"these":[53],"challenges.":[54],"By":[55],"leveraging":[56],"rich":[57],"visual":[58],"features":[59,89],"Mamba-based":[62,80],"backbone":[63],"alongside":[64],"information,":[66],"our":[67,114],"approach":[68,115],"effectively":[69],"enhances":[70],"multimodal":[74],"features.":[75],"GraspMamba":[76,104],"represents":[77],"first":[79],"model":[83],"extract":[85],"and":[87,96],"language":[88],"at":[90],"multiple":[91],"scales,":[92],"delivering":[93],"robust":[94],"performance":[95],"rapid":[97],"time.":[99],"Intensive":[100],"experiments":[101],"show":[102],"outperforms":[105],"recent":[106],"methods":[107],"by":[108],"clear":[110],"margin.":[111],"validate":[113],"through":[116],"real-world":[117],"experiments,":[119],"highlighting":[120],"its":[121],"fast":[122]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}