{"id":"https://openalex.org/W4405785249","doi":"https://doi.org/10.1109/iros58592.2024.10802256","title":"Language-driven Grasp Detection with Mask-guided Attention","display_name":"Language-driven Grasp Detection with Mask-guided Attention","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785249","doi":"https://doi.org/10.1109/iros58592.2024.10802256"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5104172302","display_name":"Tuan Van Vo","orcid":null},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Tuan Van Vo","raw_affiliation_strings":["FPT Software AI Center,Vietnam"],"affiliations":[{"raw_affiliation_string":"FPT Software AI Center,Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045614046","display_name":"Baoru Huang","orcid":"https://orcid.org/0000-0002-4421-652X"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Baoru Huang","raw_affiliation_strings":["Imperial College,London,UK"],"affiliations":[{"raw_affiliation_string":"Imperial College,London,UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012599412","display_name":"An Vuong","orcid":"https://orcid.org/0009-0003-8533-9897"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"An Vuong","raw_affiliation_strings":["FPT Software AI Center,Vietnam"],"affiliations":[{"raw_affiliation_string":"FPT Software AI Center,Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023725893","display_name":"Ngan Le","orcid":"https://orcid.org/0000-0003-2571-0511"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ngan Le","raw_affiliation_strings":["University of Arkansas,Department of Computer Science & Computer Engineering,USA"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,Department of Computer Science & Computer Engineering,USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043429366","display_name":"Thieu Vo","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Thieu Vo","raw_affiliation_strings":["National University of Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089006585","display_name":"Anh Nguyen","orcid":"https://orcid.org/0000-0002-1449-211X"},"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"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5104172302"],"corresponding_institution_ids":["https://openalex.org/I109689652"],"apc_list":null,"apc_paid":null,"fwci":1.0484,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78915647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7492","last_page":"7498"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9951000213623047,"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":0.9951000213623047,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.963699996471405,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9383999705314636,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/grasp","display_name":"GRASP","score":0.9073939323425293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7511669993400574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47015833854675293},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10658290982246399}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.9073939323425293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7511669993400574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47015833854675293},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10658290982246399}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":67,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W1999156278","https://openalex.org/W2076363786","https://openalex.org/W2089630413","https://openalex.org/W2109163007","https://openalex.org/W2123435073","https://openalex.org/W2201912979","https://openalex.org/W2564383266","https://openalex.org/W2600030077","https://openalex.org/W2824754393","https://openalex.org/W2953669419","https://openalex.org/W2962875890","https://openalex.org/W2963033241","https://openalex.org/W2963188159","https://openalex.org/W2988823324","https://openalex.org/W3004284873","https://openalex.org/W3035022492","https://openalex.org/W3035198432","https://openalex.org/W3090449556","https://openalex.org/W3096609285","https://openalex.org/W3130885760","https://openalex.org/W3186077919","https://openalex.org/W3200139538","https://openalex.org/W3204657926","https://openalex.org/W3205420310","https://openalex.org/W3216908904","https://openalex.org/W4214612132","https://openalex.org/W4214684415","https://openalex.org/W4221167790","https://openalex.org/W4280533594","https://openalex.org/W4285102324","https://openalex.org/W4306921427","https://openalex.org/W4312310776","https://openalex.org/W4327545837","https://openalex.org/W4383108836","https://openalex.org/W4385431115","https://openalex.org/W4386083025","https://openalex.org/W4388407473","https://openalex.org/W4388918482","https://openalex.org/W4389665991","https://openalex.org/W4389667112","https://openalex.org/W4389667691","https://openalex.org/W4390874280","https://openalex.org/W4394625750","https://openalex.org/W4401413802","https://openalex.org/W4401416788","https://openalex.org/W4402702930","https://openalex.org/W4405078890","https://openalex.org/W4405786915","https://openalex.org/W6736658009","https://openalex.org/W6739901393","https://openalex.org/W6747225742","https://openalex.org/W6755207826","https://openalex.org/W6767853649","https://openalex.org/W6773737242","https://openalex.org/W6781542114","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6788305448","https://openalex.org/W6788620109","https://openalex.org/W6790307280","https://openalex.org/W6791353385","https://openalex.org/W6792275077","https://openalex.org/W6801810553","https://openalex.org/W6850503672","https://openalex.org/W6852884379","https://openalex.org/W6858561505"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W165915117","https://openalex.org/W2059402478","https://openalex.org/W2123347777","https://openalex.org/W2963326767"],"abstract_inverted_index":{"Grasp":[0],"detection":[1,31,51,80],"is":[2],"an":[3],"essential":[4],"task":[5,35],"in":[6,124],"robotics":[7],"with":[8,17,52,61,113],"various":[9],"industrial":[10],"applications.":[11,98],"However,":[12],"traditional":[13],"methods":[14],"often":[15],"struggle":[16],"occlusions":[18],"and":[19,36,73],"do":[20],"not":[21],"utilize":[22],"language":[23,28,75],"for":[24,48,88,95],"grasping.":[25],"Incorporating":[26],"natural":[27,74],"into":[29],"grasp":[30,50,79,90],"remains":[32],"a":[33,45,85,110,114],"challenging":[34],"largely":[37],"unexplored.":[38],"To":[39],"address":[40],"this":[41],"gap,":[42],"we":[43],"propose":[44],"new":[46,86],"method":[47,104,123],"language-driven":[49,89,96],"mask-guided":[53],"attention":[54,59],"by":[55,109],"utilizing":[56],"the":[57,93,129],"transformer":[58],"mechanism":[60],"semantic":[62],"segmentation":[63,70],"features.":[64],"Our":[65,82],"approach":[66],"integrates":[67],"visual":[68],"data,":[69],"mask":[71],"features,":[72],"instructions,":[76],"significantly":[77],"improving":[78],"accuracy.":[81],"work":[83],"introduces":[84],"framework":[87],"detection,":[91],"paving":[92],"way":[94],"robotic":[97,126],"Intensive":[99],"experiments":[100],"show":[101],"that":[102],"our":[103,122,132],"outperforms":[105],"other":[106],"recent":[107],"baselines":[108],"clear":[111],"margin,":[112],"10.0%":[115],"success":[116],"score":[117],"improvement.":[118],"We":[119],"further":[120],"validate":[121],"real-world":[125],"experiments,":[127],"confirming":[128],"effectiveness":[130],"of":[131],"approach.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}