{"id":"https://openalex.org/W4383108207","doi":"https://doi.org/10.1109/icra48891.2023.10161450","title":"MMRDN: Consistent Representation for Multi-View Manipulation Relationship Detection in Object-Stacked Scenes","display_name":"MMRDN: Consistent Representation for Multi-View Manipulation Relationship Detection in Object-Stacked Scenes","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108207","doi":"https://doi.org/10.1109/icra48891.2023.10161450"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161450","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra48891.2023.10161450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5102991090","display_name":"Han Wang","orcid":"https://orcid.org/0000-0003-1026-7609"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Han Wang","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics Xi&#x0027;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Application,Xi&#x0027;an,Shaanxi,China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics Xi&#x0027;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Application,Xi&#x0027;an,Shaanxi,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100661885","display_name":"Jiayuan Zhang","orcid":"https://orcid.org/0000-0002-1985-2938"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayuan Zhang","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics Xi&#x0027;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Application,Xi&#x0027;an,Shaanxi,China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics Xi&#x0027;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Application,Xi&#x0027;an,Shaanxi,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101790448","display_name":"Lipeng Wan","orcid":"https://orcid.org/0000-0002-8310-0837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lipeng Wan","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics Xi&#x0027;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Application,Xi&#x0027;an,Shaanxi,China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics Xi&#x0027;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Application,Xi&#x0027;an,Shaanxi,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387334","display_name":"Xingyu Chen","orcid":"https://orcid.org/0000-0001-8211-6880"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingyu Chen","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics Xi&#x0027;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Application,Xi&#x0027;an,Shaanxi,China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics Xi&#x0027;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Application,Xi&#x0027;an,Shaanxi,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006277484","display_name":"Xuguang Lan","orcid":"https://orcid.org/0000-0002-3422-944X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuguang Lan","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics Xi&#x0027;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Application,Xi&#x0027;an,Shaanxi,China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics Xi&#x0027;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Application,Xi&#x0027;an,Shaanxi,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics Xi&#x0027;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Application,Xi&#x0027;an,Shaanxi,China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics Xi&#x0027;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Application,Xi&#x0027;an,Shaanxi,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102991090"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5426,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64961905,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3831","last_page":"3837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9990000128746033,"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":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7983572483062744},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.68076092004776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6714696884155273},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6415423154830933},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.6272901296615601},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5526264905929565},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48129239678382874},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.45405250787734985},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4482649266719818},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4374714493751526},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4261776804924011},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3321640193462372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7983572483062744},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.68076092004776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6714696884155273},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6415423154830933},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.6272901296615601},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5526264905929565},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48129239678382874},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.45405250787734985},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4482649266719818},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4374714493751526},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4261776804924011},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3321640193462372},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161450","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra48891.2023.10161450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2898251792","display_name":null,"funder_award_id":"62125305,62088102,61973246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1588424744","https://openalex.org/W2014276990","https://openalex.org/W2069446074","https://openalex.org/W2105523772","https://openalex.org/W2137901802","https://openalex.org/W2145001205","https://openalex.org/W2158498053","https://openalex.org/W2164943005","https://openalex.org/W2560674852","https://openalex.org/W2625715238","https://openalex.org/W2803437649","https://openalex.org/W2909502737","https://openalex.org/W2914433398","https://openalex.org/W2963150697","https://openalex.org/W2981720610","https://openalex.org/W3003356397","https://openalex.org/W3004003273","https://openalex.org/W3207888596","https://openalex.org/W4205403491","https://openalex.org/W4214501771","https://openalex.org/W4287263085","https://openalex.org/W4312935973","https://openalex.org/W4312954194","https://openalex.org/W6639480849","https://openalex.org/W6675134712","https://openalex.org/W6675865240","https://openalex.org/W6680688123","https://openalex.org/W6682124274","https://openalex.org/W6738819434","https://openalex.org/W6751818914","https://openalex.org/W6785723591"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W2657478029","https://openalex.org/W4248427955","https://openalex.org/W2106333554","https://openalex.org/W2626503888","https://openalex.org/W2037306763","https://openalex.org/W2080808138","https://openalex.org/W2129483190"],"abstract_inverted_index":{"Manipulation":[0],"relationship":[1,35,179],"detection":[2],"(MRD)":[3],"aims":[4],"to":[5,9,19,121,175,213,215],"guide":[6],"the":[7,13,21,100,113,123,133,148,157,165,177,185,193],"robot":[8],"grasp":[10],"objects":[11],"in":[12,27,51,54,63,196],"right":[14],"order,":[15],"which":[16,48,89,155],"is":[17,71,90,211],"important":[18],"ensure":[20],"safety":[22],"and":[23,94,111,170],"reliability":[24],"of":[25,68,118,129,140,151,160,167,180],"grasping":[26],"object":[28,153],"stacked":[29],"scenes.":[30],"Previous":[31],"works":[32],"infer":[33],"manipulation":[34],"by":[36,92,208],"deep":[37],"neural":[38],"network":[39,87],"trained":[40,91,207],"with":[41,115],"data":[42,58,102,172,210],"collected":[43],"from":[44,103,147],"a":[45,66,79,107,116,138],"predefined":[46],"view,":[47],"has":[49],"limitation":[50],"visual":[52],"dislocation":[53],"unstructured":[55],"environments.":[56],"Multi-view":[57],"provide":[59],"more":[60],"comprehensive":[61],"information":[62,131],"space,":[64],"while":[65],"challenge":[67],"multi-view":[69,81,85,96,168,197],"MRD":[70,86,198],"domain":[72],"shift.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77,136],"propose":[78],"novel":[80],"fusion":[82],"framework,":[83],"namely":[84],"(MMRDN),":[88],"2D":[93,101,169],"3D":[95,134,171],"data.":[97],"We":[98],"project":[99],"different":[104],"views":[105],"into":[106],"common":[108],"hidden":[109],"space":[110],"fit":[112],"embeddings":[114],"set":[117,139],"Von-Mises-Fisher":[119],"distributions":[120],"learn":[122],"consistent":[124],"representations.":[125],"Besides,":[126],"taking":[127],"advantage":[128],"position":[130,159],"within":[132],"data,":[135],"select":[137],"<tex>$K$</tex>":[141],"Maximum":[142],"Vertical":[143],"Neighbors":[144],"(KMVN)":[145],"points":[146],"point":[149],"cloud":[150],"each":[152],"pair,":[154],"encodes":[156],"relative":[158],"these":[161],"two":[162],"objects.":[163,181],"Finally,":[164],"features":[166],"are":[173],"concatenated":[174],"predict":[176],"pairwise":[178],"Experimental":[182],"results":[183,201],"on":[184],"challenging":[186],"REGRAD":[187],"dataset":[188],"show":[189],"that":[190,204],"MMRDN":[191],"outperforms":[192],"state-of-the-art":[194],"methods":[195],"tasks.":[199],"The":[200],"also":[202],"demonstrate":[203],"our":[205],"model":[206],"synthetic":[209],"capable":[212],"transfer":[214],"real-world":[216],"scenarios.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}