{"id":"https://openalex.org/W7131298951","doi":"https://doi.org/10.1109/tase.2026.3667740","title":"Efficient Visual Manipulation Relationship Reasoning With Relationship Attention and Sparse Graph in Robotic Grasping","display_name":"Efficient Visual Manipulation Relationship Reasoning With Relationship Attention and Sparse Graph in Robotic Grasping","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131298951","doi":"https://doi.org/10.1109/tase.2026.3667740"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2026.3667740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3667740","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-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/A5126680584","display_name":"Lu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lu Chen","raw_affiliation_strings":["Institute of Big Data Science and Industry, the Key Laboratory of Evolutionary Science Intelligence of Shanxi Province, and the School of Artificial Intelligence, Shanxi University, Taiyuan, China"],"affiliations":[{"raw_affiliation_string":"Institute of Big Data Science and Industry, the Key Laboratory of Evolutionary Science Intelligence of Shanxi Province, and the School of Artificial Intelligence, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113274188","display_name":"Zhuomao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuomao Li","raw_affiliation_strings":["Institute of Big Data Science and Industry, the Key Laboratory of Evolutionary Science Intelligence of Shanxi Province, and the School of Artificial Intelligence, Shanxi University, Taiyuan, China"],"affiliations":[{"raw_affiliation_string":"Institute of Big Data Science and Industry, the Key Laboratory of Evolutionary Science Intelligence of Shanxi Province, and the School of Artificial Intelligence, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126739689","display_name":"Zhou Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["School of Computer Science, Central China Normal University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Central China Normal University, Wuhan, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084072608","display_name":"Zhenyu Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Lu","raw_affiliation_strings":["School of Automation Science and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Automation Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113241124","display_name":"Huaiyao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaiyao Wang","raw_affiliation_strings":["Institute of Big Data Science and Industry, the Key Laboratory of Evolutionary Science Intelligence of Shanxi Province, and the School of Artificial Intelligence, Shanxi University, Taiyuan, China"],"affiliations":[{"raw_affiliation_string":"Institute of Big Data Science and Industry, the Key Laboratory of Evolutionary Science Intelligence of Shanxi Province, and the School of Artificial Intelligence, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126698170","display_name":"Chenguang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chenguang Yang","raw_affiliation_strings":["Department of Computing, Hong Kong Polytechnic University, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5126680584"],"corresponding_institution_ids":["https://openalex.org/I181877577"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53482183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"5714","last_page":"5731"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5153999924659729,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5153999924659729,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.10050000250339508,"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":0.05350000038743019,"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/leverage","display_name":"Leverage (statistics)","score":0.7555999755859375},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.7289999723434448},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5600000023841858},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5271999835968018},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.3749000132083893},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.3549000024795532},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.35089999437332153},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.3508000075817108}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7555999755859375},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.7289999723434448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6899999976158142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6798999905586243},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5600000023841858},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3898000121116638},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3549000024795532},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3508000075817108},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3343000113964081},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.3059999942779541},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2750000059604645},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2026.3667740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3667740","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1892339738","https://openalex.org/W1986760892","https://openalex.org/W1999156278","https://openalex.org/W2036637075","https://openalex.org/W2090855657","https://openalex.org/W2194775991","https://openalex.org/W2415243675","https://openalex.org/W2479423890","https://openalex.org/W2562637781","https://openalex.org/W2565639579","https://openalex.org/W2754191212","https://openalex.org/W2791992091","https://openalex.org/W2824754393","https://openalex.org/W2886970679","https://openalex.org/W2914433398","https://openalex.org/W2921688541","https://openalex.org/W2950635152","https://openalex.org/W2962766617","https://openalex.org/W2962875890","https://openalex.org/W2963150697","https://openalex.org/W2963654160","https://openalex.org/W2964241181","https://openalex.org/W3004280398","https://openalex.org/W3007627128","https://openalex.org/W3035198432","https://openalex.org/W3096609285","https://openalex.org/W3120238879","https://openalex.org/W3130885760","https://openalex.org/W3138516171","https://openalex.org/W3152893301","https://openalex.org/W3195127674","https://openalex.org/W4200498145","https://openalex.org/W4205403491","https://openalex.org/W4211191796","https://openalex.org/W4312845161","https://openalex.org/W4312936847","https://openalex.org/W4312954194","https://openalex.org/W4319663826","https://openalex.org/W4319783489","https://openalex.org/W4366352717","https://openalex.org/W4381729886","https://openalex.org/W4382366145","https://openalex.org/W4383108207","https://openalex.org/W4384519458","https://openalex.org/W4385245566","https://openalex.org/W4388407473","https://openalex.org/W4388430610","https://openalex.org/W4388624399","https://openalex.org/W4388816994","https://openalex.org/W4389179984","https://openalex.org/W4390871882","https://openalex.org/W4401416278","https://openalex.org/W4401537510","https://openalex.org/W4401567667","https://openalex.org/W4402041279","https://openalex.org/W4405710332","https://openalex.org/W4405785467","https://openalex.org/W4407897347","https://openalex.org/W4408914211","https://openalex.org/W4409013595","https://openalex.org/W4409325968","https://openalex.org/W4409474240","https://openalex.org/W4416214619"],"related_works":[],"abstract_inverted_index":{"Determining":[0],"the":[1,7,88,107,111,122,133,141,165,182,185],"reasonable":[2],"grasping":[3,16,176],"order":[4],"and":[5,33,50,74,94,124,135,158,160],"reducing":[6],"interference":[8],"to":[9,42,85,120],"surrounding":[10],"objects":[11,175],"are":[12,170],"critical":[13],"for":[14],"robotic":[15],"under":[17,177],"mutually-stacked":[18],"scenes.":[19],"However,":[20],"existing":[21],"manipulation":[22,168],"relationship":[23,51,72,78],"reasoning":[24,44,169],"methods":[25],"generally":[26],"predict":[27],"object":[28,39,98,127,163],"relationships":[29,109],"from":[30],"detection":[31,48],"perspective,":[32],"require":[34],"dense":[35],"evaluation":[36,153],"of":[37,116,126,151,184],"all":[38],"pairs,":[40],"leading":[41],"restricted":[43],"accuracy":[45,125],"caused":[46],"by":[47,100],"bias":[49],"class":[52],"imbalance.":[53],"To":[54],"solve":[55],"this":[56],"problem,":[57],"we":[58],"propose":[59],"an":[60],"EFficient":[61],"Visual":[62],"Manipulation":[63],"Relationship":[64],"Reasoning":[65],"Network,":[66],"called":[67],"EF-VMR<sup":[68,143],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[69,144],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>N,":[70],"with":[71,162],"attention":[73,79,83],"sparse":[75],"graph.":[76],"Specifically,":[77],"constructs":[80],"two":[81],"new":[82],"mechanisms":[84],"holistically":[86],"leverage":[87],"correlation":[89],"characteristics":[90],"between":[91],"visual":[92],"features":[93],"semantic":[95],"information":[96],"among":[97],"pairs":[99],"highlighting":[101],"reasoning-specific":[102],"features.":[103],"Sparse":[104],"graph":[105],"infers":[106],"mutual":[108],"within":[110],"scene":[112],"using":[113],"fixed":[114],"number":[115],"strongly-correlated":[117],"triplet":[118],"sets":[119],"improve":[121],"efficiency":[123],"pair":[128],"evaluation.":[129],"Extensive":[130],"experiments":[131],"on":[132,167],"VMRD":[134],"REGRAD":[136],"datasets":[137],"both":[138],"show":[139],"that":[140],"proposed":[142,186],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>N":[145],"achieves":[146],"SOTA":[147],"performance":[148],"in":[149],"terms":[150],"four":[152],"metrics":[154],"(mAP,":[155],"OR,":[156],"OP":[157],"IA),":[159],"compared":[161],"detection,":[164],"improvements":[166],"more":[171],"remarkable.":[172],"The":[173],"stacked":[174],"real-world":[178],"scenarios":[179],"further":[180],"proves":[181],"effectiveness":[183],"method.":[187],"Video:":[188],"https://github.com/LiMing336/VideoDemonstration.":[189]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-25T00:00:00"}