{"id":"https://openalex.org/W4413925353","doi":"https://doi.org/10.1109/icra55743.2025.11128140","title":"RTAGrasp: Learning Task-Oriented Grasping from Human Videos via Retrieval, Transfer, and Alignment","display_name":"RTAGrasp: Learning Task-Oriented Grasping from Human Videos via Retrieval, Transfer, and Alignment","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925353","doi":"https://doi.org/10.1109/icra55743.2025.11128140"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5101338631","display_name":"Wenlong Dong","orcid":"https://orcid.org/0009-0004-4127-2720"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenlong Dong","raw_affiliation_strings":["Southern University of Science and Technology,Shenzhen Key Laboratory of Robotics and Computer Vision,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Shenzhen Key Laboratory of Robotics and Computer Vision,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059542763","display_name":"Dehao Huang","orcid":"https://orcid.org/0009-0006-2693-9309"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dehao Huang","raw_affiliation_strings":["Southern University of Science and Technology,Shenzhen Key Laboratory of Robotics and Computer Vision,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Shenzhen Key Laboratory of Robotics and Computer Vision,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046718186","display_name":"Jiangshan Liu","orcid":"https://orcid.org/0000-0001-7933-5003"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangshan Liu","raw_affiliation_strings":["Southern University of Science and Technology,Department of Electronic and Electrical Engineering,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Department of Electronic and Electrical Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002919496","display_name":"Chao Tang","orcid":"https://orcid.org/0000-0003-1474-3705"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Tang","raw_affiliation_strings":["Southern University of Science and Technology,Shenzhen Key Laboratory of Robotics and Computer Vision,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Shenzhen Key Laboratory of Robotics and Computer Vision,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100430266","display_name":"Hong Zhang","orcid":"https://orcid.org/0000-0002-1677-6132"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Zhang","raw_affiliation_strings":["Southern University of Science and Technology,Shenzhen Key Laboratory of Robotics and Computer Vision,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Shenzhen Key Laboratory of Robotics and Computer Vision,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101338631"],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":5.6118,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96252981,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9918000102043152,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9918000102043152,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9914000034332275,"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/computer-science","display_name":"Computer science","score":0.8156596422195435},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6614325046539307},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6286472082138062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5489615797996521},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.5050404667854309},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42931488156318665},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3952331244945526},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08835193514823914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8156596422195435},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6614325046539307},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6286472082138062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5489615797996521},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.5050404667854309},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42931488156318665},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3952331244945526},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08835193514823914},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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":18,"referenced_works":["https://openalex.org/W1965735313","https://openalex.org/W1991544872","https://openalex.org/W2111651672","https://openalex.org/W2140104899","https://openalex.org/W3034891989","https://openalex.org/W3092297126","https://openalex.org/W3207187156","https://openalex.org/W4312933868","https://openalex.org/W4387092545","https://openalex.org/W4389666604","https://openalex.org/W4390874575","https://openalex.org/W4401414292","https://openalex.org/W4401414545","https://openalex.org/W4402704593","https://openalex.org/W4402753712","https://openalex.org/W4404446892","https://openalex.org/W4405785344","https://openalex.org/W4405787069"],"related_works":["https://openalex.org/W3201126466","https://openalex.org/W4282827391","https://openalex.org/W4405541655","https://openalex.org/W4386828785","https://openalex.org/W3165580226","https://openalex.org/W3135401135","https://openalex.org/W2886688859","https://openalex.org/W3133164560","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Task-oriented":[0],"grasping":[1,32,61,74,103],"(TOG)":[2],"is":[3],"crucial":[4],"for":[5,141],"robots":[6],"to":[7,117,122,165],"accomplish":[8],"manipulation":[9],"tasks,":[10],"requiring":[11],"the":[12,94,99,119,123,133,138,145,152],"determination":[13],"of":[14,93,113,155],"TOG":[15,26,79,120,135,147],"positions":[16,33],"and":[17,55,81,89,108,160,182],"directions.":[18],"Existing":[19],"methods":[20],"either":[21],"rely":[22],"on":[23,144,157,175],"costly":[24],"manual":[25],"annotations":[27],"or":[28,34],"only":[29],"extract":[30],"coarse":[31],"regions":[35],"from":[36,72,105],"human":[37,60,73,102],"demonstrations,":[38],"limiting":[39],"their":[40],"practicality":[41],"in":[42,126],"real-world":[43],"applications.":[44],"To":[45],"address":[46],"these":[47],"limitations,":[48],"we":[49],"introduce":[50],"RTAGrasp,":[51],"a":[52,69,86,90,127,176],"Retrieval,":[53],"Transfer,":[54],"Alignment":[56],"framework":[57],"inspired":[58],"by":[59],"strategies.":[62],"Specifically,":[63],"our":[64],"approach":[65],"first":[66],"effortlessly":[67],"constructs":[68],"robot":[70],"memory":[71,107],"demonstration":[75],"videos,":[76],"extracting":[77],"both":[78,158],"position":[80],"direction":[82],"constraints.":[83],"Then,":[84],"given":[85],"task":[87],"instruction":[88],"visual":[91],"observation":[92],"target":[95,124],"object,":[96],"RTAGrasp":[97,131,156],"retrieves":[98],"most":[100],"similar":[101],"experience":[104],"its":[106,173],"leverages":[109],"semantic":[110],"matching":[111],"capabilities":[112],"vision":[114],"foundation":[115],"models":[116],"transfer":[118],"constraints":[121,136],"object":[125,162],"training-free":[128],"manner.":[129],"Finally,":[130],"aligns":[132],"transferred":[134],"with":[137],"robot's":[139],"action":[140],"execution.":[142],"Evaluations":[143],"public":[146],"benchmark,":[148],"TaskGrasp":[149],"dataset,":[150],"show":[151],"competitive":[153],"performance":[154],"seen":[159],"unseen":[161],"categories":[163],"compared":[164],"existing":[166],"baseline":[167],"methods.":[168],"Real-world":[169],"experiments":[170],"further":[171],"validate":[172],"effectiveness":[174],"robotic":[177],"arm.":[178],"Our":[179],"code,":[180],"appendix,":[181],"video":[183],"are":[184],"available":[185],"at":[186],"https://sites.google.com/view/rtagrasp/home.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}