{"id":"https://openalex.org/W4412524639","doi":"https://doi.org/10.1145/3735014.3735890","title":"Key-Points Based Visual Servo For Accurate Cross-Task Robot Manipulations","display_name":"Key-Points Based Visual Servo For Accurate Cross-Task Robot Manipulations","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4412524639","doi":"https://doi.org/10.1145/3735014.3735890"},"language":"en","primary_location":{"id":"doi:10.1145/3735014.3735890","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3735014.3735890","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Big Data Mining and Information Processing","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/A5108946445","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0003-4266-0376"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["SJTU Paris Elite Institute of Technology, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"SJTU Paris Elite Institute of Technology, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036417472","display_name":"Zhuoli Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093776","display_name":"DHC Software (China)","ror":"https://ror.org/00kn8e190","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093776"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoli Xie","raw_affiliation_strings":["CoreNetic.AI Co., Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"CoreNetic.AI Co., Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210093776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012109138","display_name":"Genliang Chen","orcid":"https://orcid.org/0000-0002-1011-2116"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Genliang Chen","raw_affiliation_strings":["School of Mechincal Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Mechincal Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108946445"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17499595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10531","display_name":"Advanced Vision and Imaging","score":0.9994999766349792,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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":0.7573128938674927},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.7467706799507141},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6741931438446045},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6532384157180786},{"id":"https://openalex.org/keywords/servo","display_name":"Servo","score":0.606019914150238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46809887886047363},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43042951822280884},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3337318003177643},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12285372614860535},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0719878077507019}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573128938674927},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7467706799507141},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6741931438446045},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6532384157180786},{"id":"https://openalex.org/C107354338","wikidata":"https://www.wikidata.org/wiki/Q1937153","display_name":"Servo","level":2,"score":0.606019914150238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46809887886047363},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43042951822280884},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3337318003177643},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12285372614860535},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0719878077507019},{"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:10.1145/3735014.3735890","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3735014.3735890","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Big Data Mining and Information Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1677409904","https://openalex.org/W2056114668","https://openalex.org/W2151103935","https://openalex.org/W2788822937","https://openalex.org/W2964270628","https://openalex.org/W2990138404","https://openalex.org/W3045988483","https://openalex.org/W3133026276","https://openalex.org/W4251194397","https://openalex.org/W4401414814","https://openalex.org/W4401416102","https://openalex.org/W4402660140"],"related_works":["https://openalex.org/W2140798747","https://openalex.org/W2948169060","https://openalex.org/W2730112582","https://openalex.org/W2110696645","https://openalex.org/W2358580169","https://openalex.org/W2111347279","https://openalex.org/W3213722473","https://openalex.org/W2110944602","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Key-points":[0],"serve":[1],"as":[2],"critical":[3],"visual":[4],"features":[5],"for":[6,12,133],"robotic":[7],"manipulation,":[8],"yet":[9],"their":[10],"potential":[11],"guiding":[13],"robots":[14,137],"to":[15,41,52,62,68],"handle":[16],"objects":[17],"and":[18,90,95,109,129,135],"generalize":[19],"across":[20,87,112],"tasks":[21,89],"remains":[22],"underexplored.":[23],"In":[24],"this":[25,123],"work,":[26],"we":[27],"propose":[28],"a":[29,36,55,81],"key-point":[30,66],"based":[31],"servoing":[32],"framework":[33],"that":[34,85,99],"leverages":[35],"pre-trained":[37],"Vision":[38],"Transformer":[39],"(ViT)":[40],"extract":[42],"semantically":[43],"rich":[44],"key-points":[45,117],"from":[46],"images.":[47],"Unlike":[48],"prior":[49],"works":[50],"limited":[51],"known":[53],"objects,":[54],"generic":[56],"lightweight":[57],"neural":[58],"network":[59,79],"is":[60],"trained":[61],"directly":[63],"map":[64],"2D":[65],"displacements":[67],"3D":[69],"Cartesian-space":[70],"servo":[71,120],"commands,":[72],"bypassing":[73],"explicit":[74],"perspective":[75],"geometry":[76],"modeling.":[77],"This":[78],"learns":[80],"unified":[82],"2D-to-3D":[83],"correspondence":[84],"generalizes":[86],"diverse":[88],"scenarios.":[91],"Experiments":[92],"in":[93],"simulation":[94],"real-world":[96],"setups":[97],"demonstrate":[98],"our":[100],"method":[101],"achieves":[102],"higher":[103],"precision":[104],"than":[105],"optimization-based":[106],"pose":[107],"estimation":[108],"better":[110],"generalization":[111],"unseen":[113],"tasks.":[114],"By":[115],"bridging":[116],"with":[118],"task-agnostic":[119],"command":[121],"prediction,":[122],"work":[124],"advances":[125],"feature-based":[126],"manipulation":[127],"research":[128],"offers":[130],"practical":[131],"solutions":[132],"logistics":[134],"service":[136],"handling":[138],"unstructured":[139],"objects.":[140]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}