{"id":"https://openalex.org/W4386160361","doi":"https://doi.org/10.1109/icarm58088.2023.10218865","title":"Object-Centric Inference for Language Conditioned Placement: A Foundation Model based Approach","display_name":"Object-Centric Inference for Language Conditioned Placement: A Foundation Model based Approach","publication_year":2023,"publication_date":"2023-07-08","ids":{"openalex":"https://openalex.org/W4386160361","doi":"https://doi.org/10.1109/icarm58088.2023.10218865"},"language":"en","primary_location":{"id":"doi:10.1109/icarm58088.2023.10218865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarm58088.2023.10218865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","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/A5047537243","display_name":"Zhixuan Xu","orcid":"https://orcid.org/0000-0001-7335-9717"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhixuan Xu","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062930488","display_name":"Kechun Xu","orcid":"https://orcid.org/0000-0002-3632-917X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kechun Xu","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019081110","display_name":"Rong Xiong","orcid":"https://orcid.org/0000-0001-9318-9014"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Xiong","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100371992","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0002-0981-935X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047537243"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.4913,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65176879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"203","last_page":"208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.994700014591217,"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":0.9771000146865845,"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":0.8212093710899353},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6872556209564209},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.687232494354248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6199430227279663},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6146183013916016},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5964434742927551},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5701380372047424},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5606311559677124},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5483192205429077},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5363895297050476},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4441465735435486},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4371830224990845},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.41299062967300415},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4057391285896301}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212093710899353},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6872556209564209},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.687232494354248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6199430227279663},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6146183013916016},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5964434742927551},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5701380372047424},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5606311559677124},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5483192205429077},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5363895297050476},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4441465735435486},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4371830224990845},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41299062967300415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4057391285896301},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarm58088.2023.10218865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarm58088.2023.10218865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2489434015","https://openalex.org/W3091332498","https://openalex.org/W3166396011","https://openalex.org/W3186412961","https://openalex.org/W3203511201","https://openalex.org/W3205789812","https://openalex.org/W3207181464","https://openalex.org/W3207899548","https://openalex.org/W3210940825","https://openalex.org/W4200150166","https://openalex.org/W4224912544","https://openalex.org/W4226352076","https://openalex.org/W4283218993","https://openalex.org/W4285102264","https://openalex.org/W4292779060","https://openalex.org/W4383108836","https://openalex.org/W6723035356","https://openalex.org/W6773232095","https://openalex.org/W6778883912","https://openalex.org/W6785308759","https://openalex.org/W6791353385","https://openalex.org/W6801810553","https://openalex.org/W6801948084","https://openalex.org/W6810640255","https://openalex.org/W6811467201","https://openalex.org/W6839390831"],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W2793937822","https://openalex.org/W2790817834","https://openalex.org/W2220552745","https://openalex.org/W2777605427"],"abstract_inverted_index":{"We":[0,54],"focus":[1],"on":[2,29,39],"the":[3,19,40,65,118],"task":[4],"of":[5,42,51,91],"language-conditioned":[6],"object":[7],"placement,":[8,72],"in":[9,23],"which":[10,73],"a":[11,87],"robot":[12],"should":[13],"generate":[14],"placements":[15],"that":[16,59,82],"satisfy":[17],"all":[18],"spatial":[20,69],"relational":[21],"constraints":[22],"language":[24,31],"instructions.":[25,108],"Previous":[26],"works":[27],"based":[28],"rule-based":[30],"parsing":[32],"or":[33,47],"scene-centric":[34],"visual":[35],"representation":[36],"have":[37],"restrictions":[38],"form":[41],"instructions":[43],"and":[44,68,78,107],"reference":[45,66],"objects":[46,67,106],"require":[48],"large":[49],"amounts":[50],"training":[52,113],"data.":[53],"propose":[55],"an":[56],"object-centric":[57],"framework":[58],"leverages":[60],"foundation":[61],"models":[62],"to":[63,103],"ground":[64],"relations":[70],"for":[71],"is":[74],"more":[75],"sample":[76],"efficient":[77],"generalizable.":[79],"Experiments":[80],"indicate":[81],"our":[83,99],"model":[84],"can":[85],"achieve":[86],"97.75%":[88],"success":[89],"rate":[90],"placement":[92],"with":[93,110],"only":[94,111],"~0.26M":[95],"trainable":[96],"parameters.":[97],"Besides,":[98],"method":[100],"generalizes":[101],"better":[102],"both":[104],"unseen":[105],"Moreover,":[109],"25%":[112],"data,":[114],"we":[115],"still":[116],"outperform":[117],"top":[119],"competing":[120],"approach.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}