{"id":"https://openalex.org/W4415329418","doi":"https://doi.org/10.52202/085713-3700","title":"InstructSAM: A Training-free Framework for Instruction-Oriented Remote Sensing Object Recognition","display_name":"InstructSAM: A Training-free Framework for Instruction-Oriented Remote Sensing Object Recognition","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415329418","doi":"https://doi.org/10.52202/085713-3700"},"language":"en","primary_location":{"id":"doi:10.52202/085713-3700","doi":"https://doi.org/10.52202/085713-3700","is_oa":true,"landing_page_url":"https://doi.org/10.52202/085713-3700","pdf_url":"https://www.proceedings.com/content/085/085713-3700open.pdf","source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.proceedings.com/content/085/085713-3700open.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yijie Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijie Zheng","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100528811","display_name":"Weijie Wu","orcid":"https://orcid.org/0009-0005-4715-1046","observed_orcids":["https://orcid.org/0009-0005-4715-1046","https://orcid.org/0009-0001-4621-7243"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijie Wu","raw_affiliation_strings":["University of the Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685484","display_name":"Qingyun Li","orcid":"https://orcid.org/0000-0003-0274-0304","observed_orcids":["https://orcid.org/0000-0003-0274-0304","https://orcid.org/0009-0003-3338-9067"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyun Li","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101673665","display_name":"Xuehui Wang","orcid":"https://orcid.org/0000-0001-9577-3951","observed_orcids":["https://orcid.org/0000-0001-9577-3951","https://orcid.org/0009-0001-6894-1507"]},"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":"Xuehui Wang","raw_affiliation_strings":["Shanghai Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xu Zhou","raw_affiliation_strings":["University of Wollongong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wollongong","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059014261","display_name":"Aiai Ren","orcid":"https://orcid.org/0009-0007-1808-5347","observed_orcids":["https://orcid.org/0009-0007-1808-5347"]},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Aiai Ren","raw_affiliation_strings":["University of Wollongong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wollongong","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031318875","display_name":"Jun Shen","orcid":"https://orcid.org/0000-0002-9403-7140","observed_orcids":["https://orcid.org/0000-0002-9403-7140","https://orcid.org/0000-0001-7746-5285","https://orcid.org/0000-0001-9348-9324","https://orcid.org/0000-0001-7826-5875"]},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jun Shen","raw_affiliation_strings":["University of Wollongong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wollongong","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755718","display_name":"Long Zhao","orcid":"https://orcid.org/0009-0001-8335-9478","observed_orcids":["https://orcid.org/0009-0001-8335-9478"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Zhao","raw_affiliation_strings":["Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718312","display_name":"Guoqing Li","orcid":"https://orcid.org/0000-0002-5785-2306","observed_orcids":["https://orcid.org/0000-0002-5785-2306"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqing Li","raw_affiliation_strings":["Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043503650","display_name":"Xue Yang","orcid":"https://orcid.org/0000-0002-7084-9101","observed_orcids":["https://orcid.org/0000-0002-7084-9101"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Yang","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7914,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94488738,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"122814","last_page":"122850"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.48969998955726624,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.48969998955726624,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.420199990272522,"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":0.02800000086426735,"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/remote-sensing-imagery","display_name":"remote sensing images","score":0.9440000057220459},{"id":"https://openalex.org/keywords/training-free-framework","display_name":"training-free framework","score":0.7059999704360962},{"id":"https://openalex.org/keywords/earth-observation","display_name":"Earth observation","score":0.6159999966621399},{"id":"https://openalex.org/keywords/large-vision-language-models","display_name":"large vision-language models","score":0.75},{"id":"https://openalex.org/keywords/0-1-integer-programming","display_name":"0-1 integer programming","score":0.9470000267028809},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"semantic similarity","score":0.6209999918937683},{"id":"https://openalex.org/keywords/automatic-annotation","display_name":"automatic annotation","score":0.42500001192092896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8011999726295471},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6518999934196472},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5753999948501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5475999712944031},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5087000131607056},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.49939998984336853},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4399000108242035},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.421999990940094},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.38940000534057617},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3695000112056732},{"id":"https://openalex.org/C39399123","wikidata":"https://www.wikidata.org/wiki/Q1348989","display_name":"Earth observation","level":3,"score":0.35269999504089355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.29580000042915344},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C183365957","wikidata":"https://www.wikidata.org/wiki/Q17140402","display_name":"Remote sensing application","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C73752529","wikidata":"https://www.wikidata.org/wiki/Q79872","display_name":"Object-oriented programming","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/085713-3700","doi":"https://doi.org/10.52202/085713-3700","is_oa":true,"landing_page_url":"https://doi.org/10.52202/085713-3700","pdf_url":"https://www.proceedings.com/content/085/085713-3700open.pdf","source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.15818","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15818","pdf_url":"https://arxiv.org/pdf/2505.15818","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.15818","doi":"https://doi.org/10.48550/arxiv.2505.15818","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.15818","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.52202/085713-3700","doi":"https://doi.org/10.52202/085713-3700","is_oa":true,"landing_page_url":"https://doi.org/10.52202/085713-3700","pdf_url":"https://www.proceedings.com/content/085/085713-3700open.pdf","source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G427914820","display_name":null,"funder_award_id":"62506229","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6226388984","display_name":null,"funder_award_id":"25ZR1402268","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415329418.pdf","grobid_xml":"https://content.openalex.org/works/W4415329418.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W3206072662","https://openalex.org/W4296406182","https://openalex.org/W4399759382","https://openalex.org/W4401307635","https://openalex.org/W4404330874","https://openalex.org/W4404569914","https://openalex.org/W4404573363","https://openalex.org/W4404649438","https://openalex.org/W4405172832","https://openalex.org/W4405622406","https://openalex.org/W4406810929","https://openalex.org/W4407794264","https://openalex.org/W4410115177","https://openalex.org/W4410226751","https://openalex.org/W4413156626","https://openalex.org/W4413157547","https://openalex.org/W4414384031","https://openalex.org/W4415158162","https://openalex.org/W4416053382","https://openalex.org/W4416649928","https://openalex.org/W4416727328","https://openalex.org/W6910802054","https://openalex.org/W6947978218","https://openalex.org/W6947991961","https://openalex.org/W7077485857","https://openalex.org/W7134071185","https://openalex.org/W7160080400"],"related_works":["https://openalex.org/W7168250098","https://openalex.org/W7108213194","https://openalex.org/W7127359396","https://openalex.org/W7172273315","https://openalex.org/W4409366960","https://openalex.org/W4391021462","https://openalex.org/W7137077832","https://openalex.org/W7133979990","https://openalex.org/W7171436475","https://openalex.org/W7124159444"],"abstract_inverted_index":{"Language-guided":[0],"object":[1,116,128,181,217],"recognition":[2,218],"in":[3,105,214],"remote":[4,79,106],"sensing":[5,80],"imagery":[6],"is":[7,74,221],"crucial":[8],"for":[9,71,114,132],"largescale":[10],"mapping":[11],"and":[12,18,55,61,86,126,135,188,207],"automated":[13],"data":[14,104],"annotation.However,":[15],"existing":[16],"open-vocabulary":[17],"visual":[19],"grounding":[20],"methods":[21],"rely":[22],"on":[23,160],"explicit":[24],"category":[25],"cues,":[26],"limiting":[27],"their":[28],"ability":[29],"to":[30,94,122,155,195],"handle":[31],"complex":[32],"or":[33,167],"implicit":[34],"queries":[35],"that":[36,164],"require":[37],"advanced":[38],"reasoning.To":[39],"address":[40],"this":[41],"issue,":[42],"we":[43,108],"introduce":[44],"a":[45,111,140],"new":[46],"suite":[47],"of":[48,100,180,202],"tasks,":[49,205],"including":[50],"Instruction-Oriented":[51],"Object":[52],"Counting,":[53],"Detection,":[54],"Segmentation":[56],"(InstructCDS),":[57],"covering":[58],"open-vocabulary,":[59],"open-ended,":[60],"open-subclass":[62],"scenarios.We":[63],"further":[64],"present":[65],"EarthInstruct,":[66],"the":[67,98,200,203],"first":[68],"InstructCDS":[69],"benchmark":[70],"earth":[72],"observation.It":[73],"constructed":[75],"from":[76],"two":[77],"diverse":[78],"datasets":[81],"with":[82,148],"varying":[83],"spatial":[84],"resolutions":[85],"annotation":[87],"rules":[88],"across":[89,171],"20":[90],"categories,":[91],"necessitating":[92],"models":[93,121],"interpret":[95,123],"dataset-specific":[96],"instructions.Given":[97],"scarcity":[99],"semantically":[101],"rich":[102],"labeled":[103],"sensing,":[107],"propose":[109],"InstructSAM,":[110],"training-free":[112],"framework":[113],"instruction-driven":[115],"recognition.InstructSAM":[117],"leverages":[118],"large":[119],"vision-language":[120],"user":[124],"instructions":[125],"estimate":[127],"counts,":[129],"employs":[130],"SAM2":[131],"mask":[133],"proposal,":[134],"formulates":[136],"mask-label":[137],"assignment":[138],"as":[139],"binary":[141],"integer":[142],"programming":[143],"problem.By":[144],"integrating":[145],"semantic":[146],"similarity":[147],"counting":[149],"constraints,":[150],"InstructSAM":[151,165],"efficiently":[152],"assigns":[153],"categories":[154],"predicted":[156],"masks":[157],"without":[158],"relying":[159],"confidence":[161],"thresholds.Experiments":[162],"demonstrate":[163],"matches":[166],"surpasses":[168],"specialized":[169],"baselines":[170],"multiple":[172],"tasks":[173],"while":[174],"maintaining":[175],"near-constant":[176],"inference":[177],"time":[178],"regardless":[179],"count,":[182],"reducing":[183],"output":[184],"tokens":[185],"by":[186,191],"89%":[187],"overall":[189],"runtime":[190],"over":[192],"32%":[193],"compared":[194],"direct":[196],"generation":[197],"approaches.We":[198],"believe":[199],"contributions":[201],"proposed":[204],"benchmark,":[206],"effective":[208],"approach":[209],"will":[210],"advance":[211],"future":[212],"research":[213],"developing":[215],"versatile":[216],"systems.The":[219],"code":[220],"available":[222],"at":[223],"https://VoyagerXvoyagerx.github.io/InstructSAM/.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2025-10-19T00:00:00"}