{"id":"https://openalex.org/W4408354366","doi":"https://doi.org/10.1109/icassp49660.2025.10889192","title":"Prompting DirectSAM for Semantic Contour Extraction in Remote Sensing Images","display_name":"Prompting DirectSAM for Semantic Contour Extraction in Remote Sensing Images","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354366","doi":"https://doi.org/10.1109/icassp49660.2025.10889192"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5109643500","display_name":"Shiyu Miao","orcid":"https://orcid.org/0009-0006-1588-4760"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyu Miao","raw_affiliation_strings":["Hohai University,College of Computer Science and Software Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hohai University,College of Computer Science and Software Engineering,Nanjing,China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020620488","display_name":"Delong Chen","orcid":"https://orcid.org/0000-0002-8172-2894"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Delong Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology,Hong Kong SAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Hong Kong SAR","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371024","display_name":"Fan Liu","orcid":"https://orcid.org/0000-0001-8746-9845"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Liu","raw_affiliation_strings":["Hohai University,College of Computer Science and Software Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hohai University,College of Computer Science and Software Engineering,Nanjing,China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035458299","display_name":"Chuanyi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanyi Zhang","raw_affiliation_strings":["Hohai University,College of Computer Science and Software Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hohai University,College of Computer Science and Software Engineering,Nanjing,China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749023","display_name":"Yanhui Gu","orcid":"https://orcid.org/0000-0002-8838-3186"},"institutions":[{"id":"https://openalex.org/I152031979","display_name":"Nanjing Normal University","ror":"https://ror.org/036trcv74","country_code":"CN","type":"education","lineage":["https://openalex.org/I152031979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhui Gu","raw_affiliation_strings":["Nanjing Normal University,School of Computer and Electronic Information,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing Normal University,School of Computer and Electronic Information,Nanjing,China","institution_ids":["https://openalex.org/I152031979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059221217","display_name":"Shengjie Guo","orcid":"https://orcid.org/0000-0001-7365-5487"},"institutions":[{"id":"https://openalex.org/I152031979","display_name":"Nanjing Normal University","ror":"https://ror.org/036trcv74","country_code":"CN","type":"education","lineage":["https://openalex.org/I152031979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengjie Guo","raw_affiliation_strings":["Nanjing Normal University,School of Computer and Electronic Information,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing Normal University,School of Computer and Electronic Information,Nanjing,China","institution_ids":["https://openalex.org/I152031979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100781212","display_name":"Jun Zhou","orcid":"https://orcid.org/0000-0001-5822-8233"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jun Zhou","raw_affiliation_strings":["Griffith University,School of Information and Communication Technology,Queensland,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Griffith University,School of Information and Communication Technology,Queensland,Australia","institution_ids":["https://openalex.org/I11701301"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T12983","display_name":"Satellite Image Processing and Photogrammetry","score":0.9574999809265137,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9466000199317932,"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":0.7686058282852173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5917391180992126},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5664246678352356},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5055086612701416},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4460596740245819},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.3489772379398346},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3243706226348877},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3205321431159973},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.18270960450172424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686058282852173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5917391180992126},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5664246678352356},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5055086612701416},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4460596740245819},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3489772379398346},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3243706226348877},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3205321431159973},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.18270960450172424},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W845365781","https://openalex.org/W2031489346","https://openalex.org/W2065429801","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2276393162","https://openalex.org/W2302548814","https://openalex.org/W2340897893","https://openalex.org/W2798556392","https://openalex.org/W2804199516","https://openalex.org/W2896457183","https://openalex.org/W2953881420","https://openalex.org/W3121754326","https://openalex.org/W3163999715","https://openalex.org/W3172435473","https://openalex.org/W3211490618","https://openalex.org/W4200631575","https://openalex.org/W4241071816","https://openalex.org/W4290043210","https://openalex.org/W4312956471","https://openalex.org/W4313015712","https://openalex.org/W4321793403","https://openalex.org/W4390874575","https://openalex.org/W4392397297","https://openalex.org/W4394811128","https://openalex.org/W4394938913","https://openalex.org/W4399693831","https://openalex.org/W6763251565","https://openalex.org/W6766978945","https://openalex.org/W6791353385","https://openalex.org/W6799579066","https://openalex.org/W6809885388","https://openalex.org/W6811013733"],"related_works":["https://openalex.org/W2601157893","https://openalex.org/W2373006798","https://openalex.org/W2131735617","https://openalex.org/W2056912418","https://openalex.org/W2033213769","https://openalex.org/W4312376745","https://openalex.org/W2136016640","https://openalex.org/W2049538278","https://openalex.org/W2886173746","https://openalex.org/W4200043248"],"abstract_inverted_index":{"The":[0],"Direct":[1],"Segment":[2],"Anything":[3],"Model":[4],"(DirectSAM)":[5],"excels":[6],"in":[7,54,142],"class-agnostic":[8],"contour":[9,28,92],"extraction.":[10,93],"In":[11],"this":[12],"paper,":[13],"we":[14,86],"explore":[15],"its":[16],"use":[17],"by":[18],"applying":[19],"it":[20,102,151],"to":[21,123],"optical":[22],"remote":[23,89],"sensing":[24,90],"imagery,":[25],"where":[26],"semantic":[27,91],"extraction\u2014such":[29],"as":[30],"identifying":[31],"buildings,":[32],"road":[33],"networks,":[34],"and":[35,119,145,148],"coastlines-holds":[36],"significant":[37],"practical":[38],"value.":[39],"Those":[40],"applications":[41],"are":[42],"currently":[43],"handled":[44],"via":[45],"training":[46],"specialized":[47],"small":[48,52],"models":[49],"separately":[50],"on":[51,131],"datasets":[53],"each":[55],"domain.":[56],"We":[57,138],"introduce":[58],"a":[59,83,113,116],"foundation":[60],"model":[61],"derived":[62],"from":[63,76,82],"DirectSAM,":[64],"termed":[65],"DirectSAM-RS,":[66],"which":[67,127],"not":[68],"only":[69],"inherits":[70],"the":[71,124,140],"strong":[72],"segmentation":[73],"capability":[74],"acquired":[75],"natural":[77],"images,":[78],"but":[79],"also":[80],"benefits":[81],"large-scale":[84],"dataset":[85,95],"created":[87],"for":[88],"This":[94],"comprises":[96],"over":[97],"34k":[98],"image-text-contour":[99],"triplets,":[100],"making":[101],"at":[103],"least":[104],"30":[105],"times":[106],"larger":[107],"than":[108],"individual":[109],"dataset.":[110],"DirectSAM-RS":[111,141],"integrates":[112],"prompter":[114],"module:":[115],"text":[117],"encoder":[118],"cross-attention":[120],"layers":[121],"attached":[122],"DirectSAM":[125],"architecture,":[126],"allows":[128],"flexible":[129],"conditioning":[130],"target":[132],"class":[133],"labels":[134],"or":[135],"referring":[136],"expressions.":[137],"evaluate":[139],"both":[143],"zero-shot":[144],"fine-tuning":[146],"setting,":[147],"demonstrate":[149],"that":[150],"achieves":[152],"state-of-the-art":[153],"performance":[154],"across":[155],"several":[156],"downstream":[157],"benchmarks.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}