{"id":"https://openalex.org/W7160855047","doi":"https://doi.org/10.48550/arxiv.2605.07178","title":"Masks Can Talk: Extracting Structured Text Information from Single-Modal Images for Remote Sensing Change Detection","display_name":"Masks Can Talk: Extracting Structured Text Information from Single-Modal Images for Remote Sensing Change Detection","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160855047","doi":"https://doi.org/10.48550/arxiv.2605.07178"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.07178","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07178","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.07178","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135866019","display_name":"Kai Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029378855","display_name":"Hangcheng Dong","orcid":"https://orcid.org/0000-0002-4880-6762"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Hang-Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135828476","display_name":"Jiatong Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Jiatong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121972929","display_name":"Zhenkai Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zhenkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069395320","display_name":"Fupeng Wei","orcid":"https://orcid.org/0000-0002-2337-1483"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Fupeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135835351","display_name":"Wei Zhang","orcid":"https://orcid.org/0009-0004-3200-3246"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.7994999885559082,"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":0.7994999885559082,"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/T10757","display_name":"Geographic Information Systems Studies","score":0.07360000163316727,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.0210999995470047,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.7336000204086304},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7232000231742859},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5450000166893005},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5246999859809875},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4726000130176544},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45080000162124634},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.3458999991416931},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.3434999883174896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890999913215637},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.7336000204086304},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7232000231742859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5942999720573425},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5450000166893005},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5246999859809875},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45080000162124634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42149999737739563},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3707999885082245},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3314000070095062},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.303600013256073},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C2989469682","wikidata":"https://www.wikidata.org/wiki/Q1401207","display_name":"Change analysis","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C36391188","wikidata":"https://www.wikidata.org/wiki/Q1939117","display_name":"Semantic change","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.07178","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07178","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.07178","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07178","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.44956478476524353,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Remote":[0],"sensing":[1,168],"change":[2,62,78,86,121,130,208],"detection":[3,79,209],"is":[4,132,185],"pivotal":[5],"for":[6,171],"urban":[7],"monitoring,":[8],"disaster":[9],"assessment,":[10],"and":[11,46,50,94,100,144,154,194,226,256],"environmental":[12],"resource":[13],"management.":[14],"Yet,":[15],"unimodal":[16],"deep":[17,189],"learning":[18],"methods":[19,235],"frequently":[20],"confuse":[21],"genuine":[22],"semantic":[23,137],"changes":[24,259],"with":[25,76,180],"visually":[26],"similar":[27],"but":[28,39],"irrelevant":[29],"variations.":[30],"Recent":[31],"multimodal":[32,156,178,234],"approaches":[33],"incorporate":[34],"text":[35,149],"as":[36],"auxiliary":[37],"supervision,":[38],"their":[40],"descriptions":[41],"are":[42,64],"either":[43],"semantically":[44],"coarse":[45],"unstructured":[47],"or":[48],"model-generated":[49],"thus":[51],"noisy.":[52],"Critically,":[53],"all":[54],"of":[55,224,229],"them":[56],"overlook":[57],"a":[58,112,136,160,177,181,205,222],"simple":[59],"fact:":[60],"fine-grained":[61],"semantics":[63],"already":[65],"implicitly":[66],"encoded":[67],"in":[68],"the":[69,85,89,97,213],"ground-truth":[70],"mask":[71],"labels":[72,122],"that":[73,114,236,244],"come":[74],"standard":[75],"every":[77],"dataset.":[80],"These":[81],"masks":[82,245],"know":[83],"where":[84],"happened,":[87],"what":[88],"land-cover":[90],"types":[91],"were":[92,104],"before":[93],"after,":[95],"how":[96,101,142,257],"transition":[98],"occurred,":[99],"many":[102,258],"objects":[103],"involved.":[105],"In":[106],"this":[107,217],"paper,":[108],"we":[109,202],"propose":[110],"S2M,":[111],"framework":[113],"obtains":[115],"structured":[116,195],"textual":[117,196],"features":[118,193],"directly":[119],"from":[120],"at":[123],"zero":[124],"additional":[125],"annotation":[126],"cost.":[127],"Specifically,":[128],"each":[129],"region":[131],"automatically":[133],"transcribed":[134],"into":[135,146],"quadruple":[138],"(where,":[139],"what,":[140,253],"how,":[141,255],"many)":[143],"converted":[145],"several":[147],"fixed-template":[148],"descriptions,":[150],"providing":[151],"precise,":[152],"dense,":[153],"noise-free":[155],"supervision.":[157],"We":[158],"adopts":[159],"two-stage":[161],"training":[162],"strategy":[163],"to":[164,187],"fine-tune":[165],"on":[166],"remote":[167],"imagery":[169],"firstly":[170],"robust":[172],"domain-specific":[173],"representation,":[174],"after":[175],"which":[176],"decoder":[179],"bi-directional":[182],"contrastive":[183],"loss":[184],"introduced":[186],"achieve":[188],"alignment":[190],"between":[191],"visual":[192],"embeddings.":[197],"To":[198],"validate":[199],"our":[200],"method,":[201],"construct":[203],"Gaza-Change-v2,":[204],"new":[206],"multi-class":[207],"(MCD)":[210],"dataset":[211],"about":[212],"Gaza":[214],"Strip.":[215],"On":[216],"MCD":[218],"dataset,":[219],"S2M":[220],"achieves":[221],"Sek":[223],"17.80\\%":[225],"an":[227],"F$_{\\text{scd}}$":[228],"66.14\\%,":[230],"notably":[231],"surpassing":[232],"even":[233],"leverage":[237],"large":[238],"language":[239],"models.":[240],"Our":[241],"work":[242],"demonstrates":[243],"can":[246],"indeed":[247],"talk.":[248],"They":[249],"tell":[250],"us":[251],"exactly":[252],"where,":[254],"have":[260],"occurred.":[261]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-12T00:00:00"}