{"id":"https://openalex.org/W4403637278","doi":"https://doi.org/10.1145/3681769.3698578","title":"Making Archives Searchable: Vision-Language Models for Classification of Historical Aerial Imagery","display_name":"Making Archives Searchable: Vision-Language Models for Classification of Historical Aerial Imagery","publication_year":2024,"publication_date":"2024-10-22","ids":{"openalex":"https://openalex.org/W4403637278","doi":"https://doi.org/10.1145/3681769.3698578"},"language":"en","primary_location":{"id":"doi:10.1145/3681769.3698578","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3681769.3698578","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Searching and Mining Large Collections of Geospatial Data","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3681769.3698578","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094348345","display_name":"Marvin Burges","orcid":"https://orcid.org/0000-0003-1269-0769"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Marvin Burges","raw_affiliation_strings":["Computer Vision Lab, TU Wien, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0003-1269-0769","affiliations":[{"raw_affiliation_string":"Computer Vision Lab, TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074305874","display_name":"Sebastian Zambanini","orcid":"https://orcid.org/0000-0002-3459-8122"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sebastian Zambanini","raw_affiliation_strings":["Computer Vision Lab, TU Wien, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0002-3459-8122","affiliations":[{"raw_affiliation_string":"Computer Vision Lab, TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019162549","display_name":"Robert Sablatnig","orcid":"https://orcid.org/0000-0003-4195-1593"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Robert Sablatnig","raw_affiliation_strings":["Computer Vision Lab, TU Wien, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0003-4195-1593","affiliations":[{"raw_affiliation_string":"Computer Vision Lab, TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145847075"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12364","display_name":"Archaeological Research and Protection","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1912","display_name":"Space and Planetary Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12983","display_name":"Satellite Image Processing and Photogrammetry","score":0.9916999936103821,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7023663520812988},{"id":"https://openalex.org/keywords/aerial-imagery","display_name":"Aerial imagery","score":0.651307225227356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4960211217403412},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37521427869796753},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3605455756187439}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023663520812988},{"id":"https://openalex.org/C2987819851","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial imagery","level":2,"score":0.651307225227356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4960211217403412},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37521427869796753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3605455756187439}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3681769.3698578","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3681769.3698578","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Searching and Mining Large Collections of Geospatial Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3681769.3698578","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3681769.3698578","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Searching and Mining Large Collections of Geospatial Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W3126325715","https://openalex.org/W4281612449","https://openalex.org/W4308803765","https://openalex.org/W4309728497","https://openalex.org/W4362471461","https://openalex.org/W4391615698","https://openalex.org/W4393159564","https://openalex.org/W4394625555","https://openalex.org/W4394938913","https://openalex.org/W4395041667","https://openalex.org/W4403637278"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Historical":[0],"aerial":[1,55],"imagery":[2,56,97],"archives":[3],"contain":[4],"valuable":[5],"geospatial":[6],"data":[7,21],"for":[8,108],"studying":[9],"urban":[10],"development,":[11],"environmental":[12],"changes,":[13],"and":[14,22,26,46,51,75,92,126],"historical":[15,54,96],"events.":[16],"However,":[17],"the":[18,34,95,106],"volume":[19],"of":[20,36,80],"inconsistencies":[23],"in":[24,94],"metadata":[25],"georeferencing":[27],"complicate":[28],"content":[29],"classification.":[30],"This":[31],"paper":[32],"explores":[33],"application":[35],"vision-language":[37],"models,":[38],"such":[39],"as":[40],"RemoteCLIP,":[41],"GRAFT,":[42],"GPT-4o":[43],"mini,":[44],"GeoCHAT,":[45],"RS-LLaVA,":[47],"to":[48,114],"automate":[49],"classification":[50,62],"search":[52],"within":[53],"archives.":[57],"We":[58],"introduce":[59],"a":[60],"novel":[61],"dataset":[63,85],"with":[64,102],"multiple":[65],"annotated":[66],"classes,":[67],"including":[68],"bridges,":[69],"buildings,":[70],"train":[71],"tracks,":[72],"bomb":[73],"craters,":[74],"roads.":[76],"Our":[77],"exploratory":[78],"analysis":[79],"model":[81],"performance":[82],"on":[83,121],"this":[84],"provides":[86],"initial":[87],"insights":[88],"into":[89],"their":[90],"capabilities":[91],"limitations":[93],"context.":[98],"Automating":[99],"image":[100],"tagging":[101],"basic":[103],"descriptors":[104],"lays":[105],"groundwork":[107],"more":[109],"sophisticated":[110],"searches,":[111],"enhancing":[112],"access":[113],"cultural":[115],"heritage.":[116],"Future":[117],"work":[118],"should":[119],"focus":[120],"optimizing":[122],"feature":[123],"map":[124],"storage":[125],"scalability.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
