{"id":"https://openalex.org/W7202214596","doi":"https://doi.org/10.48550/arxiv.2608.09270","title":"GRASP: Granularity-Aware Region Alignment and Semantic Prototype Learning for Fine-Grained Cross-Modal Understanding in Drone Views","display_name":"GRASP: Granularity-Aware Region Alignment and Semantic Prototype Learning for Fine-Grained Cross-Modal Understanding in Drone Views","publication_year":2026,"publication_date":"2026-08-10","ids":{"openalex":"https://openalex.org/W7202214596","doi":"https://doi.org/10.48550/arxiv.2608.09270"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.09270","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.09270","pdf_url":"https://arxiv.org/pdf/2608.09270","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.09270","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011272821","display_name":"Jiahui Cui","orcid":"https://orcid.org/0009-0006-3836-9585","observed_orcids":["https://orcid.org/0009-0006-3836-9585"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Jiahui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133096601","display_name":"Yan Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003050372","display_name":"Kan Wei","orcid":"https://orcid.org/0009-0006-8165-1308","observed_orcids":["https://orcid.org/0009-0006-8165-1308"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Kan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121539856","display_name":"Enze Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Enze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075367869","display_name":"Peirong Zhang","orcid":"https://orcid.org/0000-0002-1857-5473","observed_orcids":["https://orcid.org/0000-0002-1857-5473","https://orcid.org/0009-0003-4171-3234"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Peirong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146541369","display_name":"Lei Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5146519472","display_name":"Yiru Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yiru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9458000063896179,"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":0.9458000063896179,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.049300000071525574,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0027000000700354576,"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/background-clutter","display_name":"background clutter","score":0.5139999985694885},{"id":"https://openalex.org/keywords/image-text-retrieval","display_name":"image-text retrieval","score":0.7860000133514404},{"id":"https://openalex.org/keywords/semantic-perturbation","display_name":"semantic perturbation","score":0.6420000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791100025177002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5712000131607056},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.5666999816894531},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.5570999979972839},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5055000185966492},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3723999857902527},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.31279999017715454},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2897000014781952},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28540000319480896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.257999986410141}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.09270","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.09270","pdf_url":"https://arxiv.org/pdf/2608.09270","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.2608.09270","doi":"https://doi.org/10.48550/arxiv.2608.09270","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.09270","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":"pmh:oai:arXiv.org:2608.09270","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.09270","pdf_url":"https://arxiv.org/pdf/2608.09270","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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7206245064735413}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4409367204","https://openalex.org/W4401537441","https://openalex.org/W4415536608","https://openalex.org/W4417252141","https://openalex.org/W4415880744","https://openalex.org/W7126070602","https://openalex.org/W7167844079","https://openalex.org/W7160822890","https://openalex.org/W4417100129","https://openalex.org/W4416369357"],"abstract_inverted_index":{"Fine-grained":[0],"cross-modal":[1,109,170],"understanding":[2,171],"in":[3,38,74,161,172],"drone":[4,23],"views":[5],"is":[6,178],"essential":[7],"for":[8,140,169],"aerial":[9,173],"vision-language":[10,29],"navigation.":[11],"However,":[12],"the":[13,32,47,58,83,147,151],"inherent":[14],"wide":[15],"field":[16],"of":[17,22],"view":[18],"and":[19,87,150],"overhead":[20],"perspective":[21],"scenarios":[24],"impose":[25],"dual":[26],"challenges":[27],"on":[28,146],"understanding.":[30],"At":[31,57],"macro":[33],"level,":[34,60],"overwhelming":[35],"background":[36,113],"clutter":[37],"visual":[39,118],"representations":[40],"leads":[41],"to":[42,106,116,135],"Cross-Modal":[43],"Focus":[44],"Misalignment,":[45],"where":[46,65],"model":[48],"prioritizes":[49],"global":[50],"environmental":[51],"similarities":[52],"over":[53],"specific":[54],"object":[55],"details.":[56],"micro":[59],"Visual":[61],"Isomorphism":[62],"creates":[63],"ambiguity,":[64],"candidates":[66],"share":[67],"similar":[68],"geometric":[69],"structures":[70],"yet":[71],"differ":[72],"only":[73],"subtle":[75],"attributes.":[76],"To":[77],"address":[78],"these":[79],"challenges,":[80],"we":[81,101,120],"propose":[82,121],"Granularity-Aware":[84],"Region":[85],"Alignment":[86,104],"Semantic":[88,122,131],"Prototype":[89,132],"(GRASP)":[90],"learning":[91],"framework,":[92],"enhancing":[93],"discriminative":[94],"capability":[95],"through":[96],"two":[97],"synergistic":[98],"strategies.":[99],"Specifically,":[100],"introduce":[102],"Region-Focused":[103],"(RFA)":[105],"promote":[107],"object-centric":[108],"alignment":[110],"while":[111],"suppressing":[112],"interference.":[114],"Concurrently,":[115],"tackle":[117],"isomorphism,":[119],"Perturbation":[123],"Enhanced":[124],"Matching":[125],"(SPEM),":[126],"which":[127],"leverages":[128],"a":[129],"foreground-purified":[130],"Codebook":[133],"(SPC)":[134],"construct":[136],"semantically":[137],"perturbed":[138],"negatives":[139],"fine-grained":[141,163],"semantic":[142],"discrimination.":[143],"Extensive":[144],"experiments":[145],"GeoText-1652":[148],"benchmark":[149],"unseen":[152],"ERA":[153],"dataset":[154],"demonstrate":[155],"that":[156],"GRASP":[157],"achieves":[158],"competitive":[159],"performance":[160],"drone-view":[162],"image-text":[164],"retrieval,":[165],"validating":[166],"its":[167],"effectiveness":[168],"scenarios.":[174],"Our":[175],"code":[176],"implementation":[177],"available":[179],"at":[180],"https://github.com/UCAS-JC/GRASP.":[181]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-12T00:00:00"}