{"id":"https://openalex.org/W7203947701","doi":"https://doi.org/10.48550/arxiv.2608.18996","title":"GrabVG: Graph-Attentive Binding for Visual Grounding in UAV Imagery","display_name":"GrabVG: Graph-Attentive Binding for Visual Grounding in UAV Imagery","publication_year":2026,"publication_date":"2026-08-19","ids":{"openalex":"https://openalex.org/W7203947701","doi":"https://doi.org/10.48550/arxiv.2608.18996"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.18996","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18996","pdf_url":"https://arxiv.org/pdf/2608.18996","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.18996","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139570004","display_name":"Chaowei Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Chaowei","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141557901","display_name":"Yan Di","orcid":null,"observed_orcids":[]},"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":"Di, Yan","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/A5139792332","display_name":"Jingjun Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Jingjun","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147698144","display_name":"Baozhe Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Liu, Baozhe","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101311257","display_name":"Jiaxu Tian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian, Jiaxu","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130544639","display_name":"Yuheng Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yuheng","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002446197","display_name":"Guangqian Guo","orcid":"https://orcid.org/0000-0002-8940-1382","observed_orcids":["https://orcid.org/0000-0002-8940-1382"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Guangqian","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122243439","display_name":"Shan Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Shan","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.8568999767303467,"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":0.8568999767303467,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.06480000168085098,"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":0.0340999998152256,"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/visual-grounding","display_name":"visual grounding","score":0.9929999709129333},{"id":"https://openalex.org/keywords/uav-imagery","display_name":"UAV imagery","score":0.9829999804496765},{"id":"https://openalex.org/keywords/bird-s-eye-view","display_name":"bird's-eye view","score":0.8500000238418579},{"id":"https://openalex.org/keywords/graph-attention-mechanism","display_name":"graph attention mechanism","score":0.652999997138977},{"id":"https://openalex.org/keywords/spatial-topological-relationships","display_name":"spatial topological relationships","score":0.7879999876022339},{"id":"https://openalex.org/keywords/crowded-scenes","display_name":"crowded scenes","score":0.6230000257492065},{"id":"https://openalex.org/keywords/object-localization","display_name":"object localization","score":0.37400001287460327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6693999767303467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6571999788284302},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5831999778747559},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5503000020980835},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.506600022315979},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5023999810218811},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.390500009059906},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.33309999108314514},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31610000133514404},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.18996","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18996","pdf_url":"https://arxiv.org/pdf/2608.18996","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.2608.18996","doi":"https://doi.org/10.48550/arxiv.2608.18996","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.18996","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:2608.18996","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18996","pdf_url":"https://arxiv.org/pdf/2608.18996","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203947701.pdf","grobid_xml":"https://content.openalex.org/works/W7203947701.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2798799804","https://openalex.org/W3092462694","https://openalex.org/W4414939355","https://openalex.org/W4417095222","https://openalex.org/W7110805558","https://openalex.org/W7126152037","https://openalex.org/W7128510621","https://openalex.org/W7149016882"],"related_works":["https://openalex.org/W4415314119","https://openalex.org/W7204994236","https://openalex.org/W4390190349","https://openalex.org/W3087365719","https://openalex.org/W4313145013","https://openalex.org/W4416714697","https://openalex.org/W4396576559","https://openalex.org/W4413277671","https://openalex.org/W4402039847","https://openalex.org/W4415708052"],"abstract_inverted_index":{"Visual":[0],"grounding":[1,78,93,103],"in":[2,14,79],"Unmanned":[3],"Aerial":[4],"Vehicle":[5],"(UAV)":[6],"imagery":[7],"aims":[8],"to":[9,19,45,64,76],"localize":[10],"a":[11,20,90,119,147,185],"target":[12,173],"object":[13,124],"complex":[15],"bird's-eye-view":[16],"scenes":[17],"according":[18],"natural":[21],"language":[22],"description.":[23],"However,":[24],"the":[25,196],"abundance":[26],"of":[27,122],"small,":[28],"densely":[29],"distributed,":[30],"and":[31,69,111,130,138,155,162,171,179,191,194,201],"visually":[32],"similar":[33],"objects":[34],"creates":[35],"high":[36],"visual":[37,92,98,153],"redundancy,":[38],"while":[39],"repetitive":[40],"local":[41],"configurations":[42],"give":[43],"rise":[44],"strong":[46],"topological":[47,73,157],"ambiguity.":[48],"Existing":[49],"approaches":[50],"mainly":[51],"focus":[52],"on":[53,177],"visual--language":[54],"feature":[55,113],"alignment":[56],"or":[57],"dense":[58],"contextual":[59],"interaction,":[60],"yet":[61],"they":[62],"struggle":[63],"distinguish":[65],"subtle":[66],"inter-instance":[67,156],"differences":[68],"effectively":[70],"exploit":[71],"spatial":[72,169],"structures,":[74],"leading":[75],"inaccurate":[77],"highly":[80],"crowded":[81],"scenarios.":[82],"To":[83],"address":[84],"these":[85],"challenges,":[86],"we":[87,116],"propose":[88],"$\\textbf{GrabVG}$,":[89],"novel":[91],"framework":[94],"inspired":[95],"by":[96,199],"human":[97],"search.":[99],"GrabVG":[100,183],"explicitly":[101],"decomposes":[102],"into":[104,146],"two":[105],"sequential":[106],"stages:":[107],"$\\textit{preattentive":[108],"hypothesis":[109,132],"search}$":[110],"$\\textit{graph-attentive":[112],"binding}$.":[114],"Specifically,":[115],"first":[117],"generate":[118],"compact":[120],"set":[121],"reliable":[123],"hypotheses":[125,142],"through":[126],"distillation-guided":[127],"proposal":[128],"induction":[129],"text-aware":[131],"filtering,":[133],"substantially":[134],"reducing":[135],"background":[136],"distractions":[137],"semantic":[139],"mismatches.":[140],"These":[141],"are":[143,159],"then":[144],"organized":[145],"sparse":[148],"graph,":[149],"where":[150],"language-guided":[151],"intra-instance":[152],"cues":[154],"relationships":[158],"jointly":[160],"bound":[161],"propagated":[163],"via":[164],"graph":[165],"attention,":[166],"enabling":[167],"efficient":[168],"reasoning":[170],"accurate":[172],"localization.":[174],"Extensive":[175],"experiments":[176],"AerialVG":[178],"AerialSense":[180],"show":[181],"that":[182],"achieves":[184],"favorable":[186],"accuracy--speed":[187],"trade-off,":[188],"reaching":[189],"67.31$\\%$":[190],"80.34$\\%$":[192],"Acc@0.5":[193],"outperforming":[195],"corresponding":[197],"baselines":[198],"10.55":[200],"8.76":[202],"percentage":[203],"points,":[204],"respectively.":[205]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-22T00:00:00"}