{"id":"https://openalex.org/W4416191117","doi":"https://doi.org/10.48550/arxiv.2511.08369","title":"Text-based Aerial-Ground Person Retrieval","display_name":"Text-based Aerial-Ground Person Retrieval","publication_year":2025,"publication_date":"2025-11-11","ids":{"openalex":"https://openalex.org/W4416191117","doi":"https://doi.org/10.48550/arxiv.2511.08369"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2511.08369","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.08369","pdf_url":"https://arxiv.org/pdf/2511.08369","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.08369","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101599867","display_name":"Xinyu Zhou","orcid":"https://orcid.org/0000-0001-9995-6771"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhou, Xinyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709477","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-5715-3011"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324756","display_name":"Jiayao Ma","orcid":"https://orcid.org/0000-0002-0907-2217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Jiayao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390314","display_name":"Wenhao Wang","orcid":"https://orcid.org/0000-0002-6228-7516"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111346891","display_name":"Min Cao","orcid":"https://orcid.org/0000-0002-6628-0370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Min","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5008999954","display_name":"Mang Ye","orcid":"https://orcid.org/0000-0003-3989-7655"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Mang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101599867"],"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.883899986743927,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.883899986743927,"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/T11133","display_name":"UAV Applications and Optimization","score":0.017100000753998756,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10036","display_name":"Advanced Neural Network Applications","score":0.014000000432133675,"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/robustness","display_name":"Robustness (evolution)","score":0.67330002784729},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3634999990463257},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.3264000117778778},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.299699991941452},{"id":"https://openalex.org/keywords/text-retrieval","display_name":"Text retrieval","score":0.29409998655319214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749000191688538},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.67330002784729},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5547999739646912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48660001158714294},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3634999990463257},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3264000117778778},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3077000081539154},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C2985933255","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Text retrieval","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28360000252723694},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2511.08369","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.08369","pdf_url":"https://arxiv.org/pdf/2511.08369","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2511.08369","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.08369","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":"pmh:oai:arXiv.org:2511.08369","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.08369","pdf_url":"https://arxiv.org/pdf/2511.08369","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416191117.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"introduces":[2,36],"Text-based":[3,25],"Aerial-Ground":[4],"Person":[5,26],"Retrieval":[6,27],"(TAG-PR),":[7],"which":[8,29],"aims":[9],"to":[10,45,77,101,112],"retrieve":[11],"person":[12],"images":[13],"from":[14,62],"heterogeneous":[15],"aerial":[16],"and":[17,40,83,104,107,132,138],"ground":[18],"views":[19],"with":[20,65],"textual":[21,68],"descriptions.":[22],"Unlike":[23],"traditional":[24],"(T-PR),":[28],"focuses":[30],"solely":[31],"on":[32,126],"ground-view":[33],"images,":[34],"TAG-PR":[35],"greater":[37],"practical":[38],"significance":[39],"presents":[41],"unique":[42],"challenges":[43],"due":[44],"the":[46,122,128],"large":[47],"viewpoint":[48,109],"discrepancy":[49],"across":[50],"images.":[51],"To":[52],"support":[53],"this":[54],"task,":[55],"we":[56],"contribute:":[57],"(1)":[58],"TAG-PEDES":[59,130],"dataset,":[60],"constructed":[61],"public":[63],"benchmarks":[64],"automatically":[66],"generated":[67],"descriptions,":[69],"enhanced":[70],"by":[71],"a":[72,86,95,108],"diversified":[73],"text":[74],"generation":[75],"paradigm":[76],"ensure":[78],"robustness":[79],"under":[80],"view":[81,92],"heterogeneity;":[82],"(2)":[84],"TAG-CLIP,":[85],"novel":[87],"retrieval":[88],"framework":[89],"that":[90],"addresses":[91],"heterogeneity":[93],"through":[94],"hierarchically-routed":[96],"mixture":[97],"of":[98,124],"experts":[99],"module":[100],"learn":[102],"view-specific":[103,114],"view-agnostic":[105],"features":[106,115],"decoupling":[110],"strategy":[111],"decouple":[113],"for":[116],"better":[117],"cross-modal":[118],"alignment.":[119],"We":[120],"evaluate":[121],"effectiveness":[123],"TAG-CLIP":[125],"both":[127],"proposed":[129],"dataset":[131,137],"existing":[133],"T-PR":[134],"benchmarks.":[135],"The":[136],"code":[139],"are":[140],"available":[141],"at":[142],"https://github.com/Flame-Chasers/TAG-PR.":[143]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-11-13T00:00:00"}