{"id":"https://openalex.org/W4413277612","doi":"https://doi.org/10.1109/icip55913.2025.11084696","title":"Structured Instruction Parsing and Scene Alignment For UAV Vision-Language Navigation","display_name":"Structured Instruction Parsing and Scene Alignment For UAV Vision-Language Navigation","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4413277612","doi":"https://doi.org/10.1109/icip55913.2025.11084696"},"language":"en","primary_location":{"id":"doi:10.1109/icip55913.2025.11084696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026374221","display_name":"Liangyu Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangyu Zhou","raw_affiliation_strings":["Beihang University,School of Electronic and Information Engineering,Beijing,China,100191"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,School of Electronic and Information Engineering,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085284295","display_name":"Rui Xue","orcid":"https://orcid.org/0000-0002-9188-175X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xue","raw_affiliation_strings":["Beihang University,School of Electronic and Information Engineering,Beijing,China,100191"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,School of Electronic and Information Engineering,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100570136","display_name":"Xiaoyan Luo","orcid":"https://orcid.org/0009-0006-3859-9081"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Luo","raw_affiliation_strings":["Beihang University,School of Astronautics,Beijing,China,100191"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,School of Astronautics,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20783566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2600","last_page":"2605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9976999759674072,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9976999759674072,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9972000122070312,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9832000136375427,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8182580471038818},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7353806495666504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6721498966217041},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5982521176338196},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37172067165374756}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8182580471038818},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7353806495666504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6721498966217041},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5982521176338196},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37172067165374756}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip55913.2025.11084696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2890902815","https://openalex.org/W2951973805","https://openalex.org/W2962744691","https://openalex.org/W2963800628","https://openalex.org/W2964339842","https://openalex.org/W2979727876","https://openalex.org/W2997886377","https://openalex.org/W3034578524","https://openalex.org/W3034758614","https://openalex.org/W3100923070","https://openalex.org/W3109085430","https://openalex.org/W3206064780","https://openalex.org/W4214700710","https://openalex.org/W4312996039","https://openalex.org/W4390872901","https://openalex.org/W4393154152","https://openalex.org/W4401417232","https://openalex.org/W4402727055","https://openalex.org/W4402754277"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,41,47],"aerial":[3,42],"Vision-and-Language":[4],"Navigation":[5],"(VLN)":[6],"have":[7],"introduced":[8],"a":[9,114],"more":[10,23,93],"meaningful":[11],"and":[12,22,35,54,75,98,109],"practical":[13],"paradigm":[14],"of":[15,38,89,106],"VLN":[16,43],"by":[17],"considering":[18],"significantly":[19,137],"longer":[20],"paths":[21],"complex":[24],"spatial":[25],"reasoning":[26],"compared":[27],"to":[28,62,68],"ground-based":[29],"VLN.":[30],"However,":[31],"the":[32,77,86,104,130,134,143],"larger":[33],"scale":[34],"increased":[36],"complexity":[37],"outdoor":[39],"environments":[40],"present":[44],"substantial":[45],"challenges":[46],"establishing":[48],"accurate":[49],"correspondence":[50],"between":[51,96],"textual":[52],"instructions":[53,74],"visual":[55,99,127],"scenes.":[56],"In":[57],"this":[58],"work,":[59],"we":[60,112],"propose":[61],"incorporate":[63],"Large":[64],"Language":[65],"Models":[66],"(LLMs)":[67],"extract":[69],"key":[70],"components":[71],"from":[72],"navigation":[73,90,131],"construct":[76],"corresponding":[78,126],"subtasks.":[79],"This":[80],"structured":[81],"instruction":[82],"parsing":[83],"module":[84],"ensures":[85],"appropriate":[87],"granularity":[88],"instructions,":[91],"enabling":[92],"precise":[94],"alignment":[95,117],"language":[97],"cues.":[100],"To":[101],"further":[102],"enhance":[103],"integration":[105],"multi-modal":[107],"information":[108],"cross-modal":[110],"understanding,":[111],"introduce":[113],"scene-based":[115],"subtask":[116,124],"policy":[118],"that":[119],"effectively":[120],"associates":[121],"each":[122],"parsed":[123],"with":[125],"observations":[128],"along":[129],"path.":[132],"Combined,":[133],"proposed":[135],"approach":[136],"outperforms":[138],"current":[139],"state-of-the-art":[140],"methods":[141],"on":[142],"AerialVLN":[144],"dataset.":[145]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}