{"id":"https://openalex.org/W4411996937","doi":"https://doi.org/10.1109/lsp.2025.3585831","title":"Enhancing Visual Aligning and Grounding for Aerial Vision-and-Dialog Navigation","display_name":"Enhancing Visual Aligning and Grounding for Aerial Vision-and-Dialog Navigation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411996937","doi":"https://doi.org/10.1109/lsp.2025.3585831"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3585831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3585831","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","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/A5003206712","display_name":"Guanhui Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanhui Qiao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-0014-2550","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dong Yi","orcid":"https://orcid.org/0009-0000-1282-7310"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yi","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-1282-7310","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061646454","display_name":"Lingxiang Wu","orcid":"https://orcid.org/0000-0001-9346-3597"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingxiang Wu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9346-3597","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042344822","display_name":"Hanxiao Wu","orcid":"https://orcid.org/0000-0001-7710-2177"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanxiao Wu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111918240","display_name":"Jinqiao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinqiao Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9118-2780","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18884596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"2853","last_page":"2857"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9986000061035156,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9976000189781189,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9962999820709229,"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/computer-vision","display_name":"Computer vision","score":0.7546229958534241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6891148090362549},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6773726940155029},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.5792232751846313},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.4500477910041809},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.44884663820266724},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20800653100013733},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19960463047027588}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7546229958534241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6891148090362549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6773726940155029},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5792232751846313},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.4500477910041809},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.44884663820266724},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20800653100013733},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19960463047027588},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3585831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3585831","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6506700831","display_name":null,"funder_award_id":"62306315","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2560722161","https://openalex.org/W2962766617","https://openalex.org/W2963800628","https://openalex.org/W3034578524","https://openalex.org/W3100923070","https://openalex.org/W3109085430","https://openalex.org/W3192009892","https://openalex.org/W4312769131","https://openalex.org/W4385570907","https://openalex.org/W4386075653","https://openalex.org/W4389879572","https://openalex.org/W4390120146","https://openalex.org/W4400314890","https://openalex.org/W4409367204","https://openalex.org/W6748130322","https://openalex.org/W6765527290","https://openalex.org/W6766673545","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6856155248","https://openalex.org/W6892075535"],"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":{"Vision-and-Language":[0],"Navigation":[1],"tasks":[2],"require":[3],"an":[4,34],"agent":[5],"to":[6,8,68,113,127],"navigate":[7],"a":[9,18,27,52,87,104,136],"destination":[10,49,91],"following":[11],"natural":[12],"language":[13,115],"instructions.":[14],"We":[15],"focus":[16],"on":[17],"challenging":[19],"VLN":[20],"dataset,":[21],"Aerial":[22],"Vision-and-Dialog":[23],"Navigation,":[24],"which":[25,147,164],"encompasses":[26],"diverse":[28],"array":[29],"of":[30,120,131,152,161,170],"environments":[31],"and":[32,40,79,154,177],"includes":[33],"additional":[35],"altitude":[36,153],"variable.":[37],"Significant":[38],"spatial":[39],"scale":[41],"variations":[42],"in":[43,172,179,183],"the":[44,56,60,69,75,110,129,132,150,159,173],"aerial":[45],"agent's":[46],"view":[47],"make":[48],"visual":[50,78,92],"grounding":[51],"crucial":[53],"capability":[54],"for":[55,143],"navigation":[57,95],"task.":[58],"However,":[59],"existing":[61],"frameworks":[62],"not":[63],"only":[64],"have":[65],"insufficient":[66],"attention":[67],"vision":[70],"model,":[71],"but":[72],"also":[73],"lack":[74],"correlations":[76],"between":[77],"textual":[80],"modalities.":[81],"To":[82],"address":[83],"this,":[84],"we":[85,102],"propose":[86,103],"model":[88],"that":[89,108],"aligns":[90],"images":[93,119],"with":[94,117,168],"instructions,":[96],"featuring":[97],"three":[98],"innovative":[99],"components.":[100],"Firstly,":[101],"multi-stage":[105],"pre-training":[106],"pipeline":[107],"enhances":[109,149],"model's":[111],"ability":[112],"associate":[114],"instructions":[116],"top-view":[118],"destinations.":[121],"Secondly,":[122],"trajectories":[123],"are":[124],"augmented":[125],"elastically":[126],"simulate":[128],"noise":[130],"controlling":[133],"process.":[134],"Finally,":[135],"polygon":[137],"regression":[138],"loss":[139],"function":[140],"is":[141],"introduced":[142],"rotated":[144],"object":[145],"detection,":[146],"significantly":[148],"accuracy":[151],"orientation":[155],"estimation.":[156],"Experiments":[157],"demonstrate":[158],"effectiveness":[160],"our":[162],"approach,":[163],"achieves":[165],"state-of-the-art":[166],"advancements":[167],"improvements":[169],"2.9%":[171],"val":[174],"unseen":[175,181],"dataset":[176,182],"3.0%":[178],"test":[180],"success":[184],"weighted":[185],"by":[186],"path":[187],"length.":[188]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}