{"id":"https://openalex.org/W7221828126","doi":"https://doi.org/10.48550/arxiv.2610.16364","title":"From Sound to Sense: An Anatomy of Semantic Supervision for Speech-Driven Visual Grounding in Remote Sensing Imagery","display_name":"From Sound to Sense: An Anatomy of Semantic Supervision for Speech-Driven Visual Grounding in Remote Sensing Imagery","publication_year":2026,"publication_date":"2026-10-12","ids":{"openalex":"https://openalex.org/W7221828126","doi":"https://doi.org/10.48550/arxiv.2610.16364"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.16364","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.16364","pdf_url":"https://arxiv.org/pdf/2610.16364","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":null,"license_id":null,"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/2610.16364","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153245490","display_name":"Zhongyu Pang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pang, Zhongyu","raw_affiliation_strings":["College of Electronic Science , National University of Defense Technology , Changsha 410073 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Science , National University of Defense Technology , Changsha 410073 , China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5153245490"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"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":0.7056000232696533,"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":0.7056000232696533,"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":0.09350000321865082,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.02370000071823597,"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/remote-sensing-imagery","display_name":"remote sensing images","score":0.9860000014305115},{"id":"https://openalex.org/keywords/semantic-supervision","display_name":"semantic supervision","score":0.7110000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6801000237464905},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5924999713897705},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5764999985694885},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.48159998655319214},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C161759796","wikidata":"https://www.wikidata.org/wiki/Q3982902","display_name":"Teleoperation","level":3,"score":0.44909998774528503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3978999853134155},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.39399999380111694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.392300009727478},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2867000102996826},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25839999318122864}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.16364","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.16364","pdf_url":"https://arxiv.org/pdf/2610.16364","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.16364","doi":"https://doi.org/10.48550/arxiv.2610.16364","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.16364","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:2610.16364","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.16364","pdf_url":"https://arxiv.org/pdf/2610.16364","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221828126.pdf","grobid_xml":"https://content.openalex.org/works/W7221828126.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W3127270383","https://openalex.org/W3197580070","https://openalex.org/W4297808394","https://openalex.org/W4412945669"],"related_works":["https://openalex.org/W4416942845","https://openalex.org/W2941492599","https://openalex.org/W4414739363","https://openalex.org/W3158565912","https://openalex.org/W4416887857","https://openalex.org/W7164944010","https://openalex.org/W3092512595","https://openalex.org/W2903320905","https://openalex.org/W4385823492","https://openalex.org/W4226394872"],"abstract_inverted_index":{"Speech-driven":[0],"visual":[1],"grounding":[2,70],"in":[3,25,90,147],"remote":[4],"sensing":[5],"(RSVG)":[6],"removes":[7],"the":[8,81,211,221,228],"typing":[9],"bottleneck":[10],"of":[11],"text-based":[12],"interaction":[13],"and":[14,39,75,101,122,130,150,218],"is":[15,178],"intended":[16],"to":[17,35],"preserve":[18],"prosodic":[19],"intent,":[20],"enabling":[21],"hands-free":[22],"target":[23],"acquisition":[24],"time-critical":[26],"missions.":[27],"The":[28],"direct-audio":[29],"paradigm,":[30],"mapping":[31],"raw":[32],"speech":[33,42,65,74,88],"straight":[34],"a":[36,62,68,98,102,152,160,174,184,204],"bounding":[37],"box":[38],"bypassing":[40],"automatic":[41],"recognition":[43],"(ASR),":[44],"was":[45],"recently":[46],"adopted":[47],"by":[48,85,180,192,225],"RSTalker,":[49],"but":[50,203],"what":[51],"such":[52],"grounders":[53],"actually":[54],"learn":[55],"about":[56],"language":[57],"remains":[58],"unmeasured.":[59],"SemEcho":[60],"grafts":[61],"frozen":[63],"Whisper":[64],"pathway":[66],"onto":[67],"VLTVG":[69],"host":[71],"so":[72],"that":[73],"text":[76,105,212],"share":[77],"one":[78],"decoder,":[79],"making":[80],"paired":[82],"text,":[83],"free":[84],"construction":[86],"since":[87],"corpora":[89],"this":[91,109],"task":[92],"are":[93],"synthesized":[94],"from":[95],"DIOR-RSVG":[96],"expressions,":[97],"training-time":[99],"teacher":[100],"fair,":[103],"same-host":[104],"upper":[106,213],"bound.":[107],"On":[108],"instrument":[110],"we":[111],"dissect":[112],"three":[113],"semantic":[114,128],"injection":[115],"channels":[116],"(feature-mimicry":[117],"distillation,":[118],"word-level":[119],"CTC":[120],"supervision,":[121],"two-stage":[123],"ASR":[124,176],"pretraining)":[125],"with":[126,142,196],"linear":[127],"probes,":[129],"release":[131],"Audio-DIOR-R":[132],"(80,973":[133],"training":[134],"clips;":[135],"10":[136],"timbres":[137],"x":[138],"K=3;":[139],"Qwen3-TTS":[140],"synthesis":[141],"online":[143],"sox":[144],"noise":[145],"lambda":[146],"[0,":[148],"0.4])":[149],"Audio-DIOR-Comp,":[151],"re-split":[153],"holding":[154],"out":[155],"17":[156],"attribute-category":[157],"combinations":[158],"under":[159],"2x2":[161],"acoustic-semantic":[162],"protocol.":[163],"Our":[164],"anatomy":[165],"yields":[166],"four":[167],"findings.":[168],"(i)":[169],"Whether":[170],"direct":[171,190,223],"alignment":[172],"beats":[173,219],"domain-trained":[175],"cascade":[177,187,207],"decided":[179],"recognizer":[181],"quality:":[182],"against":[183,233],"weak":[185,234],"in-domain":[186,206],"(CTC":[188,208],"0.53)":[189],"wins":[191],"9.0":[193],"Acc@0.5":[194],"points":[195],"transcription":[197],"errors":[198],"concentrated":[199],"on":[200],"spatial-relation":[201],"words,":[202],"strong":[205],"0.029)":[209],"reaches":[210],"bound":[214],"(80.8":[215],"vs.":[216],"81.0)":[217],"even":[220],"strongest":[222],"model":[224],"8.8":[226],"points;":[227],"anti-ASR":[229],"premise":[230],"holds":[231],"only":[232],"recognizers.":[235]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-15T00:00:00"}