{"id":"https://openalex.org/W4416251543","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228013","title":"Query Rephrasing for Context Independence in Scene Knowledge-guided Visual Grounding","display_name":"Query Rephrasing for Context Independence in Scene Knowledge-guided Visual Grounding","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251543","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228013"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5008274291","display_name":"Xueying Qin","orcid":"https://orcid.org/0000-0003-0057-295X"},"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":"Xilong Qin","raw_affiliation_strings":["College of Systems Engineering National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394413","display_name":"Jing Ye","orcid":"https://orcid.org/0000-0002-7832-5003"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Ye","raw_affiliation_strings":["Hunan Institute of Advanced Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Hunan Institute of Advanced Technology,Changsha,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111347020","display_name":"Haixiang Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haixiang Zhu","raw_affiliation_strings":["Hunan Institute of Advanced Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Hunan Institute of Advanced Technology,Changsha,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017356141","display_name":"Wansen Wu","orcid":"https://orcid.org/0000-0002-0467-3830"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wansen Wu","raw_affiliation_strings":["Navy Submarine Academy,Qingdao,China"],"affiliations":[{"raw_affiliation_string":"Navy Submarine Academy,Qingdao,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053458494","display_name":"Yue Hu","orcid":"https://orcid.org/0000-0002-8115-7020"},"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":false,"raw_author_name":"Yue Hu","raw_affiliation_strings":["College of Systems Engineering National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008274291"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34508079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9918000102043152,"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":0.9918000102043152,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.002400000113993883,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.0013000000035390258,"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/object","display_name":"Object (grammar)","score":0.7360000014305115},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7319999933242798},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5471000075340271},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5411999821662903},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43309998512268066},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4311999976634979},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.4253000020980835},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.3917999863624573},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.36629998683929443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7432000041007996},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7360000014305115},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7319999933242798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6322000026702881},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5471000075340271},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5411999821662903},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4652000069618225},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4311999976634979},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35760000348091125},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.35089999437332153},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3458000123500824},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3118000030517578},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29679998755455017},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2896000146865845},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311778","display_name":"China Association for Science and Technology","ror":"https://ror.org/035vmht26"},{"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":22,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2251512949","https://openalex.org/W2558535589","https://openalex.org/W2606473278","https://openalex.org/W2952524542","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W3035097537","https://openalex.org/W3110435696","https://openalex.org/W3159619744","https://openalex.org/W3170767867","https://openalex.org/W3174004334","https://openalex.org/W3174965650","https://openalex.org/W4312956471","https://openalex.org/W4313068342","https://openalex.org/W4386071652","https://openalex.org/W4387272106","https://openalex.org/W4402727689","https://openalex.org/W4402727764","https://openalex.org/W4402774238"],"related_works":[],"abstract_inverted_index":{"Scene":[0,104],"Knowledge-guided":[1,105],"Visual":[2,106],"Grounding":[3,107],"(SK-VG)":[4],"aims":[5],"to":[6,17,36,62,109,149,164],"locate":[7],"the":[8,29,41,46,52,60,64,71,88,127,143,152,157,165,172,183,188,192,199,207,211,221,226,229,236,249],"specific":[9],"object":[10,43,121,185,242],"in":[11,54,79,156,168,225,260],"an":[12,19,240],"image":[13],"that":[14,51,181,253],"is":[15,161],"referred":[16],"by":[18,114,187,202],"open-ended":[20],"query,":[21],"utilizing":[22],"textual":[23],"scene":[24,158],"knowledge":[25,213],"for":[26,59,103,220],"guidance.":[27],"Besides":[28],"grounding":[30,222,233],"ability,":[31],"SK-VG":[32,55,128,250],"models":[33,61,67],"are":[34,56,85],"expected":[35],"infer":[37],"more":[38,178],"information":[39,155],"of":[40,142,147,206,262],"target":[42,184,200],"based":[44,100,234],"on":[45,191,235,248,268],"expatiatory":[47],"contextual":[48,154],"knowledge,":[49,159],"given":[50,193],"queries":[53,72,117],"often":[57],"insufficient":[58],"identify":[63],"object.":[65],"Existing":[66],"perform":[68],"well":[69],"when":[70],"contain":[73],"obvious":[74],"visual":[75,83,189],"clues":[76],"but":[77],"falter":[78],"hard":[80,269],"situations":[81],"where":[82],"attributes":[84],"absent":[86],"from":[87],"query.":[89,166],"In":[90],"this":[91,169],"paper,":[92],"we":[93,124],"propose":[94],"a":[95,112,177],"Large":[96],"Language":[97],"Models":[98],"(LLMs)":[99],"Inference":[101],"framework":[102],"(LISK-VG)":[108],"address":[110],"such":[111],"problem":[113],"rephrasing":[115],"abstract":[116],"with":[118,239],"visually":[119],"distinguishable":[120],"descriptions.":[122],"Specifically,":[123],"explicitly":[125],"decompose":[126],"task":[129],"into":[130,176],"two":[131],"steps,":[132],"i.e.,":[133],"inference":[134,138],"and":[135,210],"grounding.":[136],"The":[137,244],"step":[139],"takes":[140],"advantage":[141],"semantic":[144],"understanding":[145,205],"capabilities":[146],"LLMs":[148],"fully":[150],"recognize":[151],"useful":[153],"which":[160,215],"then":[162],"injected":[163],"LISK-VG,":[167],"way,":[170],"transforms":[171],"originally":[173],"context-dependent":[174],"query":[175,209,238],"self-informative":[179],"form":[180],"characterizes":[182],"mainly":[186],"features":[190],"image.":[194],"This":[195],"process":[196],"significantly":[197,256],"facilitates":[198],"localization":[201],"avoiding":[203],"joint":[204],"veiled":[208],"long-winded":[212],"text,":[214],"might":[216],"be":[217],"largely":[218],"distractive":[219],"task.":[223],"Then":[224],"second":[227],"step,":[228],"model":[230],"performs":[231],"precise":[232],"converted":[237],"explicit":[241],"description.":[243],"experimental":[245],"results":[246],"conducted":[247],"dataset":[251],"demonstrate":[252],"our":[254],"LISK-VG":[255],"outperforms":[257],"other":[258],"approaches":[259],"terms":[261],"accuracy,":[263],"particularly":[264],"exhibiting":[265],"substantial":[266],"advantages":[267],"cases.":[270]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}