{"id":"https://openalex.org/W7111136517","doi":"https://doi.org/10.1145/3731443.3771367","title":"GLIIDE: Global-Local Image Integration via Descriptive Extraction","display_name":"GLIIDE: Global-Local Image Integration via Descriptive Extraction","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7111136517","doi":"https://doi.org/10.1145/3731443.3771367"},"language":null,"primary_location":{"id":"doi:10.1145/3731443.3771367","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731443.3771367","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Knowledge Capture Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731443.3771367","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Aryan Singh Dalal","orcid":"https://orcid.org/0000-0003-0720-7306"},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aryan Singh Dalal","raw_affiliation_strings":["Department of Computer Science, Kansas State University, Manhattan, KS, USA"],"raw_orcid":"https://orcid.org/0000-0003-0720-7306","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Kansas State University, Manhattan, KS, USA","institution_ids":["https://openalex.org/I189590672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Soheil Abadifard","orcid":"https://orcid.org/0000-0002-2980-4251"},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soheil Abadifard","raw_affiliation_strings":["Department of Computer Science, Kansas State university, Manhattan, KS, USA"],"raw_orcid":"https://orcid.org/0000-0002-2980-4251","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Kansas State university, Manhattan, KS, USA","institution_ids":["https://openalex.org/I189590672"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hande Kucuk McGinty","orcid":"https://orcid.org/0000-0002-9025-5538"},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hande Kucuk McGinty","raw_affiliation_strings":["Department of Computer Science, Kansas State University, Manhattan, KS, USA"],"raw_orcid":"https://orcid.org/0000-0002-9025-5538","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Kansas State University, Manhattan, KS, USA","institution_ids":["https://openalex.org/I189590672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189590672"],"apc_list":null,"apc_paid":null,"fwci":2.2554,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90675875,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"194","last_page":"197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7742000222206116,"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":0.7742000222206116,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.17489999532699585,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.016599999740719795,"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/generative-grammar","display_name":"Generative grammar","score":0.6384999752044678},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5992000102996826},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5503000020980835},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5486000180244446},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48510000109672546},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.44020000100135803},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4348999857902527},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.43059998750686646},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3961000144481659}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7272999882698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6851000189781189},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6384999752044678},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5992000102996826},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5503000020980835},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5486000180244446},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.44020000100135803},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4131999909877777},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3961000144481659},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30720001459121704},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731443.3771367","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731443.3771367","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Knowledge Capture Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731443.3771367","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731443.3771367","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Knowledge Capture Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2277195237","https://openalex.org/W2579549467","https://openalex.org/W2950096400","https://openalex.org/W2985532129","https://openalex.org/W3096609285","https://openalex.org/W3164656968","https://openalex.org/W3167599226","https://openalex.org/W4386113748","https://openalex.org/W4391426565","https://openalex.org/W4403535155","https://openalex.org/W4406031095","https://openalex.org/W4408332251","https://openalex.org/W4408532899","https://openalex.org/W4409682143","https://openalex.org/W4409771387","https://openalex.org/W4411503990","https://openalex.org/W4413291654","https://openalex.org/W4414988273","https://openalex.org/W4415110448","https://openalex.org/W4415315079","https://openalex.org/W6968871106"],"related_works":[],"abstract_inverted_index":{"Automated":[0],"Scene":[1],"Graph":[2],"Generation":[3],"(SGG)":[4],"is":[5],"challenged":[6],"by":[7],"the":[8,90,95],"\"Global-Local":[9],"Dilemma\"\u2014the":[10],"tension":[11],"between":[12],"capturing":[13],"holistic":[14],"scene":[15],"context":[16],"and":[17,123],"granular":[18],"object":[19,81],"details.":[20],"This":[21,109],"paper":[22],"presents":[23],"a":[24,28,40,48,53,65,73,102,112,116],"preliminary":[25,84,113],"investigation":[26],"into":[27],"new":[29],"generative":[30,43,117],"SGG":[31,118],"paradigm":[32,119],"designed":[33],"to":[34,58],"address":[35],"this":[36,98],"challenge.":[37],"We":[38],"introduce":[39],"novel,":[41],"two-track":[42],"framework":[44],"(GLIIDE)":[45],"that":[46,120],"creates":[47],"rich":[49],"textual":[50],"intermediary":[51],"for":[52,68,76,115],"Large":[54],"Language":[55],"Model":[56],"(LLM)":[57],"extract":[59],"knowledge.":[60],"Our":[61,83],"hybrid":[62],"pipeline":[63],"fuses":[64],"YOLO-based":[66],"track":[67,75],"extracting":[69],"factual":[70],"attributes":[71],"with":[72],"DETR-guided":[74],"generating":[77],"contextual":[78],"descriptions":[79],"of":[80,97],"interactions.":[82],"results":[85],"on":[86],"1,000":[87],"images":[88],"from":[89],"Visual":[91],"Genome":[92],"dataset":[93],"demonstrate":[94],"potential":[96],"fusion,":[99],"which":[100],"achieves":[101],"higher":[103],"Relation":[104],"Density":[105],"than":[106],"relative":[107],"baselines.":[108],"work":[110],"provides":[111],"proof-of-concept":[114],"integrates":[121],"local":[122],"global":[124],"visual":[125],"information.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-12-10T00:00:00"}