{"id":"https://openalex.org/W4393863125","doi":"https://doi.org/10.1109/mis.2024.3384513","title":"Detect2Interact: Localizing Object Key Field in Visual Question Answering with LLMs","display_name":"Detect2Interact: Localizing Object Key Field in Visual Question Answering with LLMs","publication_year":2024,"publication_date":"2024-04-03","ids":{"openalex":"https://openalex.org/W4393863125","doi":"https://doi.org/10.1109/mis.2024.3384513"},"language":"en","primary_location":{"id":"doi:10.1109/mis.2024.3384513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mis.2024.3384513","pdf_url":null,"source":{"id":"https://openalex.org/S114241109","display_name":"IEEE Intelligent Systems","issn_l":"1541-1672","issn":["1541-1672","1941-1294"],"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 Intelligent Systems","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/A5052904738","display_name":"Jialou Wang","orcid":"https://orcid.org/0000-0001-8833-4360"},"institutions":[{"id":"https://openalex.org/I32394136","display_name":"Northumbria University","ror":"https://ror.org/049e6bc10","country_code":"GB","type":"education","lineage":["https://openalex.org/I32394136"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jialou Wang","raw_affiliation_strings":["Northumbria University, Newcastle upon Tyne, U.K"],"raw_orcid":"https://orcid.org/0000-0001-8833-4360","affiliations":[{"raw_affiliation_string":"Northumbria University, Newcastle upon Tyne, U.K","institution_ids":["https://openalex.org/I32394136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107958360","display_name":"Manli Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I32394136","display_name":"Northumbria University","ror":"https://ror.org/049e6bc10","country_code":"GB","type":"education","lineage":["https://openalex.org/I32394136"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Manli Zhu","raw_affiliation_strings":["Northumbria University, Newcastle upon Tyne, U.K"],"raw_orcid":"https://orcid.org/0000-0003-2180-5740","affiliations":[{"raw_affiliation_string":"Northumbria University, Newcastle upon Tyne, U.K","institution_ids":["https://openalex.org/I32394136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013060374","display_name":"Yulei Li","orcid":"https://orcid.org/0000-0003-3579-6179"},"institutions":[{"id":"https://openalex.org/I32394136","display_name":"Northumbria University","ror":"https://ror.org/049e6bc10","country_code":"GB","type":"education","lineage":["https://openalex.org/I32394136"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yulei Li","raw_affiliation_strings":["Northumbria University, Newcastle upon Tyne, U.K"],"raw_orcid":"https://orcid.org/0000-0003-3579-6179","affiliations":[{"raw_affiliation_string":"Northumbria University, Newcastle upon Tyne, U.K","institution_ids":["https://openalex.org/I32394136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100321720","display_name":"Honglei Li","orcid":"https://orcid.org/0000-0003-3126-0764"},"institutions":[{"id":"https://openalex.org/I32394136","display_name":"Northumbria University","ror":"https://ror.org/049e6bc10","country_code":"GB","type":"education","lineage":["https://openalex.org/I32394136"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Honglei Li","raw_affiliation_strings":["Northumbria University, Newcastle upon Tyne, U.K"],"raw_orcid":"https://orcid.org/0000-0003-3126-0764","affiliations":[{"raw_affiliation_string":"Northumbria University, Newcastle upon Tyne, U.K","institution_ids":["https://openalex.org/I32394136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065079117","display_name":"Longzhi Yang","orcid":"https://orcid.org/0000-0003-2115-4909"},"institutions":[{"id":"https://openalex.org/I32394136","display_name":"Northumbria University","ror":"https://ror.org/049e6bc10","country_code":"GB","type":"education","lineage":["https://openalex.org/I32394136"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Longzhi Yang","raw_affiliation_strings":["Northumbria University, Newcastle upon Tyne, U.K"],"raw_orcid":"https://orcid.org/0000-0003-2115-4909","affiliations":[{"raw_affiliation_string":"Northumbria University, Newcastle upon Tyne, U.K","institution_ids":["https://openalex.org/I32394136"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084431277","display_name":"Wai Lok Woo","orcid":"https://orcid.org/0000-0002-8698-7605"},"institutions":[{"id":"https://openalex.org/I32394136","display_name":"Northumbria University","ror":"https://ror.org/049e6bc10","country_code":"GB","type":"education","lineage":["https://openalex.org/I32394136"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wai Lok Woo","raw_affiliation_strings":["Northumbria University, Newcastle upon Tyne, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8698-7605","affiliations":[{"raw_affiliation_string":"Northumbria University, Newcastle upon Tyne, U.K","institution_ids":["https://openalex.org/I32394136"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5052904738"],"corresponding_institution_ids":["https://openalex.org/I32394136"],"apc_list":null,"apc_paid":null,"fwci":0.7142,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68665771,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"39","issue":"3","first_page":"35","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9962000250816345,"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-science","display_name":"Computer science","score":0.8606281280517578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7023292779922485},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6186062693595886},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5667724609375},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5654655694961548},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.536388099193573},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5357427000999451},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5235459804534912},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5207383632659912},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43601691722869873},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4252392649650574},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3983168601989746},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.25267893075942993},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.19387578964233398}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8606281280517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7023292779922485},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6186062693595886},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5667724609375},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5654655694961548},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.536388099193573},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5357427000999451},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5235459804534912},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5207383632659912},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43601691722869873},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4252392649650574},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3983168601989746},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.25267893075942993},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.19387578964233398},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mis.2024.3384513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mis.2024.3384513","pdf_url":null,"source":{"id":"https://openalex.org/S114241109","display_name":"IEEE Intelligent Systems","issn_l":"1541-1672","issn":["1541-1672","1941-1294"],"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 Intelligent Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W1983927101","https://openalex.org/W2128532956","https://openalex.org/W2334493732","https://openalex.org/W2884536769","https://openalex.org/W2964146787","https://openalex.org/W2976260559","https://openalex.org/W3024280721","https://openalex.org/W4226055414","https://openalex.org/W4298392976","https://openalex.org/W4366850747","https://openalex.org/W4377164404","https://openalex.org/W4382490555","https://openalex.org/W4384918448","https://openalex.org/W4386065596","https://openalex.org/W4387723654","https://openalex.org/W4389519620","https://openalex.org/W4390874575","https://openalex.org/W4391759936","https://openalex.org/W6682086655","https://openalex.org/W6851950068","https://openalex.org/W6852999659","https://openalex.org/W6854222408","https://openalex.org/W6854866820","https://openalex.org/W6857872576"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W1508899372","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2383687187","https://openalex.org/W2081517010","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Localization":[0],"plays":[1],"a":[2,137,164],"crucial":[3,40],"role":[4],"in":[5,43,56,106],"enhancing":[6],"the":[7,29,94,126,155],"practicality":[8],"and":[9,18,36,48,65,132,153,167],"precision":[10],"of":[11,23,104],"VQA":[12,157],"systems.":[13],"By":[14],"enabling":[15],"fine-grained":[16,85],"identification":[17],"interaction":[19],"with":[20,159],"specific":[21],"parts":[22],"an":[24,81,129],"object,":[25],"it":[26],"significantly":[27],"improves":[28],"system\u2019s":[30],"ability":[31],"to":[32,62,99,113],"provide":[33],"contextually":[34],"relevant":[35],"spatially":[37,66],"accurate":[38],"responses,":[39],"for":[41,84],"applications":[42],"dynamic":[44],"environments":[45],"like":[46],"robotics":[47],"augmented":[49],"reality.":[50],"However,":[51],"traditional":[52],"systems":[53],"face":[54],"challenges":[55,78],"accurately":[57],"mapping":[58],"objects":[59,105],"within":[60],"images":[61],"generate":[63,100],"nuanced":[64],"aware":[67],"responses.":[68],"In":[69],"this":[70],"work,":[71],"we":[72,92,109,119],"introduce":[73],"\u201cDetect2Interact\u201d,":[74],"which":[75],"addresses":[76],"these":[77],"by":[79,162],"introducing":[80],"advanced":[82],"approach":[83],"object":[86,116,145,160],"visual":[87,169],"key":[88,146],"field":[89,147],"detection.":[90],"First,":[91],"use":[93,110],"segment":[95],"anything":[96],"model":[97],"(SAM)":[98],"detailed":[101],"spatial":[102,134],"maps":[103],"images.":[107],"Next,":[108],"Vision":[111],"Studio":[112],"extract":[114],"semantic":[115],"descriptions.":[117],"Third,":[118],"employ":[120],"GPT-4\u2019s":[121],"common":[122],"sense":[123],"knowledge,":[124],"bridging":[125],"gap":[127],"between":[128],"object\u2019s":[130],"semantics":[131],"its":[133],"map.":[135],"As":[136],"result,":[138],"Detect2Interact":[139],"achieves":[140],"consistent":[141],"qualitative":[142],"results":[143],"on":[144],"detection":[148,161],"across":[149],"extensive":[150],"test":[151],"cases":[152],"outperforms":[154],"existing":[156],"system":[158],"providing":[163],"more":[165],"reasonable":[166],"finer":[168],"representation.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}