{"id":"https://openalex.org/W4415707778","doi":"https://doi.org/10.1109/icme59968.2025.11209082","title":"SituLM: Leveraging Visual Instruction Tuning and an Augmented SWiG Dataset for Enhanced Grounded Situation Recognition","display_name":"SituLM: Leveraging Visual Instruction Tuning and an Augmented SWiG Dataset for Enhanced Grounded Situation Recognition","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707778","doi":"https://doi.org/10.1109/icme59968.2025.11209082"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5049728192","display_name":"Yuran Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuran Wang","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,Pittsburgh,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,United States","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058898461","display_name":"Zhi-Qi Cheng","orcid":"https://orcid.org/0000-0002-1720-2085"},"institutions":[{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi-Qi Cheng","raw_affiliation_strings":["University of Washington,School of Engineering &amp; Technology,Tacoma,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,School of Engineering &amp; Technology,Tacoma,United States","institution_ids":["https://openalex.org/I4210150356"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9699000120162964,"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":0.9699000120162964,"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/T10028","display_name":"Topic Modeling","score":0.00430000014603138,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.004100000020116568,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5437999963760376},{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.5415999889373779},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5156999826431274},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4812999963760376},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4602999985218048},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4262000024318695},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3799000084400177},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.37310001254081726},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.37299999594688416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036999702453613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.589900016784668},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5437999963760376},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5389000177383423},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4812999963760376},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37229999899864197},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C193125573","wikidata":"https://www.wikidata.org/wiki/Q7449065","display_name":"Semantic interpretation","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.27880001068115234},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C67277372","wikidata":"https://www.wikidata.org/wiki/Q7449085","display_name":"Semantic role labeling","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310094","display_name":"University of Washington","ror":"https://ror.org/00cvxb145"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2423576022","https://openalex.org/W2560747010","https://openalex.org/W2604673901","https://openalex.org/W2963346996","https://openalex.org/W3003365594","https://openalex.org/W3035399403","https://openalex.org/W3096682293","https://openalex.org/W4200630531","https://openalex.org/W4292433237","https://openalex.org/W4312900708","https://openalex.org/W4411244520"],"related_works":[],"abstract_inverted_index":{"Bridging":[0],"visual":[1,83,175],"and":[2,24,60,85,92,102,126,149,176],"linguistic":[3,177],"modalities":[4],"is":[5],"central":[6],"to":[7,19,80],"advanced":[8],"scene-understanding":[9],"tasks":[10],"such":[11],"as":[12],"Grounded":[13],"Situation":[14,43],"Recognition":[15],"(GSR),":[16],"which":[17],"aims":[18],"decode":[20],"complex":[21],"verb":[22,122,140],"frames":[23,141],"their":[25],"associated":[26],"semantic":[27,62],"roles":[28],"in":[29,121,179,203],"images.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,68,130],"offer":[35],"a":[36,71,159,180],"comprehensive":[37],"analysis":[38],"of":[39,95,168,190],"the":[40,195],"widely":[41],"used":[42],"With":[44],"Grounding":[45],"(SWiG)":[46],"dataset,":[47],"highlighting":[48],"key":[49],"issues":[50],"including":[51],"skewed":[52],"role":[53,124],"distributions,":[54],"ambiguous":[55],"annotations,":[56],"incomplete":[57],"bounding":[58],"boxes,":[59],"inconsistent":[61],"specificity.":[63],"To":[64],"address":[65],"these":[66],"challenges,":[67],"introduce":[69],"SituLM,":[70,96],"framework":[72],"that":[73,111,136],"leverages":[74],"pretrained":[75],"Large":[76],"Multimodal":[77],"Models":[78],"(LMMs)":[79],"jointly":[81],"model":[82],"cues":[84],"language":[86],"representations.":[87],"We":[88],"explore":[89],"both":[90],"single-turn":[91],"multi-turn":[93],"variants":[94],"each":[97],"capturing":[98],"distinct":[99],"inference":[100],"strategies":[101],"incorporating":[103],"chain-of-thought":[104],"reasoning.":[105],"Extensive":[106],"experiments":[107],"on":[108],"SWiG":[109,134,191],"reveal":[110],"our":[112],"approach":[113],"significantly":[114],"outperforms":[115],"existing":[116],"methods,":[117],"yielding":[118],"substantial":[119],"gains":[120],"recognition,":[123],"prediction,":[125],"grounding":[127],"accuracy.":[128],"Furthermore,":[129],"present":[131],"an":[132],"augmented":[133],"dataset":[135,157],"accommodates":[137],"multiple":[138,170],"plausible":[139],"per":[142],"image,":[143],"prioritized":[144],"by":[145],"image-text":[146],"similarity":[147],"scoring":[148],"selectively":[150],"refined":[151],"via":[152],"human":[153],"verification.":[154],"This":[155],"enriched":[156],"provides":[158],"more":[160,198],"realistic":[161],"testbed":[162],"for":[163,197],"evaluating":[164],"GSR":[165],"models":[166],"capable":[167],"handling":[169],"co-occurring":[171],"actions.":[172],"By":[173],"unifying":[174],"information":[178],"single":[181],"instruction-based":[182],"model,":[183],"SituLM":[184],"not":[185],"only":[186],"addresses":[187],"longstanding":[188],"limitations":[189],"but":[192],"also":[193],"paves":[194],"way":[196],"robust,":[199],"context-aware":[200],"scene":[201],"interpretation":[202],"real-world":[204],"scenarios.":[205],"<sup":[206],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[207],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[208]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-30T00:00:00"}