{"id":"https://openalex.org/W7160296877","doi":"https://doi.org/10.1109/wacv61042.2026.00233","title":"Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding","display_name":"Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160296877","doi":"https://doi.org/10.1109/wacv61042.2026.00233"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5100361757","display_name":"Jun Li","orcid":"https://orcid.org/0000-0002-0652-6041"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062054084","display_name":"C H Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Che Liu","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135348771","display_name":"Wenjia Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenjia Bai","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101513316","display_name":"Mingxuan Liu","orcid":"https://orcid.org/0009-0003-8142-4621"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mingxuan Liu","raw_affiliation_strings":["University of Trento"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135333914","display_name":"Rossella Arcucci","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rossella Arcucci","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086799838","display_name":"Cosmin I. Bercea","orcid":"https://orcid.org/0000-0003-2628-2766"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cosmin I. Bercea","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019012882","display_name":"Julia A. Schnabel","orcid":"https://orcid.org/0000-0001-6107-3009"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julia A. Schnabel","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":3,"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":"2359","last_page":"2369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7093999981880188,"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":0.7093999981880188,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0478999987244606,"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/T10028","display_name":"Topic Modeling","score":0.0471000000834465,"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/abnormality","display_name":"Abnormality","score":0.4334999918937683},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.3508000075817108},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.34950000047683716},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.34880000352859497},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.3483000099658966},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.34209999442100525},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.3400000035762787},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.3255000114440918}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6341999769210815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6301000118255615},{"id":"https://openalex.org/C50965678","wikidata":"https://www.wikidata.org/wiki/Q2724302","display_name":"Abnormality","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3781999945640564},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.251800000667572},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wacv61042.2026.00233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/5c38da23-b040-4972-b898-1363a5f28c0c","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/5c38da23-b040-4972-b898-1363a5f28c0c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Li, J, Liu, C, Bai, W, Liu, M, Arcucci, R, Bercea, C I & Schnabel, J A 2026, 'Knowledge to Sight : Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding', Proceedings - 2026 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2026, pp. 2359-2369. https://doi.org/10.1109/WACV61042.2026.00233","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.42160409688949585,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2102634410","https://openalex.org/W2103004421","https://openalex.org/W2152772232","https://openalex.org/W2912664121","https://openalex.org/W2963466845","https://openalex.org/W2995225687","https://openalex.org/W3043995050","https://openalex.org/W3114128166","https://openalex.org/W3216130706","https://openalex.org/W4283319802","https://openalex.org/W4304092062","https://openalex.org/W4312533035","https://openalex.org/W4379879090","https://openalex.org/W4385347692","https://openalex.org/W4386065580","https://openalex.org/W4386275705","https://openalex.org/W4390872699","https://openalex.org/W4393158799","https://openalex.org/W4400680052","https://openalex.org/W4402660140","https://openalex.org/W4402670788","https://openalex.org/W4403760591","https://openalex.org/W4404389169","https://openalex.org/W4406152279","https://openalex.org/W4407049645","https://openalex.org/W4408011351","https://openalex.org/W4409378006","https://openalex.org/W4415796386","https://openalex.org/W4416011362","https://openalex.org/W7133193597","https://openalex.org/W7133197087","https://openalex.org/W7133220107"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,60],"work,":[2],"we":[3,80],"address":[4,59],"the":[5,14,39,68,159],"problem":[6],"of":[7,70,143,158],"grounding":[8,33],"abnormalities":[9],"in":[10,31,38,192],"medical":[11,40,57,164,185],"images,":[12],"where":[13],"goal":[15],"is":[16],"to":[17,43,83,189],"localize":[18],"clinical":[19,95],"findings":[20],"based":[21],"on":[22,178],"textual":[23],"descriptions.":[24],"While":[25],"generalist":[26],"Vision-Language":[27],"Models":[28],"(VLMs)":[29],"excel":[30],"natural":[32],"tasks,":[34],"they":[35],"often":[36],"struggle":[37],"domain":[41,64,113,135],"due":[42],"rare,":[44],"compositional,":[45],"and":[46,73,105,115,137,152,170,197],"domain-specific":[47],"terms":[48],"that":[49,88],"are":[50,110],"poorly":[51],"aligned":[52],"with":[53,150,180,187],"visual":[54,99],"patterns.":[55],"Specialized":[56],"VLMs":[58],"challenge":[61],"via":[62],"large-scale":[63],"pretraining,":[65],"but":[66],"at":[67],"cost":[69],"substantial":[71],"annotation":[72],"computational":[74],"resources.":[75],"To":[76],"overcome":[77],"these":[78,174],"limitations,":[79],"propose":[81],"Knowledge":[82],"Sight":[84],"(K2Sight),":[85],"a":[86],"framework":[87],"introduces":[89],"structured":[90],"semantic":[91],"supervision":[92],"by":[93,162],"decomposing":[94],"concepts":[96],"into":[97,117],"interpretable":[98],"attributes,":[100],"such":[101],"as":[102],"shape,":[103],"density,":[104],"anatomical":[106],"location.":[107],"These":[108],"attributes":[109],"distilled":[111],"from":[112],"ontologies":[114],"encoded":[116],"concise":[118],"instruction-style":[119],"prompts,":[120],"which":[121],"guide":[122],"region-text":[123],"alignment":[124],"during":[125],"training.":[126],"Unlike":[127],"conventional":[128],"report-level":[129],"supervision,":[130],"our":[131],"approach":[132],"explicitly":[133],"bridges":[134],"knowledge":[136],"spatial":[138],"structure,":[139],"enabling":[140],"data-efficient":[141],"training":[142,172],"compact":[144,148],"models.":[145],"We":[146],"train":[147],"models":[149,175],"0.23B":[151],"2B":[153],"parameters":[154],"using":[155],"only":[156],"1.5%":[157],"data":[160],"required":[161],"state-of-the-art":[163],"VLMs.":[165],"Despite":[166],"their":[167],"small":[168],"size":[169],"limited":[171],"data,":[173],"achieve":[176],"performance":[177],"par":[179],"or":[181],"better":[182],"than":[183],"7B+":[184],"VLMs,":[186],"up":[188],"9.82%":[190],"improvement":[191],"mAP<inf":[193],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[194],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">50</inf>.":[195],"Code":[196],"models:":[198],"https://lijunrio.github.io/K2Sight/.":[199]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}