{"id":"https://openalex.org/W4402810101","doi":"https://doi.org/10.3233/ssw240008","title":"Stitching Gaps: Fusing Situated Perceptual Knowledge with Vision Transformers for High-Level Image Classification","display_name":"Stitching Gaps: Fusing Situated Perceptual Knowledge with Vision Transformers for High-Level Image Classification","publication_year":2024,"publication_date":"2024-09-11","ids":{"openalex":"https://openalex.org/W4402810101","doi":"https://doi.org/10.3233/ssw240008"},"language":"en","primary_location":{"id":"doi:10.3233/ssw240008","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ssw240008","pdf_url":null,"source":{"id":"https://openalex.org/S4210172742","display_name":"Studies on the semantic web","issn_l":"2215-0870","issn":["2215-0870"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"ebook platform"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies on the Semantic Web","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/ssw240008","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001517689","display_name":"Delfina Sol Martinez Pandiani","orcid":"https://orcid.org/0000-0003-2392-6300"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Delfina Sol Martinez Pandiani","raw_affiliation_strings":["Centrum Wiskunde & Informatica, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Centrum Wiskunde & Informatica, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048936818","display_name":"Nicolas Lazzari","orcid":"https://orcid.org/0000-0002-1601-7689"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicolas Lazzari","raw_affiliation_strings":["University of Bologna, Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007281490","display_name":"Valentina Presutti","orcid":"https://orcid.org/0000-0002-9380-5160"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Valentina Presutti","raw_affiliation_strings":["University of Bologna, Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001517689"],"corresponding_institution_ids":["https://openalex.org/I1341640284"],"apc_list":null,"apc_paid":null,"fwci":1.6629,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85533981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9629999995231628,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9629999995231628,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"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":0.9537000060081482,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9526000022888184,"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/image-stitching","display_name":"Image stitching","score":0.8051532506942749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5968682765960693},{"id":"https://openalex.org/keywords/situated","display_name":"Situated","score":0.5636503100395203},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.551463782787323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5378159284591675},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5090929865837097},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34188222885131836},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2890133559703827},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.08419191837310791}],"concepts":[{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.8051532506942749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5968682765960693},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.5636503100395203},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.551463782787323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5378159284591675},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5090929865837097},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34188222885131836},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2890133559703827},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.08419191837310791}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3233/ssw240008","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ssw240008","pdf_url":null,"source":{"id":"https://openalex.org/S4210172742","display_name":"Studies on the semantic web","issn_l":"2215-0870","issn":["2215-0870"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"ebook platform"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies on the Semantic Web","raw_type":"book-chapter"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/cf0701e3-c38d-4d3a-9c53-f5f9f95170a8","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/stitching-gaps-fusing-situated-perceptual-knowledge-with-vision-transformers-for-highlevel-image-classification(cf0701e3-c38d-4d3a-9c53-f5f9f95170a8).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Martinez Pandiani, D S, Lazzari, N & Presutti, V 2024, Stitching Gaps: Fusing Situated Perceptual Knowledge with Vision Transformers for High-Level Image Classification. in A Salatino, M Alam, F Ongenae, S Vahdati, A-L Gentile, T Pellegrini & S Jiang (eds), Knowledge Graphs in the Age of Language Models and Neuro-Symbolic AI : Proceedings of the 20th International Conference on Semantic Systems, 17\u201319 September 2024, Amsterdam, The Netherlands. Studies on the Semantic Web, vol. 60, Amsterdam, pp. 68-87, 20th International Conference on Semantic Systems, Amsterdam, Netherlands, 17/09/24. https://doi.org/10.3233/SSW240008","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:2402.19339","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.19339","pdf_url":"https://arxiv.org/pdf/2402.19339","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:arpi.unipi.it:11568/1343767","is_oa":false,"landing_page_url":"https://hdl.handle.net/11568/1343767","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2402.19339","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.19339","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.3233/ssw240008","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ssw240008","pdf_url":null,"source":{"id":"https://openalex.org/S4210172742","display_name":"Studies on the semantic web","issn_l":"2215-0870","issn":["2215-0870"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"ebook platform"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies on the Semantic Web","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W68020613","https://openalex.org/W1973382465","https://openalex.org/W2091466534","https://openalex.org/W4255291540","https://openalex.org/W3134240150","https://openalex.org/W4392793652","https://openalex.org/W4387591196","https://openalex.org/W4399199700","https://openalex.org/W172825421","https://openalex.org/W2944699522"],"abstract_inverted_index":{"The":[0,181,201],"increasing":[1],"demand":[2,26],"for":[3,30,167,247,260,267],"automatic":[4],"high-level":[5,131],"image":[6,88,141,192,249,265],"understanding,":[7],"including":[8],"the":[9,28,43,60,63,105,128,184,206,231,276],"detection":[10],"of":[11,78,183,257],"abstract":[12,223],"concepts":[13],"(AC)":[14],"in":[15,86,210,220,269],"images,":[16,97],"presents":[17],"a":[18,254],"complex":[19],"challenge":[20],"both":[21],"technically":[22],"and":[23,32,66,84,102,155,224,233,241,263,278],"ethically.":[24],"This":[25,110,251],"highlights":[27],"need":[29],"innovative":[31],"more":[33,222],"interpretable":[34],"approaches,":[35],"that":[36,47,158],"reconcile":[37],"traditional":[38],"deep":[39,64,242],"vision":[40,65],"methods":[41,197,259],"with":[42,123,130,151,162,178,216],"situated,":[44],"nuanced":[45],"knowledge":[46,77,240,261],"humans":[48],"use":[49,268],"to":[50,73,81],"interpret":[51],"images":[52,80,121],"at":[53,282],"such":[54,138],"high":[55],"semantic":[56,94,225],"levels.":[57],"To":[58,134],"bridge":[59],"gap":[61],"between":[62,235],"situated":[67,75,113,238],"perceptual":[68,76,93,114,239],"paradigms,":[69],"this":[70],"study":[71],"aims":[72],"leverage":[74],"cultural":[79,120],"enhance":[82,127],"performance":[83],"interpretability":[85,203],"AC":[87,191,248],"classification.":[89,250],"We":[90,149],"automatically":[91],"extract":[92],"units":[95],"from":[96,117],"which":[98],"we":[99,126,143,169],"then":[100],"model":[101,176],"integrate":[103],"into":[104],"ARTstract":[106],"Knowledge":[107,145],"Graph":[108,146],"(AKG).":[109],"resource":[111],"captures":[112],"semantics":[115],"gleaned":[116],"over":[118],"14,000":[119],"labeled":[122],"ACs.":[124],"Additionally,":[125],"AKG":[129],"linguistic":[132],"frames.":[133],"facilitate":[135],"downstream":[136,270],"tasks":[137],"as":[139],"AC-based":[140],"classification,":[142,193],"compute":[144],"Embeddings":[147],"(KGE).":[148],"experiment":[150],"relative":[152,185],"representations":[153],"[1]":[154],"hybrid":[156,196],"approaches":[157],"fuse":[159],"these":[160],"embeddings":[161],"visual":[163,207,213,243,272],"transformer":[164],"embeddings.":[165],"Finally,":[166],"interpretability,":[168],"conduct":[170],"posthoc":[171,202],"qualitative":[172],"analyses":[173,204],"by":[174],"examining":[175],"similarities":[177],"training":[179],"instances.":[180],"adoption":[182],"representation":[186,266],"method":[187],"significantly":[188],"bolsters":[189],"KGE-based":[190],"while":[194],"our":[195,217],"outperform":[198],"state-of-the-art":[199],"approaches.":[200],"reveal":[205],"transformer\u2019s":[208],"proficiency":[209],"capturing":[211],"pixel-level":[212],"attributes,":[214],"contrasting":[215],"method\u2019s":[218],"efficacy":[219],"representing":[221],"scene":[226],"elements.":[227],"Our":[228],"results":[229],"demonstrate":[230],"synergy":[232],"complementarity":[234],"KGE":[236],"embeddings\u2019":[237],"model\u2019s":[244],"sensory-perceptual":[245],"understanding":[246],"work":[252],"suggests":[253],"strong":[255],"potential":[256],"neurosymbolic":[258],"integration":[262],"robust":[264],"intricate":[271],"comprehension":[273],"tasks.":[274],"All":[275],"materials":[277],"code":[279],"are":[280],"available":[281],"https://github.com/delfimpandiani/Stitching-Gaps":[283]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}