{"id":"https://openalex.org/W7137940194","doi":"https://doi.org/10.1609/aaai.v40i12.38001","title":"Topology-Aware Vision Transformers for Enhanced Scene Recognition","display_name":"Topology-Aware Vision Transformers for Enhanced Scene Recognition","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137940194","doi":"https://doi.org/10.1609/aaai.v40i12.38001"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i12.38001","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.38001","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i12.38001","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123844518","display_name":"Yunxi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yunxi Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129710699","display_name":"Shuaiyu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaiyu Liu","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129731955","display_name":"Qiling Li","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiling Li","raw_affiliation_strings":["Huazhong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129706951","display_name":"Yazhou Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yazhou Ren","raw_affiliation_strings":["University of Electronic Science and Technology of China\nShenzhen Institute for Advanced Study, University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China\nShenzhen Institute for Advanced Study, University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103248543","display_name":"Xiaorong Pu","orcid":"https://orcid.org/0000-0001-7387-7194"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorong Pu","raw_affiliation_strings":["University of Electronic Science and Technology of China\nShenzhen Institute for Advanced Study, University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China\nShenzhen Institute for Advanced Study, University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5123844518"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15256959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"12","first_page":"10315","last_page":"10322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.4325999915599823,"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"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.4325999915599823,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.08789999783039093,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.06840000301599503,"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/network-topology","display_name":"Network topology","score":0.4812000095844269},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4803999960422516},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.4296000003814697},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.382999986410141},{"id":"https://openalex.org/keywords/topological-graph","display_name":"Topological graph","score":0.38280001282691956},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3781000077724457},{"id":"https://openalex.org/keywords/graph-theory","display_name":"Graph theory","score":0.32659998536109924},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.29660001397132874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7554000020027161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.539900004863739},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40549999475479126},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.382999986410141},{"id":"https://openalex.org/C8764922","wikidata":"https://www.wikidata.org/wiki/Q17104195","display_name":"Topological graph","level":3,"score":0.38280001282691956},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i12.38001","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.38001","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i12.38001","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.38001","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scene":[0,58],"recognition":[1,22,146],"(SR)":[2],"is":[3],"a":[4],"fundamental":[5],"task":[6],"in":[7,20,143],"computer":[8],"vision":[9],"(CV).":[10],"In":[11],"recent":[12],"years,":[13],"Transformer-based":[14],"methods":[15],"have":[16],"achieved":[17],"remarkable":[18],"success":[19],"scene":[21,47,72,145],"tasks.":[23,147],"Most":[24],"existing":[25],"approaches":[26],"primarily":[27],"rely":[28],"on":[29,151,168],"visual":[30,128],"features,":[31],"while":[32],"failing":[33],"to":[34,70,109,136],"effectively":[35],"model":[36],"the":[37,105,133,152],"structural":[38],"relationships":[39,67],"within":[40],"scenes,":[41],"which":[42],"are":[43],"crucial":[44],"for":[45,57],"accurate":[46],"recognition.":[48,73],"To":[49],"this":[50],"end,":[51],"we":[52,114],"propose":[53],"Topology":[54,100],"Attention":[55,76,101],"Network":[56,79],"Recognition":[59],"(TANSR),":[60],"an":[61,116],"innovative":[62,117],"method":[63],"that":[64,122],"leverages":[65],"topological":[66,111,125,138],"from":[68,84],"graphs":[69],"guide":[71],"Specifically,":[74],"Graph":[75,89],"Mask":[77],"Generation":[78,90],"(GAMGN)":[80],"generates":[81],"topology-aware":[82],"masks":[83],"graph":[85],"representations":[86],"constructed":[87],"by":[88,99],"Module":[91],"(GGM)":[92],"and":[93,140,156],"integrates":[94,123],"them":[95],"with":[96,127],"patch":[97,129],"embeddings":[98],"Guidance":[102],"(TAG),":[103],"enabling":[104],"transformer's":[106],"attention":[107],"mechanism":[108],"incorporate":[110],"information.":[112],"Furthermore,":[113],"introduce":[115],"attention-driven":[118],"multimodal":[119],"fusion":[120],"strategy":[121],"graph-derived":[124],"cues":[126],"embeddings,":[130],"substantially":[131],"enhancing":[132],"transformer\u2019s":[134],"capability":[135],"capture":[137],"information":[139],"improving":[141],"performance":[142],"complex":[144],"We":[148],"evaluate":[149],"TANSR":[150],"benchmarks":[153],"MIT-67,":[154],"Scene-15":[155],"SUN397,":[157],"where":[158],"it":[159],"achieves":[160],"consistent":[161],"state-of-the-art":[162],"(SOTA)":[163],"performance,":[164],"including":[165],"98.58%":[166],"accuracy":[167],"MIT-67.":[169]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}