{"id":"https://openalex.org/W4415428823","doi":"https://doi.org/10.3233/faia250810","title":"HAT-Match: Graph Transformer with Hybrid Attention for Two-View Correspondence Pruning","display_name":"HAT-Match: Graph Transformer with Hybrid Attention for Two-View Correspondence Pruning","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428823","doi":"https://doi.org/10.3233/faia250810"},"language":null,"primary_location":{"id":"doi:10.3233/faia250810","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250810","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250810","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100367301","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0001-6342-1337"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["School of Statistics and Data Science, Shanghai University of Finance and Economics, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Statistics and Data Science, Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067244141","display_name":"Bin Wu","orcid":"https://orcid.org/0000-0003-3779-5735"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]},{"id":"https://openalex.org/I90727586","display_name":"Zhejiang University of Finance and Economics","ror":"https://ror.org/055vj5234","country_code":"CN","type":"education","lineage":["https://openalex.org/I90727586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wu","raw_affiliation_strings":["Shanghai University of Finance and Economics Zhejiang College, Jinhua, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics Zhejiang College, Jinhua, China","institution_ids":["https://openalex.org/I181679659","https://openalex.org/I90727586"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100411552","display_name":"Yufei Chen","orcid":"https://orcid.org/0000-0002-6802-4346"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Chen","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.55953046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9106000065803528,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9106000065803528,"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/discriminative-model","display_name":"Discriminative model","score":0.6904000043869019},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5957000255584717},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5473999977111816},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5379999876022339},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5291000008583069},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5024999976158142},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.4982999861240387},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.43070000410079956},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.38929998874664307}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6904000043869019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6524999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6367999911308289},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5957000255584717},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5473999977111816},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5379999876022339},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5291000008583069},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.43070000410079956},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33899998664855957},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2906000018119812},{"id":"https://openalex.org/C100595998","wikidata":"https://www.wikidata.org/wiki/Q11731931","display_name":"Graph kernel","level":5,"score":0.27160000801086426},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia250810","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250810","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia250810","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250810","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","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":[],"abstract_inverted_index":{"Feature":[0],"correspondence,":[1],"particularly":[2],"distinguishing":[3],"inliers":[4],"(true":[5],"matches)":[6],"from":[7],"outliers":[8,162],"(false":[9],"matches),":[10],"remains":[11],"a":[12,22,72,100,120,155],"core":[13],"challenge":[14],"in":[15],"geometric":[16,64],"computer":[17],"vision.":[18],"We":[19],"present":[20],"HAT-Match,":[21],"novel":[23],"Graph":[24],"Transformer":[25],"framework":[26,158],"with":[27],"Hybrid":[28],"Attention":[29],"for":[30,41,48,57],"two-view":[31],"correspondence":[32,134,165],"pruning.":[33],"HAT-Match":[34,171],"integrates":[35],"three":[36],"types":[37],"of":[38,85,109],"attention":[39,47,122,140],"mechanismsself-attention":[40],"modeling":[42,108],"pairwise":[43],"dependencies,":[44],"SE-based":[45],"channel":[46],"emphasizing":[49],"salient":[50],"feature":[51,147],"channels,":[52],"and":[53,76,128,163,183,189],"global":[54,55,129,143],"structure-aware":[56,59],"capturing":[58],"consistency.":[60],"To":[61,132],"model":[62],"local":[63,97,111,114,127],"relationships,":[65],"we":[66,94,136],"first":[67],"generate":[68],"coarse":[69],"clusters":[70],"using":[71,99],"permutation-equivariant":[73],"graph":[74,138],"pooling":[75],"unpooling":[77],"mechanism,":[78],"which":[79],"serves":[80],"as":[81],"an":[82],"initial":[83],"grouping":[84],"potentially":[86],"consistent":[87],"correspondences.":[88],"Based":[89],"on":[90,186],"the":[91,107,142],"resulting":[92],"embeddings,":[93],"further":[95],"construct":[96],"graphs":[98,115],"DGCNN-style":[101],"k-nearest":[102],"neighbor":[103],"(KNN)":[104],"strategy,":[105],"enabling":[106],"fine-grained":[110],"dependencies.":[112],"These":[113],"are":[116],"then":[117],"passed":[118],"through":[119],"hybrid":[121],"module":[123],"that":[124,159,170],"jointly":[125],"encodes":[126],"contextual":[130],"features.":[131],"refine":[133],"confidence,":[135],"apply":[137],"Laplacian-based":[139],"over":[141],"graph,":[144],"enhancing":[145],"discriminative":[146],"propagation.":[148],"The":[149],"entire":[150],"architecture":[151],"is":[152],"integrated":[153],"into":[154],"progressive":[156],"pruning":[157],"iteratively":[160],"removes":[161],"updates":[164],"weights.":[166],"Extensive":[167],"experiments":[168],"demonstrate":[169],"achieves":[172],"state-of-the-art":[173],"results":[174],"across":[175],"various":[176],"challenging":[177],"tasks,":[178],"including":[179],"relative":[180],"pose":[181],"estimation":[182],"visual":[184],"localization,":[185],"both":[187],"indoor":[188],"outdoor":[190],"datasets.":[191]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-24T00:00:00"}