{"id":"https://openalex.org/W7164052704","doi":"https://doi.org/10.48550/arxiv.2606.09262","title":"See More, Match Better: Multi-Source Feature Fusion for Two-View Correspondence Learning","display_name":"See More, Match Better: Multi-Source Feature Fusion for Two-View Correspondence Learning","publication_year":2026,"publication_date":"2026-06-08","ids":{"openalex":"https://openalex.org/W7164052704","doi":"https://doi.org/10.48550/arxiv.2606.09262"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.09262","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09262","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.09262","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138240425","display_name":"Xiaojie Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiaojie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138262399","display_name":"Xin Jiang (6348)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109483631","display_name":"Luanyuan Dai","orcid":"https://orcid.org/0009-0006-6235-2580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Luanyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138237593","display_name":"Jinnan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jinnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138210694","display_name":"Yongdong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yongdong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138202023","display_name":"Zechao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zechao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.3718000054359436,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.3718000054359436,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.13220000267028809,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.08980000019073486,"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/feature","display_name":"Feature (linguistics)","score":0.7156000137329102},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6579999923706055},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6305000185966492},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.555899977684021},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5228999853134155},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3889000117778778},{"id":"https://openalex.org/keywords/correspondence-problem","display_name":"Correspondence problem","score":0.384799987077713}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7357000112533569},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7156000137329102},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6579999923706055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6424000263214111},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6305000185966492},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.555899977684021},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5228999853134155},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C3004257","wikidata":"https://www.wikidata.org/wiki/Q17084606","display_name":"Correspondence problem","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3513999879360199},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.31700000166893005},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31520000100135803},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.304500013589859},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.28519999980926514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26460000872612}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.09262","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09262","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.09262","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09262","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.5904942154884338,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Two-view":[0],"correspondence":[1,62,92,156],"learning":[2],"aims":[3],"to":[4,87,137],"distinguish":[5],"true":[6],"correspondences":[7],"(inliers)":[8],"from":[9],"false":[10],"ones":[11],"(outliers)":[12],"in":[13,36],"image":[14],"pairs":[15],"by":[16],"leveraging":[17],"their":[18],"underlying":[19],"differences.":[20],"Existing":[21],"methods":[22],"mainly":[23],"rely":[24],"on":[25],"coordinate-based":[26],"geometric":[27,46,101,111,132],"consistency.":[28],"However,":[29],"they":[30],"often":[31],"struggle":[32],"with":[33,110],"pseudo-consistent":[34],"outliers":[35],"scenes":[37],"containing":[38],"repetitive":[39],"structures,":[40],"textureless":[41],"regions,":[42],"or":[43],"locally":[44],"similar":[45],"patterns.":[47],"To":[48,94],"address":[49],"this":[50],"limitation,":[51],"we":[52],"propose":[53],"TriMatch,":[54],"a":[55,125,148],"multi-source":[56],"feature":[57,69,72,75,146,161],"fusion":[58],"framework":[59],"for":[60,91],"two-view":[61],"learning,":[63],"which":[64,130],"consists":[65],"of":[66,177],"two":[67],"parts:":[68],"extraction":[70],"and":[71,83,100,104,117,158,174],"refinement.":[73],"In":[74,145],"extraction,":[76],"TriMatch":[77],"jointly":[78],"extracts":[79],"geometric,":[80],"texture":[81,103],"semantic,":[82],"structural":[84,105],"semantic":[85,99,106,135],"features":[86,107,112,133],"provide":[88],"complementary":[89],"evidence":[90],"discrimination.":[93,167],"bridge":[95],"the":[96,171],"gap":[97],"between":[98],"features,":[102],"are":[108],"aligned":[109],"through":[113],"dedicated":[114],"Texture-Geometric":[115],"Alignment":[116,119],"Structural-Geometric":[118],"modules,":[120],"respectively.":[121],"We":[122],"further":[123],"introduce":[124],"Semantic-Guided":[126],"Correspondence":[127,151],"Modulation":[128],"module,":[129],"modulates":[131],"using":[134],"information":[136],"suppress":[138],"geometrically":[139],"plausible":[140],"but":[141],"semantically":[142],"inconsistent":[143],"correspondences.":[144],"refinement,":[147],"Hierarchical":[149],"Semantic-Enhanced":[150],"Refinement":[152],"strategy":[153],"progressively":[154],"models":[155],"dependencies":[157],"recalibrates":[159],"multi-context":[160],"responses,":[162],"enabling":[163],"more":[164],"reliable":[165],"inlier-outlier":[166],"Extensive":[168],"experiments":[169],"demonstrate":[170],"effectiveness,":[172],"robustness,":[173],"generalization":[175],"capability":[176],"TriMatch.":[178]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}