{"id":"https://openalex.org/W7125418978","doi":"https://doi.org/10.1109/tip.2026.3654367","title":"SigMa: Semantic Similarity-Guided Semi-Dense Feature Matching","display_name":"SigMa: Semantic Similarity-Guided Semi-Dense Feature Matching","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7125418978","doi":"https://doi.org/10.1109/tip.2026.3654367","pmid":"https://pubmed.ncbi.nlm.nih.gov/41564050"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3654367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3654367","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5123549899","display_name":"Xiang Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Fang","raw_affiliation_strings":["Electronic Information School, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Information School, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103012164","display_name":"Zizhuo Li","orcid":"https://orcid.org/0000-0003-0986-4924"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zizhuo Li","raw_affiliation_strings":["Electronic Information School, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-0986-4924","affiliations":[{"raw_affiliation_string":"Electronic Information School, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123584420","display_name":"Jiayi Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Ma","raw_affiliation_strings":["Electronic Information School and the School of Robotics, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-3264-3265","affiliations":[{"raw_affiliation_string":"Electronic Information School and the School of Robotics, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07893389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"872","last_page":"887"},"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":0.8238000273704529,"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":0.8238000273704529,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.11270000040531158,"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":0.01759999990463257,"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/feature","display_name":"Feature (linguistics)","score":0.5361999869346619},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5231000185012817},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5230000019073486},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4611000120639801},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.4593999981880188},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.41499999165534973},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.41350001096725464},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.40059998631477356},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3732999861240387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897999882698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6274999976158142},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5361999869346619},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5231000185012817},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5230000019073486},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.3497999906539917},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3422999978065491},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.3059999942779541},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.26030001044273376}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3654367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3654367","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:41564050","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41564050","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G415731887","display_name":null,"funder_award_id":"62276192","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1985238052","https://openalex.org/W2033819227","https://openalex.org/W2071730188","https://openalex.org/W2085261163","https://openalex.org/W2090042335","https://openalex.org/W2106199912","https://openalex.org/W2111073598","https://openalex.org/W2117228865","https://openalex.org/W2118185515","https://openalex.org/W2119531879","https://openalex.org/W2119605622","https://openalex.org/W2143641248","https://openalex.org/W2151103935","https://openalex.org/W2194775991","https://openalex.org/W2320444803","https://openalex.org/W2565639579","https://openalex.org/W2594519801","https://openalex.org/W2740418457","https://openalex.org/W2740578684","https://openalex.org/W2891751697","https://openalex.org/W2963210849","https://openalex.org/W2963674285","https://openalex.org/W2963748588","https://openalex.org/W2963760790","https://openalex.org/W2967756832","https://openalex.org/W2990655570","https://openalex.org/W3034275286","https://openalex.org/W3043075211","https://openalex.org/W3047057232","https://openalex.org/W3166285241","https://openalex.org/W3167976421","https://openalex.org/W3193951565","https://openalex.org/W4221154336","https://openalex.org/W4312548398","https://openalex.org/W4312933868","https://openalex.org/W4367359398","https://openalex.org/W4382458246","https://openalex.org/W4385245566","https://openalex.org/W4386075582","https://openalex.org/W4386076421","https://openalex.org/W4386083040","https://openalex.org/W4388209785","https://openalex.org/W4388820233","https://openalex.org/W4388979610","https://openalex.org/W4390871894","https://openalex.org/W4390871957","https://openalex.org/W4390872507","https://openalex.org/W4390874575","https://openalex.org/W4392172801","https://openalex.org/W4392207980","https://openalex.org/W4393154708","https://openalex.org/W4399563958","https://openalex.org/W4402753623","https://openalex.org/W4402753858","https://openalex.org/W4402771002","https://openalex.org/W4402772491","https://openalex.org/W4403510307","https://openalex.org/W4403791274","https://openalex.org/W4403791581","https://openalex.org/W4404409093","https://openalex.org/W4405138903","https://openalex.org/W4409365765","https://openalex.org/W4412610820","https://openalex.org/W4413145170","https://openalex.org/W4413155710"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"have":[2],"led":[3],"the":[4,55,94,129,132,140,213],"image":[5],"matching":[6,51],"community":[7],"to":[8,26,81,167,211],"increasingly":[9],"focus":[10],"on":[11,28,131,152,177],"obtaining":[12],"subpixel-level":[13],"correspondences":[14],"in":[15],"a":[16,46,68,73,77,107,147,185,203],"detector-free":[17],"manner,":[18],"i.e.,":[19],"semi-dense":[20,49],"feature":[21,50,70,109,134],"matching.":[22],"Existing":[23],"methods":[24],"tend":[25],"overfocus":[27],"low-level":[29,83],"local":[30,59,84,143],"features":[31,60,85,99],"while":[32,171],"ignoring":[33],"equally":[34],"important":[35],"high-level":[36,62,87],"semantic":[37,47,63,88,153],"information.":[38],"To":[39,91],"tackle":[40],"these":[41,97],"shortcomings,":[42],"we":[43,66,104,125,201],"propose":[44],"SigMa,":[45],"similarity-guided":[48],"method,":[52],"which":[53,111],"leverages":[54],"strengths":[56],"of":[57,96,139,142,205,217],"both":[58],"and":[61,76,86,100,121,192,208,215],"features.":[64],"First,":[65],"design":[67,146],"dual-branch":[69],"extractor,":[71],"comprising":[72],"convolutional":[74],"network":[75],"vision":[78],"foundation":[79],"model,":[80],"extract":[82],"features,":[89],"respectively.":[90],"fully":[92],"retain":[93],"advantages":[95],"two":[98],"effectively":[101],"integrate":[102],"them,":[103],"also":[105],"introduce":[106],"cross-domain":[108],"adapter,":[110],"could":[112],"overcome":[113],"their":[114],"spatial":[115],"resolution":[116],"mismatches,":[117],"channel":[118],"dimensionality":[119],"variations,":[120],"inter-domain":[122],"gaps.":[123],"Furthermore,":[124],"observe":[126],"that":[127,181],"performing":[128],"transformer":[130],"whole":[133],"map":[135],"is":[136,223],"unnecessary":[137],"because":[138],"similarity":[141],"representations.":[144],"We":[145],"guided":[148],"pooling":[149],"method":[150,183],"based":[151],"similarity.":[154],"This":[155],"strategy":[156],"performs":[157],"attention":[158],"computation":[159],"by":[160],"selecting":[161],"highly":[162],"semantically":[163],"similar":[164],"regions,":[165],"aiming":[166],"minimize":[168],"information":[169],"loss":[170],"maintaining":[172],"computational":[173],"efficiency.":[174],"Extensive":[175],"experiments":[176,210],"multiple":[178],"datasets":[179],"demonstrate":[180],"our":[182,218],"achieves":[184],"competitive":[186],"accuracy-efficiency":[187],"trade-off":[188],"across":[189,197],"various":[190],"tasks":[191],"exhibits":[193],"strong":[194],"generalization":[195],"capabilities":[196],"different":[198],"datasets.":[199],"Additionally,":[200],"conduct":[202],"series":[204],"ablation":[206],"studies":[207],"analysis":[209],"validate":[212],"effectiveness":[214],"rationality":[216],"method's":[219],"design.":[220],"Our":[221],"code":[222],"publicly":[224],"available":[225],"at":[226],"https://github.com/ShineFox/SigMa.":[227]},"counts_by_year":[],"updated_date":"2026-01-30T23:17:42.513302","created_date":"2026-01-23T00:00:00"}