{"id":"https://openalex.org/W4415537830","doi":"https://doi.org/10.1145/3746027.3755718","title":"SAM-Guided Semantic Knowledge Fusion for Visible-Infrared Object Detection","display_name":"SAM-Guided Semantic Knowledge Fusion for Visible-Infrared Object Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537830","doi":"https://doi.org/10.1145/3746027.3755718"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755718","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5103681744","display_name":"Ting Li","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":"Ting Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0005-9939-578X","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Songtao Li","orcid":"https://orcid.org/0000-0003-2126-9554"},"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":"Songtao Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-2126-9554","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101939278","display_name":"Shuaifeng Li","orcid":"https://orcid.org/0000-0003-2371-2513"},"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":"Shuaifeng Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-2371-2513","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109186228","display_name":"Xiaolin Qin","orcid":"https://orcid.org/0000-0001-5087-8178"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Qin","raw_affiliation_strings":["Chinese Academy of Sciences, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-5087-8178","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Chengdu, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Maoyuan Zhao","orcid":"https://orcid.org/0009-0000-6000-1839"},"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":"Maoyuan Zhao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0000-6000-1839","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036253906","display_name":"Luping Ji","orcid":"https://orcid.org/0000-0002-1200-5218"},"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":"Luping Ji","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-1200-5218","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100682790","display_name":"Mao Ye","orcid":"https://orcid.org/0000-0003-4760-8702"},"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":"Mao Ye","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-4760-8702","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8273,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92329321,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8835","last_page":"8844"},"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":0.998199999332428,"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":0.998199999332428,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5931000113487244},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.5408999919891357},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5288000106811523},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5214999914169312},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.520799994468689},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4124999940395355},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40540000796318054},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.3986999988555908},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.39410001039505005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940999865531921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6890000104904175},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5931000113487244},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.5408999919891357},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5214999914169312},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4584999978542328},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.38940000534057617},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.3603000044822693},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3296000063419342},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.328000009059906},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3197999894618988},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755718","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G563218425","display_name":null,"funder_award_id":"62276048, 62476049","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2176924101","https://openalex.org/W2548527721","https://openalex.org/W2601564443","https://openalex.org/W2929607865","https://openalex.org/W2963351448","https://openalex.org/W2964979676","https://openalex.org/W3085056143","https://openalex.org/W3130394099","https://openalex.org/W3195903836","https://openalex.org/W3207919963","https://openalex.org/W4200631567","https://openalex.org/W4214648418","https://openalex.org/W4224100776","https://openalex.org/W4225125774","https://openalex.org/W4385284012","https://openalex.org/W4386083029","https://openalex.org/W4387831688","https://openalex.org/W4390787329","https://openalex.org/W4390874575","https://openalex.org/W4391021462","https://openalex.org/W4392939416","https://openalex.org/W4393171245","https://openalex.org/W4394585952","https://openalex.org/W4401344482","https://openalex.org/W4401870923","https://openalex.org/W4402041007","https://openalex.org/W4404562995","https://openalex.org/W4407800509"],"related_works":[],"abstract_inverted_index":{"Visible-infrared":[0],"object":[1],"detection":[2,40,130],"has":[3,42],"gained":[4],"significant":[5],"attention":[6],"because":[7],"of":[8,22,125],"its":[9,28],"applications":[10],"in":[11],"autonomous":[12],"driving,":[13],"video":[14],"surveillance,":[15],"and":[16,136,161,172,198],"related":[17],"fields.":[18],"The":[19,30,59],"effective":[20],"fusion":[21,38,55,75,173,180],"multimodal":[23],"information":[24],"is":[25,62,202],"fundamental":[26],"to":[27,63,128,148],"success.":[29],"existing":[31],"approaches":[32],"concentrate":[33],"on":[34,100,194],"improving":[35],"the":[36,84,87,113,116,123,129,141,178,195],"pixel-level":[37,179],"mechanisms;":[39],"performance":[41,193],"reached":[43],"a":[44,48,72,189],"plateau.":[45],"We":[46],"propose":[47],"new":[49],"framework":[50],"for":[51],"SAM-guided":[52],"semantic":[53,65,170],"knowledge":[54,127],"(":[56],"SemFusion":[57],").":[58],"core":[60],"idea":[61],"leverage":[64],"priors":[66],"from":[67],"large":[68],"models":[69],"while":[70],"incorporating":[71],"lightweight":[73],"cross-modal":[74,156],"strategy.":[76],"Specifically,":[77],"our":[78,186],"method":[79],"comprises":[80],"two":[81],"stages.":[82],"In":[83,112],"first":[85],"stage,":[86,115],"Flow-Guided":[88],"RGB":[89],"Feature":[90],"Alignment":[91],"(FGRA)":[92],"module":[93],"establishes":[94],"object-aware":[95],"correspondences":[96],"between":[97],"multimodalities":[98],"based":[99],"SAM-generated":[101],"masks.":[102],"This":[103],"ensures":[104],"semantic-level":[105],"feature":[106,163],"matching":[107],"by":[108],"deformable":[109,155],"convolution":[110],"alignment.":[111],"second":[114],"Semantic":[117],"Knowledge":[118],"Distillation":[119],"(SKD)":[120],"strategy":[121],"facilitates":[122],"transfer":[124],"large-model":[126],"model":[131],"through":[132],"SAM":[133,168],"feature,":[134],"offset,":[135],"mask":[137],"level":[138],"distillations.":[139],"For":[140],"detector":[142],"model,":[143],"three":[144],"blocks":[145],"are":[146,154],"designed":[147],"augment":[149],"any":[150],"off-the-shelf":[151],"detector.":[152],"They":[153],"alignment,":[157],"spatio-channel":[158],"preliminary":[159],"fusion,":[160],"mask-guided":[162],"refinement.":[164],"By":[165],"alignment":[166,171],"with":[167],"masks,":[169],"can":[174],"be":[175],"achieved,":[176],"breaking":[177],"barrier.":[181],"Extensive":[182],"experiments":[183],"demonstrate":[184],"that":[185],"method,":[187],"as":[188],"plugin,":[190],"exhibits":[191],"superior":[192],"DroneVehicle,":[196],"VEDAI,":[197],"LLVIP":[199],"datasets.":[200],"Code":[201],"available":[203],"at":[204],"https://github.com/liting1018/SemFusion.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}