{"id":"https://openalex.org/W4414458694","doi":"https://doi.org/10.1109/tcsvt.2025.3613770","title":"HyPSAM: Hybrid Prompt-Driven Segment Anything Model for RGB-Thermal Salient Object Detection","display_name":"HyPSAM: Hybrid Prompt-Driven Segment Anything Model for RGB-Thermal Salient Object Detection","publication_year":2025,"publication_date":"2025-09-24","ids":{"openalex":"https://openalex.org/W4414458694","doi":"https://doi.org/10.1109/tcsvt.2025.3613770"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3613770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3613770","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","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/A5101906482","display_name":"Ruichao Hou","orcid":"https://orcid.org/0000-0001-8111-7339"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruichao Hou","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8111-7339","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xingyuan Li","orcid":"https://orcid.org/0009-0008-1047-3174"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyuan Li","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0008-1047-3174","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084591510","display_name":"Tongwei Ren","orcid":"https://orcid.org/0000-0003-3092-424X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongwei Ren","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3092-424X","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069672411","display_name":"Dongming Zhou","orcid":"https://orcid.org/0000-0003-0139-9415"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongming Zhou","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0003-0139-9415","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101546753","display_name":"Gangshan Wu","orcid":"https://orcid.org/0000-0003-1391-1762"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangshan Wu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1391-1762","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017808266","display_name":"Jinde Cao","orcid":"https://orcid.org/0000-0003-3133-7119"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinde Cao","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3133-7119","affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8276,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.94187399,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"36","issue":"3","first_page":"2697","last_page":"2712"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9926999807357788,"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":0.9926999807357788,"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":0.9593999981880188,"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/salient","display_name":"Salient","score":0.6326000094413757},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5842000246047974},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.574999988079071},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5544999837875366},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5422000288963318},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5422000288963318},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5299999713897705},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5134000182151794},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.478300005197525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.843999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7027999758720398},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6326000094413757},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5842000246047974},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.574999988079071},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5544999837875366},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5299999713897705},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5163000226020813},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5134000182151794},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4756999909877777},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.375},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3613770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3613770","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4388298099","display_name":null,"funder_award_id":"021714380026","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7343946151","display_name":null,"funder_award_id":"BE2022138","funder_id":"https://openalex.org/F4320327777","funder_display_name":"Jiangsu Provincial Key Research and Development Program"},{"id":"https://openalex.org/G7458595415","display_name":"\u9762\u5411\u590d\u6742\u573a\u666f\u89c6\u9891\u7684\u89c6\u89c9\u5173\u7cfb\u68c0\u6d4b\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072232","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G934389289","display_name":null,"funder_award_id":"62576098","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"},{"id":"https://openalex.org/F4320327777","display_name":"Jiangsu Provincial Key Research and Development Program","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W20683899","https://openalex.org/W1580389772","https://openalex.org/W1976409045","https://openalex.org/W1982075130","https://openalex.org/W1993713494","https://openalex.org/W1994922096","https://openalex.org/W2100470808","https://openalex.org/W2128272608","https://openalex.org/W2132083787","https://openalex.org/W2293332611","https://openalex.org/W2780861787","https://openalex.org/W2887356459","https://openalex.org/W2887486131","https://openalex.org/W2895230054","https://openalex.org/W2945809413","https://openalex.org/W2961348656","https://openalex.org/W2963529609","https://openalex.org/W2963868681","https://openalex.org/W3034185160","https://openalex.org/W3034278117","https://openalex.org/W3039479109","https://openalex.org/W3047800102","https://openalex.org/W3108822985","https://openalex.org/W3114651545","https://openalex.org/W3127859904","https://openalex.org/W3164802490","https://openalex.org/W3166092877","https://openalex.org/W3181848549","https://openalex.org/W3183152796","https://openalex.org/W3185043317","https://openalex.org/W3188963955","https://openalex.org/W3212645988","https://openalex.org/W4239147634","https://openalex.org/W4285040441","https://openalex.org/W4285058230","https://openalex.org/W4285163934","https://openalex.org/W4288773267","https://openalex.org/W4295165408","https://openalex.org/W4307125574","https://openalex.org/W4310018131","https://openalex.org/W4312349930","https://openalex.org/W4312699294","https://openalex.org/W4313546627","https://openalex.org/W4315606099","https://openalex.org/W4315607725","https://openalex.org/W4319866558","https://openalex.org/W4366966982","https://openalex.org/W4366984207","https://openalex.org/W4367663481","https://openalex.org/W4376872192","https://openalex.org/W4381199011","https://openalex.org/W4382398496","https://openalex.org/W4382462760","https://openalex.org/W4383890466","https://openalex.org/W4386066371","https://openalex.org/W4387614573","https://openalex.org/W4387747474","https://openalex.org/W4390479138","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4391407087","https://openalex.org/W4391992698","https://openalex.org/W4392346283","https://openalex.org/W4392346680","https://openalex.org/W4392824656","https://openalex.org/W4394938975","https://openalex.org/W4399409690","https://openalex.org/W4399423104","https://openalex.org/W4401326954","https://openalex.org/W4403780636","https://openalex.org/W4403791281","https://openalex.org/W4403936775","https://openalex.org/W4404056751","https://openalex.org/W4404565361","https://openalex.org/W4405056285","https://openalex.org/W4407242310","https://openalex.org/W4407247100","https://openalex.org/W4408202082","https://openalex.org/W4413144420","https://openalex.org/W4415708725"],"related_works":[],"abstract_inverted_index":{"RGB-thermal":[0],"salient":[1,154],"object":[2,155],"detection":[3],"(RGB-T":[4],"SOD)":[5],"aims":[6],"to":[7,31,97,128,182],"identify":[8],"prominent":[9],"objects":[10,27],"by":[11,135],"integrating":[12,176],"complementary":[13],"information":[14],"from":[15],"RGB":[16],"and":[17,25,37,94,108,149,199],"thermal":[18],"modalities.":[19],"However,":[20],"learning":[21],"the":[22,32,38,59,64,103,147,189],"precise":[23,153],"boundaries":[24],"complete":[26],"remains":[28],"challenging":[29],"due":[30],"intrinsic":[33],"insufficient":[34],"feature":[35,111],"fusion":[36,78],"extrinsic":[39],"limitations":[40,104],"of":[41,63,105,191,201],"data":[42],"scarcity.":[43],"In":[44],"this":[45,195],"paper,":[46],"we":[47,73,114],"propose":[48,75,115],"a":[49,76,116,124],"novel":[50],"hybrid":[51,137],"prompt-driven":[52],"segment":[53,65],"anything":[54,66],"model":[55,67],"(HyPSAM),":[56],"which":[57,121],"leverages":[58],"zero-shot":[60],"generalization":[61],"capabilities":[62],"(SAM)":[68],"for":[69],"RGB-T":[70,179],"SOD.":[71],"Specifically,":[72],"first":[74],"dynamic":[77,92],"network":[79,119],"(DFNet)":[80],"that":[81,164],"generates":[82],"high-quality":[83],"initial":[84],"saliency":[85,133],"maps":[86,134],"as":[87,123],"visual":[88],"prompts.":[89,138],"DFNet":[90],"employs":[91],"convolution":[93],"multi-branch":[95],"decoding":[96],"facilitate":[98],"adaptive":[99],"cross-modality":[100],"interaction,":[101],"overcoming":[102],"fixed-parameter":[106],"kernels":[107],"enhancing":[109],"multi-modal":[110],"representation.":[112],"Moreover,":[113],"plug-and-play":[117],"refinement":[118],"(P2RNet)":[120],"serves":[122],"general":[125],"optimization":[126],"strategy":[127],"guide":[129],"SAM":[130],"in":[131,194],"refining":[132],"using":[136],"The":[139,197],"text":[140],"prompt":[141,192],"ensures":[142],"reliable":[143],"modality":[144],"input,":[145],"while":[146],"mask":[148],"box":[150],"prompts":[151],"enable":[152],"localization.":[156],"Extensive":[157],"experiments":[158],"on":[159],"three":[160],"public":[161],"datasets":[162],"demonstrate":[163],"our":[165,202],"method":[166,203],"achieves":[167],"state-of-the-art":[168],"performance.":[169],"Notably,":[170],"HyPSAM":[171],"has":[172],"remarkable":[173],"versatility,":[174],"seamlessly":[175],"with":[177],"different":[178],"SOD":[180],"methods":[181],"achieve":[183],"significant":[184],"performance":[185],"gains,":[186],"thereby":[187],"highlighting":[188],"potential":[190],"engineering":[193],"field.":[196],"code":[198],"results":[200],"are":[204],"available":[205],"at:":[206],"https://github.com/milotic233/HyPSAM.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}