{"id":"https://openalex.org/W4412403845","doi":"https://doi.org/10.1109/tcsvt.2025.3588722","title":"Multi-Modal Few-Shot Semantic Segmentation Based on Triple Attention Mechanism and Hierarchical Decoding Transformer","display_name":"Multi-Modal Few-Shot Semantic Segmentation Based on Triple Attention Mechanism and Hierarchical Decoding Transformer","publication_year":2025,"publication_date":"2025-07-14","ids":{"openalex":"https://openalex.org/W4412403845","doi":"https://doi.org/10.1109/tcsvt.2025.3588722"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3588722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3588722","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/A5022046431","display_name":"Junsong Leng","orcid":"https://orcid.org/0000-0001-6443-1190"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junsong Leng","raw_affiliation_strings":["State Key Laboratory of Multispectral Information Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","School of Artificial Intelligence and Automation, State Key Laboratory of Multispectral Information Processing Technology, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multispectral Information Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Artificial Intelligence and Automation, State Key Laboratory of Multispectral Information Processing Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084498173","display_name":"Zeyu Zhao","orcid":"https://orcid.org/0000-0002-3748-2555"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Zhao","raw_affiliation_strings":["State Key Laboratory of Multispectral Information Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","School of Artificial Intelligence and Automation, State Key Laboratory of Multispectral Information Processing Technology, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multispectral Information Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Artificial Intelligence and Automation, State Key Laboratory of Multispectral Information Processing Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100304489","display_name":"Chang Tian","orcid":"https://orcid.org/0000-0003-4933-4063"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Tian","raw_affiliation_strings":["State Key Laboratory of Multispectral Information Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","School of Artificial Intelligence and Automation, State Key Laboratory of Multispectral Information Processing Technology, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multispectral Information Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Artificial Intelligence and Automation, State Key Laboratory of Multispectral Information Processing Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430402","display_name":"Zhong Chen","orcid":"https://orcid.org/0000-0001-8256-0156"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Chen","raw_affiliation_strings":["State Key Laboratory of Multispectral Information Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","School of Artificial Intelligence and Automation, State Key Laboratory of Multispectral Information Processing Technology, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multispectral Information Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Artificial Intelligence and Automation, State Key Laboratory of Multispectral Information Processing Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077461682","display_name":"Guoyou Wang","orcid":"https://orcid.org/0000-0001-5447-4111"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoyou Wang","raw_affiliation_strings":["State Key Laboratory of Multispectral Information Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","School of Artificial Intelligence and Automation, State Key Laboratory of Multispectral Information Processing Technology, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multispectral Information Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Artificial Intelligence and Automation, State Key Laboratory of Multispectral Information Processing Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100666862","display_name":"Xiaoxuan Liu","orcid":"https://orcid.org/0000-0002-1426-5056"},"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"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxuan Liu","raw_affiliation_strings":["Chinese Academy of Sciences, Aerospace Information Research Institute, Beijing, China","Aerospace Information Research Institute Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Aerospace Information Research Institute, Beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Aerospace Information Research Institute Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5022046431"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18898529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"1","first_page":"717","last_page":"731"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.8833000063896179,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.8833000063896179,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.8644000291824341,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.8402000069618225,"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/computer-science","display_name":"Computer science","score":0.639477550983429},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6381145715713501},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5745329856872559},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4773973524570465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4699048399925232},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4452204704284668},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35075750946998596},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33020514249801636},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1895175576210022},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12314280867576599},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10159137845039368},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1002950668334961}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.639477550983429},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6381145715713501},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5745329856872559},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4773973524570465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4699048399925232},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4452204704284668},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35075750946998596},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33020514249801636},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1895175576210022},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12314280867576599},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10159137845039368},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1002950668334961},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3588722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3588722","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1507506748","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W2108598243","https://openalex.org/W2507296351","https://openalex.org/W2560023338","https://openalex.org/W2770233088","https://openalex.org/W2963078159","https://openalex.org/W2963078860","https://openalex.org/W2963599420","https://openalex.org/W2963727650","https://openalex.org/W2963845150","https://openalex.org/W2981787211","https://openalex.org/W2983850069","https://openalex.org/W2990230185","https://openalex.org/W3033502887","https://openalex.org/W3047258141","https://openalex.org/W3106906018","https://openalex.org/W3108189450","https://openalex.org/W3176065502","https://openalex.org/W3198377975","https://openalex.org/W3204077273","https://openalex.org/W3209086464","https://openalex.org/W4214893857","https://openalex.org/W4221153269","https://openalex.org/W4224860128","https://openalex.org/W4226058394","https://openalex.org/W4285601852","https://openalex.org/W4287891158","https://openalex.org/W4289639938","https://openalex.org/W4312248562","https://openalex.org/W4312310776","https://openalex.org/W4312592495","https://openalex.org/W4313175608","https://openalex.org/W4313180545","https://openalex.org/W4313196086","https://openalex.org/W4317672152","https://openalex.org/W4362683490","https://openalex.org/W4385245566","https://openalex.org/W4386071547","https://openalex.org/W4386075526","https://openalex.org/W4386075956","https://openalex.org/W4386790226","https://openalex.org/W4386833253","https://openalex.org/W4387729931","https://openalex.org/W4388191728","https://openalex.org/W4390873881","https://openalex.org/W4390874575","https://openalex.org/W4391216174","https://openalex.org/W4391305834","https://openalex.org/W4391451889","https://openalex.org/W4391454478","https://openalex.org/W4402727134","https://openalex.org/W4402944023","https://openalex.org/W4403791750","https://openalex.org/W4404782797"],"related_works":["https://openalex.org/W2161474341","https://openalex.org/W4302615923","https://openalex.org/W3203142394","https://openalex.org/W2351061015","https://openalex.org/W4220731478","https://openalex.org/W1974101135","https://openalex.org/W2017509870","https://openalex.org/W4251141768","https://openalex.org/W4360952157","https://openalex.org/W2153647085"],"abstract_inverted_index":{"The":[0,73,136,182],"goal":[1],"of":[2,10,27,188,199],"Few-Shot":[3],"Segmentation":[4],"(FSS)":[5],"is":[6,50,139],"to":[7,52,57,69,131,141,158],"segment":[8],"images":[9],"novel":[11,103,205],"categories":[12],"using":[13],"few":[14],"labeled":[15],"examples.":[16],"However,":[17],"FSS":[18],"tasks":[19],"face":[20],"challenges":[21,34],"such":[22],"as":[23],"over-segmentation":[24],"and":[25,42,174,196],"lack":[26],"generalization":[28,195],"issues.":[29],"This":[30],"paper":[31,121],"addresses":[32],"these":[33],"by":[35],"employing":[36],"a":[37,43,87,123],"triple":[38],"attention":[39],"mechanism":[40,138],"(TAM)":[41],"hierarchical":[44],"decoding":[45],"transformer":[46],"(HDT).":[47],"Specifically,":[48],"TAM":[49],"proposed":[51,190],"enhance":[53,132],"the":[54,70,78,83,99,117,133,143,154,164,170,186,189,194],"model\u2019s":[55],"ability":[56,101],"focus":[58],"on":[59,102,169,204],"spatial":[60],"regions":[61],"within":[62],"query":[63,80],"features":[64,81,85,92],"that":[65,107],"are":[66],"semantically":[67],"relevant":[68],"target":[71],"category.":[72],"HDT":[74],"module":[75],"then":[76],"aggregates":[77],"enhanced":[79],"with":[82,93],"support":[84],"in":[86],"decoupled":[88],"manner,":[89],"generating":[90],"dense":[91],"pixel-level":[94],"semantic":[95,201],"relevance,":[96],"which":[97],"improves":[98],"segmentation":[100,118,134,197,202],"classes.":[104],"Additionally,":[105],"considering":[106],"class-level":[108],"labels":[109],"inside":[110],"image":[111,126],"can":[112],"provide":[113,159],"weak":[114],"supervision":[115],"for":[116,163],"task,":[119],"this":[120],"introduces":[122],"contrastive":[124],"language":[125],"pretraining":[127],"(CLIP)":[128],"based":[129],"model":[130],"performance.":[135,181],"Grad-CAM":[137],"utilized":[140],"convert":[142],"class":[144],"logit":[145],"scores":[146],"from":[147],"CLIP":[148],"into":[149],"localization":[150,161],"heatmaps,":[151],"effectively":[152],"leveraging":[153],"text":[155],"label":[156],"information":[157],"prior":[160],"cues":[162],"model.":[165],"Extensive":[166],"experiments":[167],"conducted":[168],"PASCAL-5<sup":[171],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[172,176],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><i>i</i></sup>":[173,177],"COCO-20<sup":[175],"datasets":[178],"demonstrate":[179],"state-of-the-art":[180],"experimental":[183],"results":[184],"validate":[185],"effectiveness":[187],"method,":[191],"significantly":[192],"improving":[193],"performance":[198],"few-shot":[200],"models":[203],"categories.":[206]},"counts_by_year":[],"updated_date":"2026-01-29T23:13:10.619473","created_date":"2025-10-10T00:00:00"}