{"id":"https://openalex.org/W7123648884","doi":"https://doi.org/10.1109/mmsp64401.2025.11324228","title":"DFR: A Decompose-Fuse-Reconstruct Framework for Multi-Modal Few-Shot Segmentation","display_name":"DFR: A Decompose-Fuse-Reconstruct Framework for Multi-Modal Few-Shot Segmentation","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7123648884","doi":"https://doi.org/10.1109/mmsp64401.2025.11324228"},"language":null,"primary_location":{"id":"doi:10.1109/mmsp64401.2025.11324228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-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/A5122950502","display_name":"Shuai Chen","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":true,"raw_author_name":"Shuai Chen","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122961849","display_name":"Fanman Meng","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":"Fanman Meng","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101828494","display_name":"Xiwei Zhang","orcid":"https://orcid.org/0000-0001-5073-3569"},"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":"Xiwei Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122931631","display_name":"Haoran Wei","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":"Haoran Wei","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075564577","display_name":"Chenhao Wu","orcid":"https://orcid.org/0000-0001-7865-1223"},"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":"Chenhao Wu","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122948659","display_name":"Qingbo Wu","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":"Qingbo Wu","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122931242","display_name":"Hongliang 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":"Hongliang Li","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5122950502"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.663613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6579999923706055,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6579999923706055,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.10130000114440918,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.039000000804662704,"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/semantics","display_name":"Semantics (computer science)","score":0.7016000151634216},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6395999789237976},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6176000237464905},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4726000130176544},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4449000060558319},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.41830000281333923},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.41029998660087585},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3278999924659729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896000146865845},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7016000151634216},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6395999789237976},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6176000237464905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6141999959945679},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3594000041484833},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.31360000371932983},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3059999942779541},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2944999933242798},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.2687000036239624},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.25929999351501465},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp64401.2025.11324228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320329861","display_name":"Natural Science Foundation of Sichuan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2031489346","https://openalex.org/W2144794286","https://openalex.org/W2412782625","https://openalex.org/W2963078159","https://openalex.org/W2990230185","https://openalex.org/W3047258141","https://openalex.org/W4214573368","https://openalex.org/W4287891158","https://openalex.org/W4312420092","https://openalex.org/W4312603774","https://openalex.org/W4313123347","https://openalex.org/W4386075526","https://openalex.org/W4386245957","https://openalex.org/W4390874575","https://openalex.org/W4393148751","https://openalex.org/W4393149717","https://openalex.org/W4393159433","https://openalex.org/W4393159443","https://openalex.org/W4402727612","https://openalex.org/W4402754105","https://openalex.org/W4402917127","https://openalex.org/W4403386295","https://openalex.org/W4409367314"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"DFR":[3,78],"(Decompose,":[4],"Fuse":[5],"and":[6,70,104,127,137,166,172],"Reconstruct),":[7],"a":[8,87,115],"novel":[9],"framework":[10,79],"that":[11,91],"addresses":[12],"the":[13,56,60],"fundamental":[14],"challenge":[15],"of":[16,44],"effectively":[17],"utilizing":[18],"multi-modal":[19,158],"guidance":[20,149],"in":[21,49],"few-shot":[22],"segmentation":[23],"(FSS).":[24],"While":[25],"existing":[26],"approaches":[27],"primarily":[28],"rely":[29],"on":[30],"visual":[31,93],"support":[32],"samples":[33],"or":[34,39],"textual":[35,99],"descriptions,":[36],"their":[37],"single":[38],"dual-modal":[40],"paradigms":[41],"limit":[42],"exploitation":[43],"rich":[45],"perceptual":[46],"information":[47],"available":[48],"real-world":[50],"scenarios.":[51],"To":[52],"overcome":[53],"this":[54],"limitation,":[55],"proposed":[57],"approach":[58],"leverages":[59],"Segment":[61],"Anything":[62],"Model":[63],"(SAM)":[64],"to":[65,121],"systematically":[66],"integrate":[67],"visual,":[68,125,164],"textual,":[69,126,165],"audio":[71,106,128,167],"modalities":[72,129,168],"for":[73,108],"enhanced":[74],"semantic":[75,133,148],"understanding.":[76],"The":[77],"introduces":[80],"three":[81],"key":[82],"innovations:":[83],"1)":[84],"Multi-modal":[85,112],"Decompose:":[86],"hierarchical":[88],"decomposition":[89],"scheme":[90],"extracts":[92],"region":[94],"proposals":[95],"via":[96],"SAM,":[97],"expands":[98],"semantics":[100],"into":[101],"fine-grained":[102],"descriptors,":[103],"processes":[105],"features":[107],"contextual":[109],"enrichment;":[110],"2)":[111],"Contrastive":[113],"Fuse:":[114],"fusion":[116],"strategy":[117],"employing":[118],"contrastive":[119],"learning":[120],"maintain":[122],"consistency":[123],"across":[124,163],"while":[130],"enabling":[131],"dynamic":[132],"interactions":[134],"between":[135],"foreground":[136],"background":[138],"features;":[139],"3)":[140],"Dual-path":[141],"Reconstruct:":[142],"an":[143],"adaptive":[144],"integration":[145],"mechanism":[146],"combining":[147],"from":[150,157],"tri-modal":[151],"fused":[152],"tokens":[153],"with":[154],"geometric":[155],"cues":[156],"location":[159],"priors.":[160],"Extensive":[161],"experiments":[162],"under":[169],"both":[170],"synthetic":[171],"real":[173],"settings":[174],"demonstrate":[175],"DFR's":[176],"substantial":[177],"performance":[178],"improvements":[179],"over":[180],"state-of-the-art":[181],"methods.":[182]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-14T00:00:00"}
