{"id":"https://openalex.org/W7131639254","doi":"https://doi.org/10.1109/tcsvt.2026.3668226","title":"SyMFood: Synergistic Multi-Modal Prompting for Fine-Grained Zero-Shot Food Detection","display_name":"SyMFood: Synergistic Multi-Modal Prompting for Fine-Grained Zero-Shot Food Detection","publication_year":2026,"publication_date":"2026-02-26","ids":{"openalex":"https://openalex.org/W7131639254","doi":"https://doi.org/10.1109/tcsvt.2026.3668226"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3668226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3668226","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/A5126933034","display_name":"Xinlong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I182707071","display_name":"Ludong University","ror":"https://ror.org/028h95t32","country_code":"CN","type":"education","lineage":["https://openalex.org/I182707071"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinlong Wang","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Ludong University, Yantai, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0007-9954-0427","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Ludong University, Yantai, Shandong, China","institution_ids":["https://openalex.org/I182707071"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039322394","display_name":"Weiqing Min","orcid":"https://orcid.org/0000-0001-6668-9208"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqing Min","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6668-9208","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007119840","display_name":"Shoulong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I182707071","display_name":"Ludong University","ror":"https://ror.org/028h95t32","country_code":"CN","type":"education","lineage":["https://openalex.org/I182707071"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shoulong Liu","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Ludong University, Yantai, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Ludong University, Yantai, Shandong, China","institution_ids":["https://openalex.org/I182707071"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121308452","display_name":"Guorui Sheng","orcid":null},"institutions":[{"id":"https://openalex.org/I182707071","display_name":"Ludong University","ror":"https://ror.org/028h95t32","country_code":"CN","type":"education","lineage":["https://openalex.org/I182707071"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guorui Sheng","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Ludong University, Yantai, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0001-6790-0239","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Ludong University, Yantai, Shandong, China","institution_ids":["https://openalex.org/I182707071"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126946217","display_name":"Shuqiang Jiang","orcid":null},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqiang Jiang","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1596-4326","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16990486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"7","first_page":"9561","last_page":"9574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.423799991607666,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.423799991607666,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T11393","display_name":"Biosensors and Analytical Detection","score":0.05640000104904175,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10036","display_name":"Advanced Neural Network Applications","score":0.04500000178813934,"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":0.6660000085830688},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5916000008583069},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.505299985408783},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4668000042438507},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4562999904155731},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3912999927997589}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102999925613403},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6660000085830688},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5916000008583069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5304999947547913},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.505299985408783},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3912999927997589},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.337799996137619},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26089999079704285},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3668226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3668226","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":[{"id":"https://metadata.un.org/sdg/2","score":0.777547299861908,"display_name":"Zero hunger"}],"awards":[{"id":"https://openalex.org/G1251363176","display_name":null,"funder_award_id":"62125207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G594686096","display_name":null,"funder_award_id":"62472411","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6272792294","display_name":null,"funder_award_id":"JQ24021","funder_id":"https://openalex.org/F4320334977","funder_display_name":"Beijing Municipal Natural Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334977","display_name":"Beijing Municipal Natural Science Foundation","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-grained":[0],"object":[1],"detection":[2],"in":[3,208,215],"food":[4,14,59],"computing":[5],"is":[6],"severely":[7],"constrained":[8],"by":[9,33],"the":[10,17,69,103,131,166,212,216],"vast":[11],"diversity":[12],"of":[13,20],"items":[15],"and":[16,61,75,170,188],"high":[18],"cost":[19],"data":[21],"annotation.":[22],"Existing":[23],"Zero-Shot":[24],"Food":[25,89,156],"Detection":[26],"(ZSFD)":[27],"methods":[28],"attempt":[29],"to":[30,55,68,96,124,148],"solve":[31],"this":[32,80],"leveraging":[34],"semantic":[35,127],"information,":[36],"but":[37],"they":[38],"suffer":[39],"from":[40,115],"two":[41],"critical":[42],"bottlenecks:":[43],"(1)":[44],"a":[45,91,107,135,142,154,204],"\"Semantic":[46],"Dilemma\"":[47],"(SD)":[48],"where":[49],"textual":[50],"descriptions":[51,114],"are":[52],"too":[53],"ambiguous":[54],"distinguish":[56],"visually":[57],"similar":[58],"categories,":[60],"(2)":[62],"an":[63],"\"Architectural":[64],"Bottleneck\"":[65],"(AB)":[66],"due":[67],"granularity":[70],"mismatch":[71],"between":[72,165],"high-level":[73],"semantics":[74],"low-level":[76],"visual":[77,122,150,168],"features.":[78],"In":[79],"article,":[81],"we":[82],"propose":[83],"SyMFood":[84,105,133],"(Synergistic":[85],"Multi-modal":[86],"Framework":[87],"for":[88],"Generalization),":[90],"novel":[92],"ZSFD":[93],"framework":[94],"designed":[95],"systematically":[97],"overcome":[98],"these":[99],"challenges.":[100],"To":[101,129],"resolve":[102],"SD,":[104],"employs":[106],"multi-modal":[108,171],"prompt":[109],"system,":[110],"which":[111],"combines":[112],"rich":[113],"Large":[116],"Language":[117],"Models":[118],"(LLMs)":[119],"with":[120],"unambiguous":[121],"exemplars":[123],"provide":[125],"precise":[126],"grounding.":[128],"break":[130],"AB,":[132],"introduces":[134],"\u201cRefine-then-Fuse\u201d":[136],"architecture.":[137],"This":[138],"design":[139],"first":[140],"utilizes":[141],"Context-Aware":[143],"Spatial-Channel":[144],"Refinement":[145],"(CaSC)":[146],"block":[147],"enhance":[149],"features":[151,169],"independently.":[152],"Subsequently,":[153],"Progressive":[155],"Knowledge":[157],"Fusion":[158],"(ProFus)":[159],"module":[160],"performs":[161],"bi-directional,":[162],"iterative":[163],"co-refinement":[164],"enhanced":[167],"prompts":[172],"across":[173,178],"all":[174],"scales.":[175],"Extensive":[176],"experiments":[177],"four":[179],"challenging":[180],"datasets,":[181],"including":[182],"food-specific":[183],"(UEC":[184],"FOOD":[185],"256,":[186],"FOWA)":[187],"general-purpose":[189],"(PASCAL":[190],"VOC,":[191],"MS":[192],"COCO)":[193],"benchmarks,":[194],"validate":[195],"our":[196],"approach.":[197],"The":[198,221],"proposed":[199],"method":[200],"outperforms":[201],"baselines,":[202],"yielding":[203],"notable":[205],"8.5%":[206],"improvement":[207],"Harmonic":[209],"Mean":[210],"on":[211],"FOWA":[213],"dataset":[214],"genearl":[217],"ZSD":[218],"(GZSD)":[219],"setting.":[220],"source":[222],"code":[223],"will":[224],"be":[225],"available":[226],"at":[227],"https://github.com/Niko000202/SymFood0202.":[228]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-02-27T00:00:00"}