{"id":"https://openalex.org/W4415536819","doi":"https://doi.org/10.1145/3746027.3754967","title":"MM-Prompt: Multi-modality and Multi-granularity Prompts for Few-Shot Segmentation","display_name":"MM-Prompt: Multi-modality and Multi-granularity Prompts for Few-Shot Segmentation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536819","doi":"https://doi.org/10.1145/3746027.3754967"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754967","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754967","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":"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/A5103239470","display_name":"Hang Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Xiong","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-1777-6724","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091558139","display_name":"Runmin Cong","orcid":"https://orcid.org/0000-0003-0972-4008"},"institutions":[{"id":"https://openalex.org/I4210102264","display_name":"Shandong University of Political Science and Law","ror":"https://ror.org/01b2j5886","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210102264"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runmin Cong","raw_affiliation_strings":["Shandong University, Jinan, Shandong, China and Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0003-0972-4008","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, Shandong, China and Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan, Shandong, China","institution_ids":["https://openalex.org/I4210102264"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084535846","display_name":"J.R. Chen","orcid":"https://orcid.org/0000-0002-0469-4463"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jinpeng Chen","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-0469-4463","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020541871","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0002-0492-2489"},"institutions":[{"id":"https://openalex.org/I4210102264","display_name":"Shandong University of Political Science and Law","ror":"https://ror.org/01b2j5886","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210102264"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Shandong University, Jinan, Shandong, China and Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0002-0492-2489","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, Shandong, China and Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan, Shandong, China","institution_ids":["https://openalex.org/I4210102264"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448845","display_name":"Feng Li","orcid":"https://orcid.org/0000-0001-9862-0432"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Li","raw_affiliation_strings":["Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-9862-0432","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030238978","display_name":"Huihui Bai","orcid":"https://orcid.org/0000-0002-3879-8957"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huihui Bai","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3879-8957","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008386708","display_name":"Sam Kwong","orcid":"https://orcid.org/0000-0001-7484-7261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Kwong","raw_affiliation_strings":["Lingnan University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-7484-7261","affiliations":[{"raw_affiliation_string":"Lingnan University, Hong Kong, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"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":0.25531474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3067","last_page":"3075"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/leverage","display_name":"Leverage (statistics)","score":0.7493000030517578},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.713699996471405},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7124999761581421},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6391000151634216},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6226999759674072},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.483599990606308},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.483599990606308},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.41029998660087585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876999974250793},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7493000030517578},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.713699996471405},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7124999761581421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6459000110626221},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6391000151634216},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6226999759674072},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.483599990606308},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.483599990606308},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4406000077724457},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.335999995470047},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32749998569488525},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754967","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754967","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/G347848230","display_name":null,"funder_award_id":"62471278,62302141,62331003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4811629003","display_name":null,"funder_award_id":"tsqn202306079","funder_id":"https://openalex.org/F4320326189","funder_display_name":"Taishan Scholar Project of Shandong Province"},{"id":"https://openalex.org/G5943259286","display_name":null,"funder_award_id":"JZ2024HGTB0255","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326189","display_name":"Taishan Scholar Project of Shandong Province","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":2,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W4391454478"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,105,133,151],"effectiveness":[2],"of":[3,18,37,50,76,104],"Segment":[4],"Anything":[5],"Model":[6],"(SAM)":[7],"based":[8],"methods":[9,26],"in":[10,165,174],"Few-Shot":[11],"Segmentation":[12],"(FSS)":[13],"tasks,":[14,167],"our":[15,120],"closer":[16],"examination":[17],"their":[19],"prompt":[20,63,122],"encoding":[21],"mechanism":[22],"reveals":[23],"that":[24,160],"these":[25,55],"rely":[27],"solely":[28],"on":[29,150],"visual":[30,88,92],"information":[31],"to":[32,67,138],"generate":[33],"a":[34,48],"single":[35],"type":[36],"prompt.":[38],"Consequently,":[39],"they":[40],"suffer":[41],"from":[42],"semantic":[43],"granularity":[44,117],"representation":[45],"bias":[46],"and":[47,73,90,97,112,130,153,172],"loss":[49],"spatial":[51],"information.":[52],"To":[53,141],"address":[54],"limitations,":[56],"this":[57,175],"paper":[58],"introduces":[59],"an":[60],"innovative":[61],"multi-modal":[62,121],"encoder,":[64],"enabling":[65],"SAM":[66],"leverage":[68],"both":[69,109],"annotated":[70],"reference":[71],"images":[72],"textual":[74],"descriptions":[75],"class":[77],"names":[78],"as":[79,139],"segmentation":[80],"prompts.":[81],"This":[82],"approach":[83],"generates":[84],"text":[85],"prompts,":[86,89,93],"dense":[87],"sparse":[91],"spanning":[94],"multiple":[95],"modalities":[96],"granularities.":[98],"These":[99],"prompts":[100],"provide":[101],"enhanced":[102],"representations":[103],"target":[106],"class,":[107],"capturing":[108],"abstract":[110],"semantics":[111],"specific":[113],"details,":[114],"while":[115],"ensuring":[116],"appropriateness.":[118],"When":[119],"encoder":[123,129],"is":[124,136],"integrated":[125],"with":[126],"SAM's":[127],"image":[128],"mask":[131],"decoder,":[132],"overall":[134],"model":[135],"referred":[137],"MM-Prompt.":[140],"validate":[142],"its":[143,169],"effectiveness,":[144],"we":[145],"conducted":[146],"extensive":[147],"empirical":[148],"studies":[149],"PASCAL-5^i":[152],"COCO-20^i":[154],"datasets.":[155],"The":[156],"experimental":[157],"results":[158],"demonstrate":[159],"MM-Prompt":[161],"achieves":[162],"state-of-the-art":[163],"performance":[164],"FSS":[166],"highlighting":[168],"substantial":[170],"potential":[171],"value":[173],"domain.":[176]},"counts_by_year":[],"updated_date":"2026-06-18T10:00:31.954636","created_date":"2025-10-25T00:00:00"}