{"id":"https://openalex.org/W4408355217","doi":"https://doi.org/10.1109/icassp49660.2025.10889759","title":"Anchor-Prompt-based Segmentation and Embedding Model","display_name":"Anchor-Prompt-based Segmentation and Embedding Model","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355217","doi":"https://doi.org/10.1109/icassp49660.2025.10889759"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101518994","display_name":"Shuman Li","orcid":"https://orcid.org/0000-0002-4248-7836"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuman Li","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088132719","display_name":"Zhipeng Lin","orcid":"https://orcid.org/0000-0001-5941-2163"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Lin","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072541670","display_name":"Haotian Wang","orcid":"https://orcid.org/0000-0003-2928-5575"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotian Wang","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108571731","display_name":"Wenjing Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjing Yang","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103069404","display_name":"Hengzhu Liu","orcid":"https://orcid.org/0000-0002-8797-4144"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengzhu Liu","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.04270000010728836,"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/T10057","display_name":"Face and Expression Recognition","score":0.04270000010728836,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.016499999910593033,"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/T10320","display_name":"Neural Networks and Applications","score":0.01549999974668026,"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/computer-science","display_name":"Computer science","score":0.6606050729751587},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5928397178649902},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5581962466239929},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47195425629615784},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4218136966228485},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42151159048080444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6606050729751587},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5928397178649902},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5581962466239929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47195425629615784},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4218136966228485},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42151159048080444}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2144506857","https://openalex.org/W2222512263","https://openalex.org/W2953920664","https://openalex.org/W2982723417","https://openalex.org/W3033114334","https://openalex.org/W3084173793","https://openalex.org/W3106651317","https://openalex.org/W3118493742","https://openalex.org/W3167949052","https://openalex.org/W3203676240","https://openalex.org/W4294982734","https://openalex.org/W4297239485","https://openalex.org/W4311545237","https://openalex.org/W4312396403","https://openalex.org/W4372267871","https://openalex.org/W4372341157","https://openalex.org/W4385988898","https://openalex.org/W4390874575","https://openalex.org/W4390874670","https://openalex.org/W4403906568","https://openalex.org/W4404612908","https://openalex.org/W4409261941","https://openalex.org/W6784930956","https://openalex.org/W6846581650","https://openalex.org/W6852276098","https://openalex.org/W6852629184"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Tackling":[0],"multi-object":[1],"tracking":[2],"and":[3,17,65,76,98,178],"segmentation":[4,177],"(MOTS)":[5],"can":[6],"be":[7],"attributed":[8],"to":[9,94,114],"a":[10,134,149],"multi-task":[11],"learning":[12,117],"task,":[13],"i.e.,":[14],"performing":[15],"Segmentation":[16,64],"Identity":[18],"Embedding":[19,66],"jointly":[20],"(SIEJ).":[21],"Unfortunately,":[22],"achieving":[23],"optimal":[24,70],"SIEJ":[25,71],"is":[26,112],"non-trivial,":[27],"as":[28],"it":[29],"relies":[30],"on":[31,155],"different":[32],"spatiotemporal":[33],"features":[34],"of":[35,40,46,151,161],"objects.":[36],"Besides,":[37],"the":[38,44,48,55,82,91,100,105,125,141,145,159,162],"lack":[39],"labeled":[41],"data":[42],"raises":[43],"difficulty":[45],"balancing":[47],"two":[49],"objectives":[50],"in":[51,128],"SIEJ.":[52],"Empowered":[53],"by":[54,72,121],"Segment":[56],"Anything":[57],"Model":[58,67],"(SAM),":[59],"we":[60],"propose":[61],"an":[62,78],"Anchor-Prompt-based":[63],"(APSEM)":[68],"towards":[69],"introducing":[73],"redundant":[74,88,119,129],"anchors":[75,89,120],"designing":[77],"embedding":[79,110,142,180],"decoder.":[80],"On":[81,104],"one":[83],"hand,":[84,107],"our":[85,108],"APSEM":[86,164],"allows":[87],"for":[90,118,166],"same":[92,126],"object":[93],"identify":[95],"occluded":[96],"objects":[97],"refine":[99],"pixel-wise":[101],"edge":[102],"mask.":[103],"other":[106],"proposed":[109,163],"decoder":[111],"designed":[113],"address":[115],"identity":[116,179],"minimizing":[122],"differences":[123],"between":[124],"identities":[127],"prompts.":[130],"We":[131],"also":[132,171],"create":[133],"parameter-efficient":[135],"fine-tuning":[136],"strategy,":[137],"which":[138],"helps":[139],"combine":[140],"module":[143,175],"into":[144],"foundation":[146],"model":[147],"through":[148,182],"bit":[150],"data.":[152],"Experimental":[153],"results":[154,170],"MOTSChallenge":[156],"datasets":[157],"validate":[158],"effectiveness":[160],"method":[165],"MOTS":[167],"tasks.":[168],"Such":[169],"demonstrate":[172],"that":[173],"each":[174],"improves":[176],"performance":[181],"joint":[183],"training.":[184]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}