{"id":"https://openalex.org/W4415708345","doi":"https://doi.org/10.1109/icme59968.2025.11209932","title":"CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detection","display_name":"CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detection","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708345","doi":"https://doi.org/10.1109/icme59968.2025.11209932"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5030385109","display_name":"Mingyi Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingyi Guo","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373458","display_name":"Yuyang Liu","orcid":"https://orcid.org/0000-0002-3697-6561"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyang Liu","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101582861","display_name":"Zhiyuan Yan","orcid":"https://orcid.org/0000-0003-2286-2771"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Yan","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001960948","display_name":"Zongying Lin","orcid":"https://orcid.org/0009-0005-6707-173X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongying Lin","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070755370","display_name":"Peixi Peng","orcid":"https://orcid.org/0000-0002-7427-8764"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peixi Peng","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100813706","display_name":"Yonghong Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Tian","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5030385109"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31057982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7445999979972839,"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":0.7445999979972839,"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":0.1745000034570694,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.05119999870657921,"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/object","display_name":"Object (grammar)","score":0.6128000020980835},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5623999834060669},{"id":"https://openalex.org/keywords/incremental-learning","display_name":"Incremental learning","score":0.5498999953269958},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4749000072479248},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.41920000314712524},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.4187000095844269},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3483999967575073},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.34630000591278076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570000290870667},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6128000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118999719619751},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5623999834060669},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.5498999953269958},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4702000021934509},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41449999809265137},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C149490388","wikidata":"https://www.wikidata.org/wiki/Q1718507","display_name":"Sequential Pattern Mining","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2473930607","https://openalex.org/W2560647685","https://openalex.org/W2962966271","https://openalex.org/W2964189064","https://openalex.org/W3034435444","https://openalex.org/W3195577467","https://openalex.org/W4226029051","https://openalex.org/W4312310776","https://openalex.org/W4313026212","https://openalex.org/W4386076281","https://openalex.org/W4390871664","https://openalex.org/W4390872020","https://openalex.org/W4390874134","https://openalex.org/W4402727372","https://openalex.org/W4402754307","https://openalex.org/W4402917172","https://openalex.org/W4413156836"],"related_works":[],"abstract_inverted_index":{"Incremental":[0],"object":[1],"detection":[2],"is":[3,16],"fundamentally":[4],"challenged":[5],"by":[6],"catastrophic":[7],"forgetting.":[8],"A":[9],"major":[10],"factor":[11],"contributing":[12],"to":[13,53,66],"this":[14],"issue":[15],"background":[17,20],"shift,":[18],"where":[19],"categories":[21],"in":[22,86],"sequential":[23],"tasks":[24],"may":[25],"overlap":[26],"with":[27],"either":[28],"previously":[29],"learned":[30],"or":[31],"future":[32],"unseen":[33],"classes.":[34,60],"To":[35],"address":[36],"this,":[37],"we":[38],"propose":[39],"a":[40],"novel":[41],"method":[42],"called":[43],"Class-Agnostic":[44],"Shared":[45],"Attribute":[46],"Base":[47],"(CASA)":[48],"that":[49],"encourages":[50],"the":[51,72,78,93,104,116,120],"model":[52],"learn":[54],"category-agnostic":[55],"attributes":[56,95,100],"shared":[57],"across":[58],"incremental":[59],"Our":[61],"approach":[62],"leverages":[63],"an":[64,87],"LLM":[65],"generate":[67],"candidate":[68],"textual":[69],"attributes,":[70],"selects":[71],"most":[73],"relevant":[74],"ones":[75],"based":[76],"on":[77,115],"current":[79],"training":[80],"data,":[81],"and":[82,98,111],"records":[83],"their":[84],"importance":[85],"assignment":[88],"matrix.":[89],"For":[90],"subsequent":[91],"tasks,":[92],"retained":[94],"are":[96,101],"frozen,":[97],"new":[99],"selected":[102],"from":[103],"remaining":[105],"candidates,":[106],"ensuring":[107],"both":[108],"knowledge":[109],"retention":[110],"adaptability.":[112],"Extensive":[113],"experiments":[114],"COCO":[117],"dataset":[118],"demonstrate":[119],"state-of-the-art":[121],"performance":[122],"of":[123],"our":[124],"method.":[125]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}