{"id":"https://openalex.org/W4392904152","doi":"https://doi.org/10.1109/icassp48485.2024.10447589","title":"Exploration of Visual Prompt in Grounded Pre-Trained Open-Set Detection","display_name":"Exploration of Visual Prompt in Grounded Pre-Trained Open-Set Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904152","doi":"https://doi.org/10.1109/icassp48485.2024.10447589"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447589","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5102963871","display_name":"Qibo Chen","orcid":"https://orcid.org/0009-0000-7712-3402"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qibo Chen","raw_affiliation_strings":["China Mobile(Zhejiang) Research & Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile(Zhejiang) Research & Innovation Institute","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101623674","display_name":"Weizhong Jin","orcid":"https://orcid.org/0000-0001-9335-2336"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhong Jin","raw_affiliation_strings":["China Mobile(Zhejiang) Research & Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile(Zhejiang) Research & Innovation Institute","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102979713","display_name":"Shuchang Li","orcid":"https://orcid.org/0009-0007-1014-1914"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuchang Li","raw_affiliation_strings":["China Mobile(Zhejiang) Research & Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile(Zhejiang) Research & Innovation Institute","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006444815","display_name":"Mengdi Liu","orcid":"https://orcid.org/0000-0002-3457-0197"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengdi Liu","raw_affiliation_strings":["China Mobile(Zhejiang) Research & Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile(Zhejiang) Research & Innovation Institute","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053169627","display_name":"Li Yu","orcid":"https://orcid.org/0009-0006-2152-0234"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Yu","raw_affiliation_strings":["China Mobile(Zhejiang) Research & Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile(Zhejiang) Research & Innovation Institute","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110290929","display_name":"Jian Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Jiang","raw_affiliation_strings":["China Mobile(Zhejiang) Research & Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile(Zhejiang) Research & Innovation Institute","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012421792","display_name":"Xiaozheng Wang","orcid":"https://orcid.org/0000-0002-4827-6992"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaozheng Wang","raw_affiliation_strings":["China Mobile(Zhejiang) Research & Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile(Zhejiang) Research & Innovation Institute","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180662265"],"apc_list":null,"apc_paid":null,"fwci":0.2629,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46337724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6115","last_page":"6119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9948999881744385,"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/computer-science","display_name":"Computer science","score":0.8187160491943359},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7630766034126282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7002366185188293},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6356746554374695},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6250826120376587},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6242519021034241},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6003629565238953},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5554050803184509},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5085943937301636},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.45677298307418823},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4490700960159302},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.4189227819442749},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4162607789039612},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4098619222640991},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2952001690864563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187160491943359},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7630766034126282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7002366185188293},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6356746554374695},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6250826120376587},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6242519021034241},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6003629565238953},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5554050803184509},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5085943937301636},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45677298307418823},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4490700960159302},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4189227819442749},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4162607789039612},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4098619222640991},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2952001690864563},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447589","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1773149199","https://openalex.org/W2144506857","https://openalex.org/W2547875792","https://openalex.org/W2896457183","https://openalex.org/W2962766617","https://openalex.org/W2963037989","https://openalex.org/W2983943451","https://openalex.org/W3096609285","https://openalex.org/W3122239467","https://openalex.org/W3159619744","https://openalex.org/W3174770825","https://openalex.org/W3198377975","https://openalex.org/W3206072662","https://openalex.org/W4224246420","https://openalex.org/W4287113019","https://openalex.org/W4288083516","https://openalex.org/W4288089799","https://openalex.org/W4295884768","https://openalex.org/W4296605949","https://openalex.org/W4312559104","https://openalex.org/W4312956471","https://openalex.org/W4390873343","https://openalex.org/W4404612908","https://openalex.org/W6620707391","https://openalex.org/W6769627184","https://openalex.org/W6789909235","https://openalex.org/W6791353385","https://openalex.org/W6797716411","https://openalex.org/W6810039040","https://openalex.org/W6842874653"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2965546495","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W4311804456","https://openalex.org/W151699219","https://openalex.org/W2085633464","https://openalex.org/W1966122760"],"abstract_inverted_index":{"Text":[0],"prompts":[1,19,80,129],"are":[2,20],"crucial":[3],"for":[4,17],"generalizing":[5,28],"pre-trained":[6,70],"open-set":[7],"object":[8],"detection":[9,44,71],"models":[10],"to":[11,29,36,42,73,81,105,121],"new":[12,30,59,75,83],"categories.":[13,110],"However,":[14],"current":[15],"methods":[16,149],"text":[18],"limited":[21,96],"as":[22],"they":[23],"require":[24],"manual":[25],"feedback":[26],"when":[27,108],"categories,":[31],"which":[32,67,126],"restricts":[33],"their":[34],"ability":[35],"model":[37,72],"complex":[38],"scenes,":[39],"often":[40],"leading":[41],"incorrect":[43],"results.":[45],"To":[46,77],"address":[47],"this":[48],"limitation,":[49],"we":[50,86],"propose":[51,87],"a":[52,63,88],"novel":[53],"visual":[54,79,128],"prompt":[55,90,147],"method":[56,135],"that":[57,93,143],"learns":[58],"category":[60,115],"knowledge":[61],"from":[62],"few":[64],"labeled":[65],"images,":[66],"generalizes":[68],"the":[69,74,114,118,134,137],"category.":[76],"allow":[78],"represent":[82],"categories":[84],"adequately,":[85],"statistical-based":[89],"construction":[91],"module":[92],"is":[94],"not":[95],"by":[97],"predefined":[98],"vocabulary":[99],"lengths,":[100],"thus":[101],"allowing":[102],"more":[103,130,152],"vectors":[104],"be":[106],"used":[107],"representing":[109],"We":[111,132],"further":[112],"utilize":[113],"dictionaries":[116],"in":[117,154],"pre-training":[119],"dataset":[120,140],"design":[122],"task-specific":[123],"similarity":[124],"dictionaries,":[125],"make":[127],"discriminative.":[131],"evaluate":[133],"on":[136],"ODinW":[138],"[1]":[139],"and":[141,150],"show":[142],"it":[144],"outperforms":[145],"existing":[146],"learning":[148],"performs":[151],"consistently":[153],"combinatorial":[155],"inference.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}