{"id":"https://openalex.org/W4392904326","doi":"https://doi.org/10.1109/icassp48485.2024.10445738","title":"Visual Prompt Tuning for Weakly Supervised Phrase Grounding","display_name":"Visual Prompt Tuning for Weakly Supervised Phrase Grounding","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904326","doi":"https://doi.org/10.1109/icassp48485.2024.10445738"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445738","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":"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/A5102631475","display_name":"Pengyue Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengyue Lin","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence","School of Artificial Intelligence, Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101490809","display_name":"Zhihan Yu","orcid":"https://orcid.org/0009-0000-6411-9420"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihan Yu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence","School of Artificial Intelligence, Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068753064","display_name":"Mingcong Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingcong Lu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence","School of Artificial Intelligence, Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013283012","display_name":"Fangxiang Feng","orcid":"https://orcid.org/0000-0002-4798-4233"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangxiang Feng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence","School of Artificial Intelligence, Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068728736","display_name":"Ruifan Li","orcid":"https://orcid.org/0000-0002-3543-6272"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruifan Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence","School of Artificial Intelligence, Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351304","display_name":"Xiaojie Wang","orcid":"https://orcid.org/0000-0003-0314-8951"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence","School of Artificial Intelligence, Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102631475"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":1.0399,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75866782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7895","last_page":"7899"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.996999979019165,"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/phrase","display_name":"Phrase","score":0.8176652193069458},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.7381459474563599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7355448007583618},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6933900117874146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.647357702255249},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.645431399345398},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.503602921962738},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4402995705604553},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4379500448703766},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42045271396636963},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4012904465198517},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3791190981864929},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10154962539672852}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.8176652193069458},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.7381459474563599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355448007583618},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6933900117874146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.647357702255249},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.645431399345398},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.503602921962738},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4402995705604553},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4379500448703766},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42045271396636963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4012904465198517},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3791190981864929},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10154962539672852},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445738","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321470","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1931639407","https://openalex.org/W2277195237","https://openalex.org/W2776207810","https://openalex.org/W2963042258","https://openalex.org/W2963080533","https://openalex.org/W2963914122","https://openalex.org/W2966466719","https://openalex.org/W2989176720","https://openalex.org/W3034727271","https://openalex.org/W3117585461","https://openalex.org/W3174770825","https://openalex.org/W3176196997","https://openalex.org/W3179041377","https://openalex.org/W3185341429","https://openalex.org/W4205685122","https://openalex.org/W4214650614","https://openalex.org/W4224807381","https://openalex.org/W4224925089","https://openalex.org/W4285192809","https://openalex.org/W4293518031","https://openalex.org/W4312651322","https://openalex.org/W4312747482","https://openalex.org/W4312960937","https://openalex.org/W4390873481","https://openalex.org/W4402753899","https://openalex.org/W6791353385","https://openalex.org/W6810290167","https://openalex.org/W6838821989","https://openalex.org/W6853242345","https://openalex.org/W6859465070"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2021787609","https://openalex.org/W1537063595","https://openalex.org/W2097328689","https://openalex.org/W4234899305","https://openalex.org/W2012262991","https://openalex.org/W2379604501","https://openalex.org/W2366906938","https://openalex.org/W2373794620","https://openalex.org/W2373854414"],"abstract_inverted_index":{"Previous":[0],"works":[1],"on":[2,13,95],"the":[3,19,34,68,76,85,96,101],"task":[4,98],"of":[5,103],"weakly":[6],"supervised":[7],"phrase":[8,55],"grounding":[9,56,86],"(WSG)":[10],"rely":[11],"heavily":[12],"object":[14],"detectors":[15,35],"providing":[16],"RoIs":[17],"for":[18],"localization.":[20],"However,":[21],"such":[22],"methods":[23,94],"cannot":[24],"be":[25],"applied":[26],"effectively":[27],"to":[28,49],"real-world":[29],"scenarios":[30],"largely":[31],"because":[32],"that":[33],"are":[36],"trained":[37],"with":[38,58,79],"limited":[39],"categories.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,74],"propose":[45],"a":[46,53,59],"refinement-based":[47],"approach":[48],"WSG":[50,97],"through":[51],"fine-tuning":[52],"detector-free":[54],"model":[57],"visual":[60,63,77],"prompt.":[61],"This":[62],"prompt":[64,78],"is":[65],"extracted":[66],"from":[67],"text-related":[69],"representations":[70],"in":[71],"CLIP.":[72],"Furthermore,":[73],"combine":[75],"learnable":[80],"features":[81],"and":[82,99],"then":[83],"fine-tune":[84],"network.":[87],"Our":[88],"experimental":[89],"results":[90],"significantly":[91],"outperform":[92],"state-of-the-art":[93],"shows":[100],"effectiveness":[102],"our":[104],"method.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}