{"id":"https://openalex.org/W4404609393","doi":"https://doi.org/10.1109/tpami.2024.3504568","title":"Fine-Grained Visual Text Prompting","display_name":"Fine-Grained Visual Text Prompting","publication_year":2024,"publication_date":"2024-11-21","ids":{"openalex":"https://openalex.org/W4404609393","doi":"https://doi.org/10.1109/tpami.2024.3504568","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030287"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3504568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3504568","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100604251","display_name":"Lingfeng Yang","orcid":"https://orcid.org/0000-0002-2725-8947"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]},{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingfeng Yang","raw_affiliation_strings":["PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2725-8947","affiliations":[{"raw_affiliation_string":"PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125","https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693026","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-4996-7365"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["NKIARI, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4996-7365","affiliations":[{"raw_affiliation_string":"NKIARI, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038675825","display_name":"Yueze Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueze Wang","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence (BAAI), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence (BAAI), Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073515474","display_name":"Xinlong Wang","orcid":"https://orcid.org/0000-0002-6974-7976"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinlong Wang","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence (BAAI), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6974-7976","affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence (BAAI), Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100726984","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-4800-832X"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]},{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4800-832X","affiliations":[{"raw_affiliation_string":"PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125","https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6568,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.91377984,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"47","issue":"3","first_page":"1594","last_page":"1609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9988999962806702,"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":0.6753849983215332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6079009771347046},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5235506892204285},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.44189196825027466},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40165114402770996},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3318389058113098},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3261500597000122}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6753849983215332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6079009771347046},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5235506892204285},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.44189196825027466},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40165114402770996},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3318389058113098},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3261500597000122}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3504568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3504568","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40030287","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030287","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8035023450","display_name":null,"funder_award_id":"070-63233084","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"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":118,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W1797268635","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W2102605133","https://openalex.org/W2104408738","https://openalex.org/W2138554385","https://openalex.org/W2216125271","https://openalex.org/W2222512263","https://openalex.org/W2489434015","https://openalex.org/W2560023338","https://openalex.org/W2598915960","https://openalex.org/W2886799640","https://openalex.org/W2948210185","https://openalex.org/W2962764817","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2963948108","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2987401211","https://openalex.org/W2987734933","https://openalex.org/W2999219213","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3096609285","https://openalex.org/W3098267758","https://openalex.org/W3110435696","https://openalex.org/W3113410735","https://openalex.org/W3120485916","https://openalex.org/W3126391825","https://openalex.org/W3143107425","https://openalex.org/W3159619744","https://openalex.org/W3173220247","https://openalex.org/W3190434222","https://openalex.org/W3198377975","https://openalex.org/W3199245537","https://openalex.org/W3204250462","https://openalex.org/W3204715535","https://openalex.org/W4205172069","https://openalex.org/W4214490042","https://openalex.org/W4224035735","https://openalex.org/W4224308101","https://openalex.org/W4225517085","https://openalex.org/W4254415482","https://openalex.org/W4281838252","https://openalex.org/W4284961860","https://openalex.org/W4285192809","https://openalex.org/W4288089799","https://openalex.org/W4310486995","https://openalex.org/W4310557340","https://openalex.org/W4312310776","https://openalex.org/W4312629998","https://openalex.org/W4312651322","https://openalex.org/W4312773012","https://openalex.org/W4312872987","https://openalex.org/W4313145515","https://openalex.org/W4322718191","https://openalex.org/W4361194507","https://openalex.org/W4382490555","https://openalex.org/W4386065512","https://openalex.org/W4386065815","https://openalex.org/W4386071509","https://openalex.org/W4386075561","https://openalex.org/W4386076084","https://openalex.org/W4386076148","https://openalex.org/W4386076215","https://openalex.org/W4386076522","https://openalex.org/W4390873481","https://openalex.org/W4390873795","https://openalex.org/W4390874575","https://openalex.org/W4402716383","https://openalex.org/W4402753466","https://openalex.org/W4402754004","https://openalex.org/W4404612908","https://openalex.org/W6602324145","https://openalex.org/W6620707391","https://openalex.org/W6638319203","https://openalex.org/W6705319163","https://openalex.org/W6723035356","https://openalex.org/W6735463952","https://openalex.org/W6753838793","https://openalex.org/W6769627184","https://openalex.org/W6772372853","https://openalex.org/W6775970589","https://openalex.org/W6778485988","https://openalex.org/W6778883912","https://openalex.org/W6781547866","https://openalex.org/W6789753369","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6798837711","https://openalex.org/W6799465499","https://openalex.org/W6801512601","https://openalex.org/W6802347785","https://openalex.org/W6802517928","https://openalex.org/W6809885388","https://openalex.org/W6810081322","https://openalex.org/W6810334672","https://openalex.org/W6810601475","https://openalex.org/W6810837128","https://openalex.org/W6810876946","https://openalex.org/W6811013733","https://openalex.org/W6811070434","https://openalex.org/W6838865580","https://openalex.org/W6840582082","https://openalex.org/W6845373907","https://openalex.org/W6847003901","https://openalex.org/W6847386724","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6850787431","https://openalex.org/W6850991314","https://openalex.org/W6852107595","https://openalex.org/W6853242345","https://openalex.org/W6854222408","https://openalex.org/W6872446165"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2383687187","https://openalex.org/W2081517010","https://openalex.org/W2121496884","https://openalex.org/W2387910809","https://openalex.org/W2294221496"],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs),":[2],"such":[3],"as":[4],"CLIP,":[5],"excel":[6],"in":[7,110],"zero-shot":[8,72,159],"image-level":[9],"visual":[10,52,100,106],"understanding":[11],"but":[12],"struggle":[13],"with":[14,57],"object-based":[15,75],"tasks":[16,76],"requiring":[17],"precise":[18,78],"localization":[19],"and":[20,41,54,81,91,112,127],"recognition.":[21],"Visual":[22,66,88],"prompts,":[23],"like":[24,121],"colorful":[25],"boxes":[26],"or":[27],"circles,":[28],"are":[29],"suggested":[30],"to":[31,45,134],"enhance":[32],"local":[33],"perception.":[34],"However,":[35],"these":[36],"methods":[37,169],"often":[38],"include":[39],"irrelevant":[40],"noisy":[42],"pixels,":[43],"leading":[44],"suboptimal":[46],"performance.":[47],"The":[48],"design":[49],"of":[50,186],"better":[51],"prompts":[53],"their":[55],"collaboration":[56],"text":[58],"prompting":[59,101,147],"remains":[60],"underexplored.":[61],"This":[62],"paper":[63],"introduces":[64],"Fine-Grained":[65,87],"Text":[67,93],"Prompting":[68,89,94],"(FGVTP),":[69],"a":[70,119,154],"new":[71],"framework":[73],"for":[74],"using":[77],"semantic":[79,116],"masks":[80,117],"reinforced":[82],"image-text":[83,144],"alignment.":[84],"FGVTP":[85,156,187],"comprises":[86],"(FGVP)":[90],"Consistency-Enhanced":[92],"(CETP).":[95],"Specifically,":[96],"we":[97],"carefully":[98],"study":[99],"designs":[102],"by":[103,146,170],"exploring":[104],"more":[105],"markings":[107],"that":[108],"vary":[109],"shape":[111],"form.":[113],"FGVP":[114],"uses":[115],"from":[118],"segmenter":[120],"the":[122,179,184],"Segment":[123],"Anything":[124],"Model":[125],"(SAM)":[126],"employs":[128],"background":[129],"blurring":[130],"(Blur":[131],"Reverse":[132],"Mask)":[133],"highlight":[135],"targets":[136],"while":[137],"maintaining":[138],"spatial":[139],"coherence.":[140],"Further,":[141],"CETP":[142],"enhances":[143],"alignment":[145],"captions":[148],"based":[149],"on":[150,163,172,178],"FGVP-processed":[151],"images.":[152],"As":[153],"result,":[155],"achieves":[157],"superior":[158],"referring":[160],"expression":[161],"comprehension":[162],"RefCOCO/+/g":[164],"benchmarks,":[165],"outperforming":[166],"previous":[167],"SOTA":[168],"5.8%":[171],"average.":[173],"Part":[174],"detection":[175],"experiments":[176],"conducted":[177],"PACO":[180],"dataset":[181],"further":[182],"validate":[183],"preponderance":[185],"over":[188],"existing":[189],"works.":[190],"Code":[191],"is":[192],"available":[193],"at":[194],"https://github.com/ylingfeng/FGVP.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}