{"id":"https://openalex.org/W4415537998","doi":"https://doi.org/10.1145/3746027.3755316","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","display_name":"Open-Set Image Tagging with Multi-Grained Text Supervision","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537998","doi":"https://doi.org/10.1145/3746027.3755316"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755316","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":null,"display_name":"Xinyu Huang","orcid":"https://orcid.org/0009-0001-0223-2732"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Huang","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-0223-2732","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039784470","display_name":"Yijie Huang","orcid":"https://orcid.org/0000-0002-8320-9277"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Jie Huang","raw_affiliation_strings":["OPPO Research Institute, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8320-9277","affiliations":[{"raw_affiliation_string":"OPPO Research Institute, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017142743","display_name":"Youcai Zhang","orcid":"https://orcid.org/0000-0003-1412-2677"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youcai Zhang","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","OPPO Research Institute, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1412-2677","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"OPPO Research Institute, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110964104","display_name":"Weiwei Tian","orcid":"https://orcid.org/0000-0002-3725-8457"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Tian","raw_affiliation_strings":["College of Biomedical Engineering, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3725-8457","affiliations":[{"raw_affiliation_string":"College of Biomedical Engineering, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100680617","display_name":"Rui Feng","orcid":"https://orcid.org/0000-0002-4747-0574"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rui Feng","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4747-0574","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070073283","display_name":"Yuejie Zhang","orcid":"https://orcid.org/0000-0001-7993-7223"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuejie Zhang","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","OPPO Research Institute, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7993-7223","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"OPPO Research Institute, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101259621","display_name":"Yanchun Xie","orcid":"https://orcid.org/0000-0002-1410-7082"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanchun Xie","raw_affiliation_strings":["OPPO Research Institute, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1410-7082","affiliations":[{"raw_affiliation_string":"OPPO Research Institute, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077242187","display_name":"Yaqian Li","orcid":"https://orcid.org/0009-0001-6137-0174"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaqian Li","raw_affiliation_strings":["OPPO Research Institute, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-6137-0174","affiliations":[{"raw_affiliation_string":"OPPO Research Institute, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433824","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0001-6926-0538"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["International Digital Economy Academy (IDEA), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-6926-0538","affiliations":[{"raw_affiliation_string":"International Digital Economy Academy (IDEA), Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4117","last_page":"4126"},"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":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9969000220298767,"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/generalization","display_name":"Generalization","score":0.5812000036239624},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5343000292778015},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5238000154495239},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4726000130176544},{"id":"https://openalex.org/keywords/expansive","display_name":"Expansive","score":0.4383000135421753},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.40149998664855957},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2791000008583069}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234999775886536},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5812000036239624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.548799991607666},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5343000292778015},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5238000154495239},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C2780502288","wikidata":"https://www.wikidata.org/wiki/Q28838156","display_name":"Expansive","level":3,"score":0.4383000135421753},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3935999870300293},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37130001187324524},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3646000027656555},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2599000036716461}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755316","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":15,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2007972815","https://openalex.org/W2108598243","https://openalex.org/W2398118205","https://openalex.org/W2886641317","https://openalex.org/W3090449556","https://openalex.org/W3138516171","https://openalex.org/W3168547821","https://openalex.org/W3173909648","https://openalex.org/W3176641147","https://openalex.org/W3198377975","https://openalex.org/W4214673031","https://openalex.org/W4288083516","https://openalex.org/W4312310776"],"related_works":[],"abstract_inverted_index":{"This":[0,59],"paper":[1],"introduces":[2],"the":[3,100,183],"Recognize":[4],"Anything":[5],"Plus":[6],"Model":[7],"(RAM++),":[8],"an":[9],"open-set":[10,77,103,120,149],"image":[11,111,121],"tagging":[12,122],"model":[13],"effectively":[14],"leveraging":[15],"multi-grained":[16],"text":[17,26,51],"supervision.":[18],"Previous":[19],"approaches":[20],"(e.g.,":[21],"CLIP)":[22],"primarily":[23],"utilize":[24],"global":[25,50],"supervision":[27,48,91],"paired":[28],"with":[29,49],"images,":[30],"leading":[31],"to":[32,86],"sub-optimal":[33],"performance":[34],"in":[35],"recognizing":[36],"multiple":[37],"individual":[38,46],"semantic":[39],"tags.":[40],"In":[41],"contrast,":[42],"RAM++":[43,80,115,134,153,174],"seamlessly":[44],"integrates":[45],"tag":[47,68,90,95,132],"supervision,":[52,97],"all":[53],"within":[54],"a":[55],"unified":[56],"alignment":[57],"framework.":[58],"integration":[60],"not":[61],"only":[62],"ensures":[63],"efficient":[64],"recognition":[65,112],"of":[66,102,156],"predefined":[67,129],"categories,":[69,133],"but":[70],"also":[71],"enhances":[72],"generalization":[73],"capabilities":[74],"for":[75,128],"diverse":[76,170],"categories.":[78],"Furthermore,":[79],"employs":[81],"large":[82],"language":[83],"models":[84,123],"(LLMs)":[85],"convert":[87],"semantically":[88],"constrained":[89],"into":[92],"more":[93],"expansive":[94],"description":[96,105],"thereby":[98],"enriching":[99],"scope":[101],"visual":[104],"concepts.":[106],"Comprehensive":[107],"evaluations":[108],"on":[109,124,144,167,182],"various":[110],"benchmarks":[113],"demonstrate":[114],"exceeds":[116],"existing":[117],"state-of-the-art":[118],"(SOTA)":[119],"most":[125],"aspects.":[126],"Specifically,":[127],"commonly":[130],"used":[131],"showcases":[135],"10.2":[136],"mAP":[137,140,158,161,177,180],"and":[138,146,159,164,178],"15.4":[139],"enhancements":[141],"over":[142,162],"CLIP":[143,163],"OpenImages":[145],"ImageNet.":[147],"For":[148,169],"categories":[150],"beyond":[151],"predefined,":[152],"records":[154],"improvements":[155,181],"5.0":[157],"6.4":[160],"RAM":[165],"respectively":[166],"OpenImages.":[168],"human-object":[171],"interaction":[172],"phrases,":[173],"achieves":[175],"7.8":[176],"4.7":[179],"HICO":[184],"benchmark.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}