{"id":"https://openalex.org/W7094950095","doi":"https://doi.org/10.1145/3746027.3754501","title":"SAM based Region-Word Clustering and Inference Score Adjusting for Open-Vocabulary Object Detection","display_name":"SAM based Region-Word Clustering and Inference Score Adjusting for Open-Vocabulary Object Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W7094950095","doi":"https://doi.org/10.1145/3746027.3754501"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754501","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":"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":null,"display_name":"Qiuyu Liang","orcid":"https://orcid.org/0009-0004-3261-7256"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiuyu Liang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yongqiang Zhang","orcid":"https://orcid.org/0000-0002-0437-7337"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqiang Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.55692101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2596","last_page":"2605"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5077000260353088,"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":0.5077000260353088,"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":0.13940000534057617,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.06689999997615814,"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/inference","display_name":"Inference","score":0.736299991607666},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.679099977016449},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6276000142097473},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6273000240325928},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5623000264167786},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5425999760627747}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.736299991607666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6886000037193298},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.679099977016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6696000099182129},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6276000142097473},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6273000240325928},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5623000264167786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5425999760627747},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.529699981212616},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4609000086784363},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3898000121116638},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27239999175071716}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754501","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":[{"id":"https://metadata.un.org/sdg/4","score":0.7936520576477051,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4168310557","display_name":null,"funder_award_id":"62206077","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2886641317","https://openalex.org/W2948672349","https://openalex.org/W3008128219","https://openalex.org/W3096609285","https://openalex.org/W3138516171","https://openalex.org/W3173859428","https://openalex.org/W3176659256","https://openalex.org/W3202623927","https://openalex.org/W4310557340","https://openalex.org/W4312424618","https://openalex.org/W4312563428","https://openalex.org/W4312574296","https://openalex.org/W4313023122","https://openalex.org/W4320731783","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4393855552","https://openalex.org/W4399490424","https://openalex.org/W4399790320","https://openalex.org/W4402152357"],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"object":[1,128],"detection":[2,129],"aims":[3],"to":[4,27,58,80,199],"detect":[5],"and":[6,32,121,164,183,226],"recognize":[7],"novel":[8,54,69,108,148,165,205,236],"categories":[9,102,206],"that":[10],"are":[11,97],"not":[12],"seen":[13,101],"in":[14,88],"the":[15,22,85,186,215],"training":[16],"set.Most":[17],"existing":[18,233],"methods":[19,47,234],"rely":[20],"on":[21,211,224,230,235],"Region":[23],"Proposal":[24],"Network":[25],"(RPN)":[26],"extract":[28],"regions":[29],"of":[30,84,136,218],"interest":[31],"align":[33],"them":[34,185],"with":[35,103],"textual":[36],"descriptions":[37],"through":[38],"one-to-one":[39],"region-word":[40,119],"alignment,":[41],"such":[42],"as":[43],"bipartite":[44,181],"matching.However,":[45],"these":[46,112],"encounter":[48],"three":[49,137],"major":[50],"challenges:":[51],"1)":[52,139],"Insufficient":[53],"proposals:":[55],"RPN":[56],"tends":[57],"generate":[59],"high-confidence":[60],"proposals":[61,146,160,178],"for":[62,68,74,107,126,147],"base":[63,163],"categories,":[64,149],"but":[65],"low-confidence":[66],"ones":[67],"categories.":[70,109,166,237],"2)":[71,167],"Missing":[72],"matches":[73],"duplicate":[75],"instances:":[76],"Bipartite":[77],"matching":[78,173,182],"struggles":[79],"handle":[81],"multiple":[82],"instances":[83],"same":[86,187],"category":[87],"an":[89,152],"image.":[90],"3)":[91,189],"Inference":[92],"bias:":[93],"During":[94],"inference,":[95],"classifiers":[96],"often":[98],"biased":[99],"toward":[100],"lower":[104],"prediction":[105],"scores":[106],"To":[110,143,170],"address":[111],"challenges,":[113],"we":[114,150,175],"propose":[115],"a":[116,194],"SAM":[117],"based":[118],"clustering":[120],"inference":[122],"score":[123,196],"adjusting":[124],"model":[125],"open-vocabulary":[127],"(coined":[130],"CADet).":[131],"Specifically,":[132],"our":[133,219],"method":[134],"consists":[135],"components:":[138],"Enhanced":[140],"proposal":[141],"generation:":[142],"ensure":[144],"sufficient":[145],"incorporate":[151],"unsupervised":[153],"localization":[154],"SAM,":[155],"which":[156],"generates":[157],"more":[158,172],"comprehensive":[159],"covering":[161],"both":[162],"Region-word":[168],"clustering:":[169],"mine":[171],"samples,":[174],"cluster":[176],"similar":[177],"derived":[179],"from":[180],"assign":[184],"pseudo-labels.":[188],"Score":[190],"adjusting:":[191],"We":[192],"introduce":[193],"similarity-guided":[195],"adjustment":[197],"strategy":[198],"effectively":[200],"mitigate":[201],"classifier":[202],"bias":[203],"against":[204],"during":[207],"inference.":[208],"Extensive":[209],"experiments":[210],"two":[212],"datasets":[213],"demonstrate":[214],"superior":[216],"performance":[217],"approach,":[220],"achieving":[221],"36.4%":[222],"mAP":[223,229],"COCO":[225],"29.6%":[227],"mask":[228],"LVIS,":[231],"outperforming":[232]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}