{"id":"https://openalex.org/W7164813978","doi":"https://doi.org/10.1145/3805622.3810686","title":"From Noisy Candidates to Reliable Grounding in Weakly-Supervised Referring Expression Comprehension","display_name":"From Noisy Candidates to Reliable Grounding in Weakly-Supervised Referring Expression Comprehension","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164813978","doi":"https://doi.org/10.1145/3805622.3810686"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810686","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810686","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810686","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138652663","display_name":"Yunlong He","orcid":"https://orcid.org/0009-0007-7502-3644"},"institutions":[{"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":"Yunlong He","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0007-7502-3644","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056371961","display_name":"Ziqi Gu","orcid":null},"institutions":[{"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":"Ziqi Gu","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-5938-2621","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378754","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0001-6212-4891"},"institutions":[{"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":"Tong Zhang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-6212-4891","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019391901","display_name":"Pan Gao","orcid":"https://orcid.org/0000-0002-4492-5430"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Cui","raw_affiliation_strings":["Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4492-5430","affiliations":[{"raw_affiliation_string":"Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054364063","display_name":"Chunyan Xu","orcid":"https://orcid.org/0000-0002-0814-4362"},"institutions":[{"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":"Chunyan Xu","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0814-4362","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93451491,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"317","last_page":"326"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5496000051498413,"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":0.5496000051498413,"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":0.33340001106262207,"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":0.028999999165534973,"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/leverage","display_name":"Leverage (statistics)","score":0.5914999842643738},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5442000031471252},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5401999950408936},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.5040000081062317},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.48420000076293945},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.44620001316070557},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42640000581741333},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.39959999918937683},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38690000772476196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6862999796867371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6812999844551086},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5914999842643738},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5442000031471252},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4569999873638153},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.39959999918937683},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38359999656677246},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.33719998598098755},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30410000681877136},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2802000045776367},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810686","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810686","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810686","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810686","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7152211666107178}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2247513039","https://openalex.org/W2558535589","https://openalex.org/W2946086442","https://openalex.org/W2955014993","https://openalex.org/W2962764817","https://openalex.org/W2963037989","https://openalex.org/W2963109634","https://openalex.org/W2963800628","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2981663434","https://openalex.org/W2984121207","https://openalex.org/W2987401211","https://openalex.org/W2987734933","https://openalex.org/W3035097537","https://openalex.org/W3096609285","https://openalex.org/W3117585461","https://openalex.org/W3126391825","https://openalex.org/W3138516171","https://openalex.org/W3174965650","https://openalex.org/W3178418424","https://openalex.org/W4214490042","https://openalex.org/W4249013746","https://openalex.org/W4309181071","https://openalex.org/W4384820618","https://openalex.org/W4386071755","https://openalex.org/W4386076636","https://openalex.org/W4386609057","https://openalex.org/W4390871807","https://openalex.org/W4392543666","https://openalex.org/W4403791264","https://openalex.org/W4409369745","https://openalex.org/W4413145345","https://openalex.org/W4413158413","https://openalex.org/W4415538135","https://openalex.org/W4415707921","https://openalex.org/W4415795571","https://openalex.org/W4415800512"],"related_works":[],"abstract_inverted_index":{"Weakly-Supervised":[0],"Referring":[1],"Expression":[2],"Comprehension":[3],"(WREC)":[4],"aims":[5],"to":[6,99,138,156],"ground":[7],"natural":[8],"language":[9],"expressions":[10],"in":[11,29,48],"image":[12],"regions,":[13],"using":[14],"only":[15],"image-text":[16,90],"pairs":[17],"without":[18],"bounding-box":[19],"annotations.":[20],"However,":[21],"the":[22,51,57,132,150,183],"absence":[23],"of":[24,168],"explicit":[25],"localization":[26,163],"supervision":[27],"results":[28],"noisy":[30,80,120],"training":[31],"signals":[32],"and":[33,109,135,141,178],"unreliable":[34],"candidate":[35,126],"selection.":[36],"We":[37],"observe":[38],"that":[39,77,129,182],"modern":[40],"query-based":[41],"detectors":[42],"exhibit":[43],"a":[44,72,94,124,158,169],"high-recall,":[45],"low-precision":[46],"behavior":[47],"WREC:":[49],"although":[50],"top-ranked":[52],"query":[53],"often":[54],"localizes":[55],"inaccurately,":[56],"ground-truth":[58],"region":[59],"is":[60],"frequently":[61],"recalled":[62],"among":[63],"high-confidence":[64],"candidates.":[65],"Motivated":[66],"by":[67],"this":[68],"observation,":[69],"we":[70,92,122],"propose":[71],"Noisy-to-Reliable":[73],"Grounding":[74],"(NRG)":[75],"framework":[76],"progressively":[78,145],"transforms":[79],"high-recall":[81],"candidates":[82],"into":[83],"reliable":[84],"grounding":[85,147],"supervision.":[86,114],"Given":[87],"an":[88],"paired":[89],"data,":[91],"leverage":[93],"large":[95],"Vision-Language":[96],"Model":[97],"(VLM)":[98],"generate":[100],"confidence-aware":[101,151],"soft":[102],"pseudo":[103,152],"labels,":[104],"which":[105],"provide":[106],"robust":[107],"semantic":[108],"spatial":[110],"guidance":[111],"under":[112],"weak":[113],"To":[115],"disentangle":[116],"true":[117],"positives":[118],"from":[119],"candidates,":[121],"introduce":[123],"contrastive":[125],"mining":[127],"module":[128],"jointly":[130],"exploits":[131],"detector\u2019s":[133],"prediction":[134],"VLM-derived":[136],"cues":[137],"identify":[139],"positive":[140],"hard":[142],"negative":[143],"queries,":[144],"enhancing":[146],"discriminability.":[148],"Furthermore,":[149],"labels":[153],"are":[154],"integrated":[155],"construct":[157],"regression":[159],"objective,":[160],"enabling":[161],"effective":[162],"learning":[164],"through":[165],"low-rank":[166],"adaptation":[167],"pretrained":[170],"open-vocabulary":[171],"detector.":[172],"Extensive":[173],"experiments":[174],"on":[175],"RefCOCO,":[176],"RefCOCO+,":[177],"RefCOCOg":[179],"datasets":[180],"demonstrate":[181],"proposed":[184],"NRG":[185],"consistently":[186],"outperforms":[187],"existing":[188],"WREC":[189],"methods.":[190]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}