{"id":"https://openalex.org/W4313590975","doi":"https://doi.org/10.1145/3579095","title":"VL-NMS: Breaking Proposal Bottlenecks in Two-stage Visual-language Matching","display_name":"VL-NMS: Breaking Proposal Bottlenecks in Two-stage Visual-language Matching","publication_year":2023,"publication_date":"2023-01-04","ids":{"openalex":"https://openalex.org/W4313590975","doi":"https://doi.org/10.1145/3579095"},"language":"en","primary_location":{"id":"doi:10.1145/3579095","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579095","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5040532721","display_name":"Chenchi Zhang","orcid":"https://orcid.org/0000-0002-9034-4506"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenchi Zhang","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0002-9034-4506","affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenbo Ma","orcid":"https://orcid.org/0000-0002-3188-1811"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Ma","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0002-3188-1811","affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101485989","display_name":"Jun Xiao","orcid":"https://orcid.org/0000-0002-6142-9914"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0002-6142-9914","affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7374-8739","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101687931","display_name":"Jian Shao","orcid":"https://orcid.org/0000-0002-7842-7616"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Shao","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0002-7842-7616","affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008666077","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-9017-2508"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueting Zhuang","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0001-9017-2508","affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100336360","display_name":"Long Chen","orcid":"https://orcid.org/0000-0001-6148-9709"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Long Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-6148-9709","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5318,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64425212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"19","issue":"5s","first_page":"1","last_page":"24"},"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":0.9972000122070312,"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":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.891576886177063},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6816768646240234},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5559534430503845},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5397170186042786},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5097012519836426},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48978519439697266},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.472037672996521},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.47012221813201904},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34319597482681274},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32697683572769165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3115497827529907},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13948357105255127},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10084721446037292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.891576886177063},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6816768646240234},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5559534430503845},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5397170186042786},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5097012519836426},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48978519439697266},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.472037672996521},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.47012221813201904},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34319597482681274},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32697683572769165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3115497827529907},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13948357105255127},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10084721446037292},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3579095","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579095","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-125357","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-125357","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3905147744","display_name":null,"funder_award_id":"U19B2043, 61976185","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7235758038","display_name":null,"funder_award_id":"226-2022-00051","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":89,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W1964073652","https://openalex.org/W2102605133","https://openalex.org/W2185175083","https://openalex.org/W2251512949","https://openalex.org/W2302548814","https://openalex.org/W2489434015","https://openalex.org/W2525778437","https://openalex.org/W2550553598","https://openalex.org/W2558535589","https://openalex.org/W2571175805","https://openalex.org/W2606473278","https://openalex.org/W2612624696","https://openalex.org/W2612690371","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2770129969","https://openalex.org/W2792265253","https://openalex.org/W2798556392","https://openalex.org/W2876852810","https://openalex.org/W2886904239","https://openalex.org/W2894964039","https://openalex.org/W2896442399","https://openalex.org/W2896457183","https://openalex.org/W2904910963","https://openalex.org/W2946574595","https://openalex.org/W2952524542","https://openalex.org/W2955014993","https://openalex.org/W2962764817","https://openalex.org/W2962964995","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2963402592","https://openalex.org/W2963445828","https://openalex.org/W2963760481","https://openalex.org/W2963769056","https://openalex.org/W2963783181","https://openalex.org/W2963914122","https://openalex.org/W2964080601","https://openalex.org/W2964121718","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2966715458","https://openalex.org/W2966817867","https://openalex.org/W2973233205","https://openalex.org/W2979727876","https://openalex.org/W2980088508","https://openalex.org/W2981165461","https://openalex.org/W2982419388","https://openalex.org/W2984121207","https://openalex.org/W2984816230","https://openalex.org/W2986755220","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W2989176720","https://openalex.org/W2997762001","https://openalex.org/W3003423830","https://openalex.org/W3003487319","https://openalex.org/W3004019157","https://openalex.org/W3034325957","https://openalex.org/W3034692043","https://openalex.org/W3034772468","https://openalex.org/W3035097537","https://openalex.org/W3035268124","https://openalex.org/W3035454331","https://openalex.org/W3035517717","https://openalex.org/W3035605030","https://openalex.org/W3099166112","https://openalex.org/W3110435696","https://openalex.org/W3159619744","https://openalex.org/W3173364567","https://openalex.org/W3174364033","https://openalex.org/W3187664142","https://openalex.org/W3199858703","https://openalex.org/W3201770677","https://openalex.org/W3204924011","https://openalex.org/W3211772574","https://openalex.org/W3212847756","https://openalex.org/W4214490042","https://openalex.org/W4288043227","https://openalex.org/W4293518249","https://openalex.org/W4297792979","https://openalex.org/W4312351586","https://openalex.org/W4312457137","https://openalex.org/W4313145013","https://openalex.org/W4382236626","https://openalex.org/W4403220085"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2012262991","https://openalex.org/W2373794620","https://openalex.org/W2060629350","https://openalex.org/W2357294589","https://openalex.org/W2386861027","https://openalex.org/W2349302580","https://openalex.org/W2390154576","https://openalex.org/W2916983164","https://openalex.org/W2012531322"],"abstract_inverted_index":{"The":[0],"prevailing":[1],"framework":[2],"for":[3,144],"matching":[4,22,34,106,180,188,199,210],"multimodal":[5,209],"inputs":[6],"is":[7,115,184],"based":[8,61],"on":[9,32,62,207,224],"a":[10,137,142,149,177],"two-stage":[11,28,198],"process:":[12],"(1)":[13],"detecting":[14],"proposals":[15,52,59,71,89,122,162],"with":[16,25,148],"an":[17,45],"object":[18],"detector":[19],"and":[20,135,174,218,227],"(2)":[21],"text":[23,78,93,166],"queries":[24],"proposals.":[26],"Existing":[27],"solutions":[29],"mostly":[30],"focus":[31],"the":[33,49,54,63,70,77,92,98,105,116,124,156,165,169,187,203,231],"step.":[35],"In":[36],"this":[37,84,109],"article,":[38],"we":[39,111],"argue":[40],"that":[41,69,88],"these":[42],"methods":[43],"overlook":[44],"obvious":[46],"mismatch":[47],"between":[48],"roles":[50],"of":[51,171,205,233],"in":[53,76,102,176],"two":[55],"stages:":[56],"they":[57],"generate":[58],"solely":[60],"detection":[64],"confidence":[65],"(i.e.,":[66,80],"query-agnostic),":[67],"hoping":[68],"contain":[72],"all":[73,129],"instances":[74,131],"mentioned":[75,130],"query":[79,94],"query-aware).":[81],"Due":[82],"to":[83,91,119,140,159,164,186],"mismatch,":[85],"chances":[86],"are":[87,95],"relevant":[90],"suppressed":[96],"during":[97],"filtering":[99],"process,":[100],"which":[101,114],"turn":[103],"bounds":[104],"performance.":[107,181],"To":[108],"end,":[110],"propose":[112],"VL-NMS,":[113],"first":[117,125],"method":[118],"yield":[120],"query-aware":[121],"at":[123],"stage.":[126],"VL-NMS":[127,183,206],"regards":[128],"as":[132],"critical":[133,150,172],"objects":[134],"introduces":[136],"lightweight":[138],"module":[139],"predict":[141],"score":[143],"aligning":[145],"each":[146],"proposal":[147],"object.":[151],"These":[152],"scores":[153],"can":[154,191],"guide":[155],"NMS":[157],"operation":[158],"filter":[160],"out":[161],"irrelevant":[163],"query,":[167],"increasing":[168],"recall":[170],"objects,":[173],"resulting":[175],"significantly":[178],"improved":[179],"Since":[182],"agnostic":[185],"step,":[189],"it":[190],"be":[192],"easily":[193],"integrated":[194],"into":[195],"any":[196],"state-of-the-art":[197],"method.":[200],"We":[201],"validate":[202],"effectiveness":[204],"three":[208],"tasks,":[211],"namely":[212],"referring":[213],"expression":[214],"grounding,":[215,217],"phrase":[216],"image-text":[219],"matching.":[220],"Extensive":[221],"ablation":[222],"studies":[223],"several":[225],"baselines":[226],"benchmarks":[228],"consistently":[229],"demonstrate":[230],"superiority":[232],"VL-NMS.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}