{"id":"https://openalex.org/W3163747765","doi":"https://doi.org/10.1109/icme52920.2022.9859880","title":"Visual Grounding with Transformers","display_name":"Visual Grounding with Transformers","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W3163747765","doi":"https://doi.org/10.1109/icme52920.2022.9859880","mag":"3163747765"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859880","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"https://openalex.org/A5100783342","display_name":"Ye Du","orcid":"https://orcid.org/0000-0002-3057-1862"},"institutions":[{"id":"https://openalex.org/I4392738276","display_name":"State Key Laboratory of Virtual Reality Technology and Systems","ror":"https://ror.org/0009eea46","country_code":null,"type":"facility","lineage":["https://openalex.org/I4392738276","https://openalex.org/I82880672"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ye Du","raw_affiliation_strings":["Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China","Hangzhou Innovation Institute, Beihang University","State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China","institution_ids":["https://openalex.org/I82880672","https://openalex.org/I4392738276"]},{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039781970","display_name":"Zehua Fu","orcid":"https://orcid.org/0000-0002-3639-4406"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]},{"id":"https://openalex.org/I4392738276","display_name":"State Key Laboratory of Virtual Reality Technology and Systems","ror":"https://ror.org/0009eea46","country_code":null,"type":"facility","lineage":["https://openalex.org/I4392738276","https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Fu","raw_affiliation_strings":["Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China","State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","Hangzhou Innovation Institute, Beihang University"],"affiliations":[{"raw_affiliation_string":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China","institution_ids":["https://openalex.org/I82880672","https://openalex.org/I4392738276"]},{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056847110","display_name":"Qingjie Liu","orcid":"https://orcid.org/0000-0002-5181-6451"},"institutions":[{"id":"https://openalex.org/I4392738276","display_name":"State Key Laboratory of Virtual Reality Technology and Systems","ror":"https://ror.org/0009eea46","country_code":null,"type":"facility","lineage":["https://openalex.org/I4392738276","https://openalex.org/I82880672"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingjie Liu","raw_affiliation_strings":["Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China","State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","Hangzhou Innovation Institute, Beihang University"],"affiliations":[{"raw_affiliation_string":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China","institution_ids":["https://openalex.org/I82880672","https://openalex.org/I4392738276"]},{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100398953","display_name":"Yunhong Wang","orcid":"https://orcid.org/0000-0001-8001-2703"},"institutions":[{"id":"https://openalex.org/I4392738276","display_name":"State Key Laboratory of Virtual Reality Technology and Systems","ror":"https://ror.org/0009eea46","country_code":null,"type":"facility","lineage":["https://openalex.org/I4392738276","https://openalex.org/I82880672"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhong Wang","raw_affiliation_strings":["Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China","State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","Hangzhou Innovation Institute, Beihang University"],"affiliations":[{"raw_affiliation_string":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China","institution_ids":["https://openalex.org/I82880672","https://openalex.org/I4392738276"]},{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100783342"],"corresponding_institution_ids":["https://openalex.org/I4392738276","https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":3.4782,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.94645658,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9973999857902527,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996999979019165,"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":0.778736412525177},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.660345196723938},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.6122698187828064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5255429148674011},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.4783613085746765},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4624410569667816},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45678362250328064},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4129781424999237},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3298473358154297},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13266029953956604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778736412525177},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.660345196723938},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.6122698187828064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5255429148674011},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4783613085746765},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4624410569667816},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45678362250328064},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4129781424999237},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3298473358154297},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13266029953956604},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859880","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G7665144123","display_name":null,"funder_award_id":"U20B2069","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G950554376","display_name":null,"funder_award_id":"2018YFB1701600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1485009520","https://openalex.org/W1522301498","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2064675550","https://openalex.org/W2144960104","https://openalex.org/W2194775991","https://openalex.org/W2412400526","https://openalex.org/W2489434015","https://openalex.org/W2505639562","https://openalex.org/W2571175805","https://openalex.org/W2605295222","https://openalex.org/W2623594919","https://openalex.org/W2626778328","https://openalex.org/W2740757571","https://openalex.org/W2745166287","https://openalex.org/W2753107664","https://openalex.org/W2784458614","https://openalex.org/W2796347433","https://openalex.org/W2799263800","https://openalex.org/W2904164128","https://openalex.org/W2904910963","https://openalex.org/W2919570819","https://openalex.org/W2937843571","https://openalex.org/W2946086442","https://openalex.org/W2949107813","https://openalex.org/W2950477723","https://openalex.org/W2950628590","https://openalex.org/W2950739196","https://openalex.org/W2952524542","https://openalex.org/W2962764817","https://openalex.org/W2962766617","https://openalex.org/W2963109634","https://openalex.org/W2963341956","https://openalex.org/W2963383024","https://openalex.org/W2963735856","https://openalex.org/W2964022527","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2969318875","https://openalex.org/W2974011685","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W3006154882","https://openalex.org/W3008187564","https://openalex.org/W3034772468","https://openalex.org/W3034772996","https://openalex.org/W3092462694","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3098085362","https://openalex.org/W3098232790","https://openalex.org/W3103465009","https://openalex.org/W3107331169","https://openalex.org/W3110435696","https://openalex.org/W3112077297","https://openalex.org/W3168649818","https://openalex.org/W3173364567","https://openalex.org/W4289126595","https://openalex.org/W4293584584","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6639102338","https://openalex.org/W6750227808","https://openalex.org/W6757135208","https://openalex.org/W6778485988","https://openalex.org/W6782838747","https://openalex.org/W6784094891"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,43,94,134],"transformer":[6,44],"based":[7],"approach":[8,37,66],"for":[9],"visual":[10,72,112],"grounding.":[11],"Unlike":[12],"existing":[13],"proposal-and-rank":[14],"frameworks":[15,25],"that":[16,26,126],"rely":[17],"heavily":[18],"on":[19,40,137],"pretrained":[20,51],"object":[21,122],"detectors":[22,52],"or":[23,53],"proposal-free":[24,131],"upgrade":[27],"an":[28],"off-the-shelf":[29],"one-stage":[30],"detector":[31],"by":[32,115,133],"fusing":[33],"textual":[34,79],"embeddings,":[35],"our":[36,65,90,127],"is":[38,47,67],"built":[39],"top":[41],"of":[42,49,77,101],"encoder-decoder":[45],"and":[46,104],"independent":[48],"any":[50],"word":[54],"embedding":[55],"models.":[56],"Termed":[57],"as":[58],"VGTR":[59,91],"\u2013":[60],"Visual":[61],"Grounding":[62],"with":[63],"TRansformers,":[64],"designed":[68],"to":[69,92,109,118],"learn":[70],"semantic-discriminative":[71],"features":[73],"under":[74],"the":[75,78,116,120],"guidance":[76],"description":[80,117],"without":[81],"harming":[82],"their":[83],"location":[84],"ability.":[85],"This":[86],"information":[87],"flow":[88],"enables":[89],"have":[93],"strong":[95],"capability":[96],"in":[97],"capturing":[98],"context-level":[99],"semantics":[100],"both":[102],"vision":[103],"language":[105],"modalities,":[106],"rendering":[107],"us":[108],"aggregate":[110],"accurate":[111],"clues":[113],"implied":[114],"locate":[119],"interested":[121],"instance.":[123],"Experiments":[124],"show":[125],"method":[128],"outperforms":[129],"state-of-the-art":[130],"approaches":[132],"considerable":[135],"margin":[136],"four":[138],"benchmarks.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}