{"id":"https://openalex.org/W4283029876","doi":"https://doi.org/10.1109/tip.2022.3181516","title":"Progressive Language-Customized Visual Feature Learning for One-Stage Visual Grounding","display_name":"Progressive Language-Customized Visual Feature Learning for One-Stage Visual Grounding","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4283029876","doi":"https://doi.org/10.1109/tip.2022.3181516","pmid":"https://pubmed.ncbi.nlm.nih.gov/35709109"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3181516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3181516","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5002061412","display_name":"Yue Liao","orcid":"https://orcid.org/0000-0002-2671-0655"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yue Liao","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049610245","display_name":"Aixi Zhang","orcid":"https://orcid.org/0000-0001-9863-0091"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aixi Zhang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438521","display_name":"Zhiyuan Chen","orcid":"https://orcid.org/0000-0003-3210-0324"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhiyuan Chen","raw_affiliation_strings":["Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056811650","display_name":"Tianrui Hui","orcid":"https://orcid.org/0000-0002-1172-1554"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrui Hui","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Information Engineering, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Information Engineering, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330138","display_name":"Si Liu","orcid":"https://orcid.org/0000-0002-9180-2935"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002061412"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":3.9749,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.9498129,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"4266","last_page":"4277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980000257492065,"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":0.9952999949455261,"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":0.7812258005142212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6267240643501282},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6003469228744507},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5678881406784058},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4985172748565674},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49073684215545654},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4810371696949005},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.46576690673828125},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45819032192230225},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4264489412307739},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11828786134719849},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11051598191261292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7812258005142212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6267240643501282},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6003469228744507},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5678881406784058},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4985172748565674},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49073684215545654},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4810371696949005},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.46576690673828125},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45819032192230225},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4264489412307739},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11828786134719849},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11051598191261292},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2022.3181516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3181516","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:35709109","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35709109","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G5696407354","display_name":null,"funder_award_id":"62122010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7834498664","display_name":null,"funder_award_id":"61876177","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1849277567","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W2006147162","https://openalex.org/W2194775991","https://openalex.org/W2247513039","https://openalex.org/W2251512949","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2571175805","https://openalex.org/W2601564443","https://openalex.org/W2606473278","https://openalex.org/W2620365397","https://openalex.org/W2752782242","https://openalex.org/W2760103357","https://openalex.org/W2770129969","https://openalex.org/W2799263800","https://openalex.org/W2904910963","https://openalex.org/W2946086442","https://openalex.org/W2948947170","https://openalex.org/W2952524542","https://openalex.org/W2962764817","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2963735856","https://openalex.org/W2963783181","https://openalex.org/W2964345792","https://openalex.org/W2983358816","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W3010803012","https://openalex.org/W3012573144","https://openalex.org/W3034325957","https://openalex.org/W3034772468","https://openalex.org/W3035097537","https://openalex.org/W3083600713","https://openalex.org/W3090449556","https://openalex.org/W3098232790","https://openalex.org/W3110435696","https://openalex.org/W3130619535","https://openalex.org/W3182736162","https://openalex.org/W4214490042","https://openalex.org/W4289126595","https://openalex.org/W6620707391","https://openalex.org/W6739901393","https://openalex.org/W6744053590","https://openalex.org/W6755207826","https://openalex.org/W6757135208","https://openalex.org/W6757817989","https://openalex.org/W6760424586","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6797397777"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3124914020","https://openalex.org/W4390516098","https://openalex.org/W2141033859","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2383687187","https://openalex.org/W2181948922","https://openalex.org/W2081517010","https://openalex.org/W2121496884"],"abstract_inverted_index":{"Visual":[0,104,116],"grounding":[1,18,121,156],"is":[2,52,171],"a":[3,11,32,74,98,113,120],"task":[4],"to":[5,55],"localize":[6],"an":[7,14],"object":[8,161],"described":[9],"by":[10,137],"sentence":[12],"in":[13,31,47,173],"image.":[15],"Conventional":[16],"visual":[17,21,65,76,87,126,155],"methods":[19,149],"extract":[20],"and":[22,26,66,119],"linguistic":[23,67,81,129],"features":[24],"isolatedly":[25],"then":[27],"perform":[28,56],"cross-modal":[29,57],"interaction":[30,58],"post-fusion":[33,39],"manner.":[34],"We":[35,93,123],"argue":[36],"that":[37],"this":[38,70],"mechanism":[40,79,96],"does":[41],"not":[42],"fully":[43],"utilize":[44],"the":[45,60,64,84,90,95,125,135,174],"information":[46,82],"two":[48],"modalities.":[49],"Instead,":[50],"it":[51],"more":[53],"desired":[54],"during":[59],"extraction":[61,85],"process":[62],"of":[63,86,112,134],"feature.":[68],"In":[69],"paper,":[71],"we":[72],"propose":[73],"language-customized":[75],"feature":[77,88,105,127],"learning":[78,106],"where":[80],"guides":[83],"from":[89],"very":[91],"beginning.":[92],"instantiate":[94],"as":[97],"one-stage":[99],"framework":[100],"named":[101],"Progressive":[102,114],"Language-customized":[103,115],"(PLV).":[107],"Our":[108,143],"proposed":[109,144],"PLV":[110,145],"consists":[111],"Encoder":[117],"(PLVE)":[118],"module.":[122],"customize":[124],"with":[128,150],"guidance":[130],"at":[131],"each":[132],"stage":[133],"PLVE":[136],"Channel-wise":[138],"Language-guided":[139],"Interaction":[140],"Modules":[141],"(CLIM).":[142],"outperforms":[146],"conventional":[147],"state-of-the-art":[148],"large":[151],"margins":[152],"across":[153],"five":[154],"datasets":[157],"without":[158],"pre-training":[159],"on":[160],"detection":[162],"datasets,":[163],"while":[164],"achieving":[165],"real-time":[166],"speed.":[167],"The":[168],"source":[169],"code":[170],"available":[172],"supplementary":[175],"material.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}