{"id":"https://openalex.org/W3198016657","doi":"https://doi.org/10.1145/3463945.3469055","title":"Language-Conditioned Region Proposal and Retrieval Network for Referring Expression Comprehension","display_name":"Language-Conditioned Region Proposal and Retrieval Network for Referring Expression Comprehension","publication_year":2021,"publication_date":"2021-08-21","ids":{"openalex":"https://openalex.org/W3198016657","doi":"https://doi.org/10.1145/3463945.3469055","mag":"3198016657"},"language":"en","primary_location":{"id":"doi:10.1145/3463945.3469055","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3463945.3469055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Workshop on Multi-Modal Pre-Training for Multimedia Understanding","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/A5101899130","display_name":"Yanwei Xie","orcid":"https://orcid.org/0009-0009-9141-8907"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanwei Xie","raw_affiliation_strings":["University of Science and Technology of China, HeFei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, HeFei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424059","display_name":"Daqing Liu","orcid":"https://orcid.org/0000-0002-8286-0105"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daqing Liu","raw_affiliation_strings":["University of Science and Technology of China, HeFei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, HeFei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088031350","display_name":"Xuejin Chen","orcid":"https://orcid.org/0000-0003-0478-7018"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuejin Chen","raw_affiliation_strings":["University of Science and Technology of China, HeFei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, HeFei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["University of Science and Technology of China, HeFei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, HeFei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101899130"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0961,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3929902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"14","last_page":"22"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9940000176429749,"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":0.9818000197410583,"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":0.85672926902771},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6360838413238525},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6048523783683777},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5982051491737366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5977599024772644},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5161119699478149},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5106411576271057},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4847516715526581},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.45976606011390686},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08773663640022278}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.85672926902771},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6360838413238525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6048523783683777},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5982051491737366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5977599024772644},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5161119699478149},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5106411576271057},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4847516715526581},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.45976606011390686},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08773663640022278},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3463945.3469055","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3463945.3469055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Workshop on Multi-Modal Pre-Training for Multimedia Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2571175805","https://openalex.org/W2601564443","https://openalex.org/W2887585070","https://openalex.org/W2938603906","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2963323244","https://openalex.org/W2963351448","https://openalex.org/W2963644680","https://openalex.org/W2963735856","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2987734933","https://openalex.org/W2989604896","https://openalex.org/W3034772468","https://openalex.org/W3035323998","https://openalex.org/W3035365026","https://openalex.org/W3037533539","https://openalex.org/W3105136412"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W2616627668","https://openalex.org/W3137121595","https://openalex.org/W2392243736","https://openalex.org/W86652014","https://openalex.org/W2051345519","https://openalex.org/W2381031055","https://openalex.org/W2366070815","https://openalex.org/W2373862202","https://openalex.org/W2388232445"],"abstract_inverted_index":{"Referring":[0],"expression":[1],"comprehension":[2],"(REC)":[3],"is":[4,179],"a":[5,112,147,159,170],"multi-modal":[6],"task":[7,87],"that":[8,81,119,195],"aims":[9],"to":[10,17,96,101,126,153,165,181],"localize":[11],"target":[12,47,133],"regions":[13,123],"in":[14,40],"images":[15],"according":[16],"language":[18,54,66,128,187],"descriptions.":[19],"Existing":[20],"methods":[21,29,34,58,74,92],"can":[22],"be":[23],"concluded":[24],"into":[25],"two":[26],"categories,":[27],"proposal-based":[28,73],"and":[30,43,89,116,129,158,189,209],"proposal-free":[31,57,91],"methods.":[32],"Proposal-based":[33],"first":[35,120],"detect":[36,154],"all":[37],"candidate":[38],"objects":[39,50],"the":[41,46,53,61,65,72,90,107,127,132,139,142,174],"image":[42],"then":[44,130],"retrieve":[45],"among":[48],"those":[49,122,155],"based":[51,63],"on":[52,64,138,206],"description,":[55],"while":[56],"directly":[59],"locate":[60],"region":[62,69,78,114,134,149,161,167],"without":[67],"any":[68],"proposals.":[70],"However,":[71],"suffer":[75],"from":[76],"separate":[77],"proposal":[79,115,150],"networks":[80],"actually":[82],"do":[83],"not":[84,94],"suit":[85],"this":[86],"well,":[88],"are":[93],"able":[95],"perform":[97,166],"fine-grained":[98],"visual-language":[99],"alignments":[100],"yield":[102],"higher":[103],"precision.":[104],"To":[105],"overcome":[106],"above":[108],"drawbacks,":[109],"we":[110],"propose":[111],"language-conditioned":[113,148,160],"retrieval":[117,162,168],"network":[118,144,151,163],"detects":[121],"only":[124],"related":[125],"retrieves":[131],"by":[135],"compositional":[136],"reasoning":[137],"language.":[140,175],"Specifically,":[141],"proposed":[143,180,197],"consists":[145],"of":[146,173],"(LC-RPN)":[152],"language-related":[156],"regions,":[157],"(LC-RRN)":[164],"with":[169,202],"full":[171],"understanding":[172],"A":[176],"pre-training":[177],"mechanism":[178],"teach":[182],"our":[183,196],"model":[184],"knowledge":[185],"about":[186],"decomposing":[188],"vision-language":[190],"alignment.":[191],"Experimental":[192],"results":[193],"demonstrate":[194],"method":[198],"achieves":[199],"leading":[200],"performance":[201],"high":[203],"inference":[204],"speed":[205],"RefCOCO,":[207],"RefCOCO+,":[208],"RefCOCOg":[210],"benchmarks.":[211]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}