{"id":"https://openalex.org/W4395464584","doi":"https://doi.org/10.1145/3660638","title":"UniQRNet: Unifying Referring Expression Grounding and Segmentation with QRNet","display_name":"UniQRNet: Unifying Referring Expression Grounding and Segmentation with QRNet","publication_year":2024,"publication_date":"2024-04-25","ids":{"openalex":"https://openalex.org/W4395464584","doi":"https://doi.org/10.1145/3660638"},"language":"en","primary_location":{"id":"doi:10.1145/3660638","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3660638","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3660638","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":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3660638","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091465907","display_name":"Jiabo Ye","orcid":"https://orcid.org/0009-0009-5451-8984"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabo Ye","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-5451-8984","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076792499","display_name":"Junfeng Tian","orcid":"https://orcid.org/0000-0001-8566-7012"},"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":"Junfeng Tian","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8566-7012","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452477","display_name":"Ming Yan","orcid":"https://orcid.org/0000-0003-4959-8878"},"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":"Ming Yan","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4959-8878","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066544410","display_name":"Haiyang Xu","orcid":"https://orcid.org/0000-0001-9442-5912"},"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":"Haiyang Xu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9442-5912","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005965903","display_name":"Qinghao Ye","orcid":"https://orcid.org/0000-0002-7977-5540"},"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":"Qinghao Ye","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7977-5540","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019915855","display_name":"Yaya Shi","orcid":"https://orcid.org/0000-0003-0465-6712"},"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaya Shi","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China and NLPR, Chinese Academy of Sciences Institute of Automation, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0465-6712","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China and NLPR, Chinese Academy of Sciences Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083991825","display_name":"Xiaoshan Yang","orcid":"https://orcid.org/0000-0001-5453-9755"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshan Yang","raw_affiliation_strings":["NLPR, CASIA, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5453-9755","affiliations":[{"raw_affiliation_string":"NLPR, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068832926","display_name":"Xuwu Wang","orcid":"https://orcid.org/0000-0003-3363-570X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuwu Wang","raw_affiliation_strings":["Fudan University - Handan Campus, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3363-570X","affiliations":[{"raw_affiliation_string":"Fudan University - Handan Campus, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329266","display_name":"Ji Zhang","orcid":"https://orcid.org/0000-0002-3835-7975"},"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":"Ji Zhang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3835-7975","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010540039","display_name":"Liang He","orcid":"https://orcid.org/0000-0002-4723-5486"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4723-5486","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103028717","display_name":"Xin Lin","orcid":"https://orcid.org/0009-0008-4110-8989"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Lin","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-4110-8989","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6579,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64355925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"20","issue":"8","first_page":"1","last_page":"28"},"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":0.9914000034332275,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9796000123023987,"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":0.9045368432998657},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.667150616645813},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5979369282722473},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5810654163360596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5600402355194092},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5238038301467896},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5110891461372375},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4987599849700928},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4590221345424652},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4431285262107849},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4107874631881714},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41010645031929016},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.321227490901947},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22388851642608643},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09814384579658508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9045368432998657},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.667150616645813},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5979369282722473},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5810654163360596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5600402355194092},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5238038301467896},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5110891461372375},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4987599849700928},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4590221345424652},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4431285262107849},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4107874631881714},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41010645031929016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.321227490901947},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22388851642608643},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09814384579658508},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3660638","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3660638","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3660638","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"}],"best_oa_location":{"id":"doi:10.1145/3660638","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3660638","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3660638","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G2236499929","display_name":null,"funder_award_id":"2021ZD0111000","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3455679652","display_name":null,"funder_award_id":"2021ZD0111004","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3880861595","display_name":null,"funder_award_id":"21511100101","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G4763156897","display_name":null,"funder_award_id":"21511100100","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G4815797352","display_name":null,"funder_award_id":"No. 21511100101, No. 22511105901, No. 19511120200, No. 21511100100, and No. 18DZ2270800","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G5686620817","display_name":null,"funder_award_id":"22511105901","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G6300629003","display_name":null,"funder_award_id":"19511120200","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G7638806211","display_name":null,"funder_award_id":"18DZ2270800","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395464584.pdf","grobid_xml":"https://content.openalex.org/works/W4395464584.grobid-xml"},"referenced_works_count":97,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2006147162","https://openalex.org/W2194775991","https://openalex.org/W2247513039","https://openalex.org/W2251512949","https://openalex.org/W2302086703","https://openalex.org/W2302548814","https://openalex.org/W2489434015","https://openalex.org/W2490270993","https://openalex.org/W2558535589","https://openalex.org/W2605127024","https://openalex.org/W2606473278","https://openalex.org/W2619383789","https://openalex.org/W2745461083","https://openalex.org/W2798556392","https://openalex.org/W2876852810","https://openalex.org/W2884585870","https://openalex.org/W2894964039","https://openalex.org/W2904910963","https://openalex.org/W2946086442","https://openalex.org/W2952524542","https://openalex.org/W2962749469","https://openalex.org/W2962764817","https://openalex.org/W2962766617","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963383024","https://openalex.org/W2963705779","https://openalex.org/W2963800628","https://openalex.org/W2964010806","https://openalex.org/W2964345792","https://openalex.org/W2979987972","https://openalex.org/W2983358816","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2987734933","https://openalex.org/W3003985474","https://openalex.org/W3004019157","https://openalex.org/W3006871679","https://openalex.org/W3034325957","https://openalex.org/W3034692043","https://openalex.org/W3034772468","https://openalex.org/W3034984754","https://openalex.org/W3035097537","https://openalex.org/W3035268124","https://openalex.org/W3035640828","https://openalex.org/W3035644209","https://openalex.org/W3037533539","https://openalex.org/W3092760908","https://openalex.org/W3098232790","https://openalex.org/W3107094551","https://openalex.org/W3108748824","https://openalex.org/W3110435696","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3153682083","https://openalex.org/W3157528469","https://openalex.org/W3159619744","https://openalex.org/W3163747765","https://openalex.org/W3170182874","https://openalex.org/W3171206729","https://openalex.org/W3171547673","https://openalex.org/W3172522282","https://openalex.org/W3173364567","https://openalex.org/W3174004334","https://openalex.org/W3177271687","https://openalex.org/W3182736162","https://openalex.org/W3192448690","https://openalex.org/W3207127495","https://openalex.org/W4200631575","https://openalex.org/W4214490042","https://openalex.org/W4226392681","https://openalex.org/W4285212262","https://openalex.org/W4301104990","https://openalex.org/W4309181071","https://openalex.org/W4310825192","https://openalex.org/W4312349930","https://openalex.org/W4312351586","https://openalex.org/W4312543911","https://openalex.org/W4312845548","https://openalex.org/W4313145013","https://openalex.org/W4382466550","https://openalex.org/W4384820618","https://openalex.org/W4385571080","https://openalex.org/W4386075524","https://openalex.org/W4386076142","https://openalex.org/W4386076539","https://openalex.org/W4387969285","https://openalex.org/W4390873149","https://openalex.org/W4393156126","https://openalex.org/W4402727018","https://openalex.org/W4402753874","https://openalex.org/W6803916128"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W4287027631","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"Referring":[0],"expression":[1,135],"comprehension":[2],"aims":[3],"to":[4,36,79,132,155,163,183],"align":[5],"natural":[6],"language":[7,77],"queries":[8],"with":[9,57,244],"visual":[10,34,52,81,109,166,242],"scenes,":[11],"which":[12,61],"requires":[13],"establishing":[14],"fine-grained":[15,148],"correspondence":[16],"between":[17],"vision":[18],"and":[19,113,137,185,204,227,232,247],"language.":[20],"This":[21],"has":[22],"important":[23],"applications":[24],"in":[25,98,209],"multi-modal":[26,63],"reasoning":[27],"systems.":[28],"Existing":[29],"methods":[30,216],"typically":[31],"use":[32],"text-agnostic":[33],"backbones":[35],"extract":[37],"features":[38,53,243],"independently":[39],"without":[40],"considering":[41],"the":[42,50,58,89,99,108,114,130,152,158,187,192,239],"specific":[43],"text":[44,245],"input.":[45],"However,":[46,84],"we":[47,68,122],"argue":[48],"that":[49,75,92,146,176,235],"extracted":[51],"can":[54,93,237,248],"be":[55],"inconsistent":[56,115],"referring":[59,134,223],"expression,":[60],"hurts":[62],"understanding.":[64],"To":[65,119],"address":[66],"this,":[67],"first":[69],"propose":[70,124],"Query-modulated":[71],"Refinement":[72],"Network":[73],"(QRNet)":[74],"leverages":[76,147],"guidance":[78,106],"guide":[80,157],"feature":[82],"extraction.":[83],"it":[85],"only":[86,94],"focuses":[87],"on":[88,221],"grounding":[90,136,225],"task":[91,154],"provide":[95],"coarse-grained":[96],"annotations":[97],"form":[100],"of":[101,161,180,241],"bounding":[102],"box":[103],"coordinates.":[104],"The":[105,140],"for":[107],"backbone":[110],"is":[111],"indirect,":[112],"issue":[116],"still":[117],"exists.":[118],"this":[120],"end,":[121],"further":[123],"UniQRNet,":[125],"a":[126,143,172,218],"multi-task":[127,144],"framework":[128,141],"over":[129],"QRNet":[131,162],"learn":[133,164],"segmentation":[138,153,228],"jointly.":[139],"introduces":[142],"head":[145],"pixel-level":[149],"supervision":[150,181],"from":[151],"directly":[156],"intermediate":[159],"layers":[160],"text-consistent":[165],"features.":[167],"Besides,":[168],"UniQRNet":[169,212,236],"also":[170],"includes":[171],"loss":[173],"balance":[174],"strategy":[175],"allows":[177],"two":[178],"types":[179],"signals":[182],"cooperate":[184],"optimize":[186],"model":[188],"together.":[189],"We":[190],"conduct":[191],"most":[193],"comprehensive":[194,224],"comparison":[195],"experiment":[196],"covering":[197],"four":[198],"major":[199],"datasets,":[200],"ten":[201],"evaluation":[202,206],"set":[203],"three":[205],"metrics":[207],"used":[208],"previous":[210,214],"work.":[211],"outperforms":[213],"state-of-the-art":[215],"by":[217],"large":[219],"margin":[220],"both":[222],"(1.8%~5.09%)":[226],"tasks":[229],"(0.57%~5.56%).":[230],"Ablation":[231],"analysis":[233],"reveal":[234],"improve":[238],"consistency":[240],"input":[246],"bring":[249],"significant":[250],"performance":[251],"improvement.":[252]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}