{"id":"https://openalex.org/W4361983876","doi":"https://doi.org/10.1109/tcsvt.2023.3263468","title":"Fully and Weakly Supervised Referring Expression Segmentation With End-to-End Learning","display_name":"Fully and Weakly Supervised Referring Expression Segmentation With End-to-End Learning","publication_year":2023,"publication_date":"2023-03-31","ids":{"openalex":"https://openalex.org/W4361983876","doi":"https://doi.org/10.1109/tcsvt.2023.3263468"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3263468","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3263468","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5100753255","display_name":"Hui Li","orcid":"https://orcid.org/0000-0001-8945-5391"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["School of Advanced Technology, Xi&#x2019;an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8945-5391","affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi&#x2019;an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044193894","display_name":"Ming-Jie Sun","orcid":"https://orcid.org/0000-0003-0649-522X"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjie Sun","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011918180","display_name":"Jimin Xiao","orcid":"https://orcid.org/0000-0002-9416-2486"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jimin Xiao","raw_affiliation_strings":["School of Advanced Technology, Xi&#x2019;an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9416-2486","affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi&#x2019;an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033755146","display_name":"Eng Gee Lim","orcid":"https://orcid.org/0000-0003-0199-7386"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Eng Gee Lim","raw_affiliation_strings":["School of Advanced Technology, Xi&#x2019;an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0199-7386","affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi&#x2019;an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362745","display_name":"Yao Zhao","orcid":"https://orcid.org/0000-0002-8581-9554"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8581-9554","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5824,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91478716,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"33","issue":"10","first_page":"5999","last_page":"6012"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9921000003814697,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9868000149726868,"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/segmentation","display_name":"Segmentation","score":0.8196316957473755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7777531743049622},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7430866360664368},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6888833045959473},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5531460642814636},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5031432509422302},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.49808835983276367},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48711133003234863},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4737551808357239},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4588698744773865},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4234699010848999},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.41442248225212097},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37000197172164917},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30346906185150146},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15024128556251526},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09578162431716919}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8196316957473755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777531743049622},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7430866360664368},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6888833045959473},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5531460642814636},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5031432509422302},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.49808835983276367},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48711133003234863},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4737551808357239},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4588698744773865},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4234699010848999},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.41442248225212097},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37000197172164917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30346906185150146},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15024128556251526},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09578162431716919},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3263468","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3263468","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G1794522962","display_name":"\u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u7684\u4ea4\u4e92\u5f0f\u591a\u89c6\u70b9\u89c6\u9891\u6280\u672f\u7814\u7a76","funder_award_id":"61972323","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8012633139","display_name":null,"funder_award_id":"2022YFE0200300","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":82,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W2031489346","https://openalex.org/W2194775991","https://openalex.org/W2247513039","https://openalex.org/W2250539671","https://openalex.org/W2337429362","https://openalex.org/W2489434015","https://openalex.org/W2565639579","https://openalex.org/W2600144439","https://openalex.org/W2602809673","https://openalex.org/W2605127024","https://openalex.org/W2798556392","https://openalex.org/W2876852810","https://openalex.org/W2900953995","https://openalex.org/W2910628332","https://openalex.org/W2950623159","https://openalex.org/W2952524542","https://openalex.org/W2962914239","https://openalex.org/W2962942822","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2963198662","https://openalex.org/W2963351448","https://openalex.org/W2963623257","https://openalex.org/W2963800628","https://openalex.org/W2964015378","https://openalex.org/W2964199361","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2966715458","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2980088508","https://openalex.org/W2987734933","https://openalex.org/W2994818707","https://openalex.org/W2996952120","https://openalex.org/W3034325957","https://openalex.org/W3034692043","https://openalex.org/W3034730770","https://openalex.org/W3034777757","https://openalex.org/W3035097537","https://openalex.org/W3035218869","https://openalex.org/W3035454331","https://openalex.org/W3035497460","https://openalex.org/W3035517717","https://openalex.org/W3035644209","https://openalex.org/W3090619019","https://openalex.org/W3093025045","https://openalex.org/W3093600664","https://openalex.org/W3094172275","https://openalex.org/W3098232790","https://openalex.org/W3104844437","https://openalex.org/W3107094551","https://openalex.org/W3108748824","https://openalex.org/W3109643012","https://openalex.org/W3110042533","https://openalex.org/W3126391825","https://openalex.org/W3128990302","https://openalex.org/W3138516171","https://openalex.org/W3154169267","https://openalex.org/W3159619744","https://openalex.org/W3164772195","https://openalex.org/W3169998662","https://openalex.org/W3172522282","https://openalex.org/W3177087374","https://openalex.org/W3187664142","https://openalex.org/W3192692200","https://openalex.org/W3201770677","https://openalex.org/W3204228395","https://openalex.org/W4205474609","https://openalex.org/W4312543911","https://openalex.org/W4313054169","https://openalex.org/W6726873649","https://openalex.org/W6749526849","https://openalex.org/W6753441378","https://openalex.org/W6764136514","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6783787784","https://openalex.org/W6784930956","https://openalex.org/W6848151499"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W2979236518","https://openalex.org/W2358318464","https://openalex.org/W2340870721","https://openalex.org/W3091955004"],"abstract_inverted_index":{"Referring":[0],"Expression":[1],"Segmentation":[2],"(RES),":[3],"which":[4,32],"is":[5,159,173,202],"aimed":[6],"at":[7],"localizing":[8],"and":[9,29,38,56,77,82,115,153,161,169,195,215,224],"segmenting":[10],"the":[11,15,27,35,47,50,61,80,94,100,104,108,112,117,122,126,142,164,170],"target":[12,105],"according":[13],"to":[14,74,134],"given":[16],"language":[17],"expression,":[18,114],"has":[19],"drawn":[20],"increasing":[21],"attention.":[22],"Existing":[23],"methods":[24,212],"jointly":[25],"consider":[26],"localization":[28,81,101,123],"segmentation":[30,83,127,144,171,177],"steps,":[31],"rely":[33],"on":[34,111,151,183,213,229],"fused":[36],"visual":[37,95,118],"linguistic":[39,88],"features":[40],"for":[41,97],"both":[42],"steps.":[43,84],"We":[44],"argue":[45],"that":[46],"conflict":[48],"between":[49],"purpose":[51],"of":[52],"identifying":[53],"an":[54],"object":[55,106],"generating":[57],"a":[58,70,138,184,219],"mask":[59],"limits":[60],"RES":[62,136,190,211],"performance.":[63],"To":[64,179],"solve":[65],"this":[66],"problem,":[67],"we":[68,187],"propose":[69],"parallel":[71],"position-kernel-segmentation":[72],"pipeline":[73,130],"better":[75],"isolate":[76],"then":[78,116],"interact":[79],"In":[85],"our":[86,181],"pipeline,":[87],"information":[89],"will":[90,226],"not":[91],"directly":[92],"contaminate":[93],"feature":[96],"segmentation.":[98],"Specifically,":[99],"step":[102,124],"localizes":[103],"in":[107,137],"image":[109],"based":[110],"referring":[113],"kernel":[119],"obtained":[120],"from":[121],"guides":[125],"step.":[128],"This":[129],"also":[131],"enables":[132],"us":[133],"train":[135],"weakly-supervised":[139,176,185,216],"way,":[140],"where":[141],"pixel-level":[143],"labels":[145],"are":[146],"replaced":[147],"by":[148,218],"click":[149,165,198],"annotations":[150,166],"center":[152],"corner":[154],"points.":[155],"The":[156,222],"position":[157],"head":[158,172],"fully-supervised":[160],"trained":[162,174],"with":[163,175,197],"as":[167],"supervision,":[168],"losses.":[178],"validate":[180],"framework":[182],"setting,":[186],"annotated":[188],"three":[189],"benchmark":[191],"datasets":[192],"(RefCOCO,":[193],"RefCOCO+":[194],"RefCOCOg)":[196],"annotations.":[199],"Our":[200],"method":[201],"simple":[203],"but":[204],"surprisingly":[205],"effective,":[206],"outperforming":[207],"all":[208],"previous":[209],"state-of-the-art":[210],"fully-":[214],"settings":[217],"large":[220],"margin.":[221],"code":[223],"dataset":[225],"be":[227],"released":[228],"<uri":[230],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[231],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/detectiveli/PKS.git</uri>":[232],".":[233]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}