{"id":"https://openalex.org/W4392449449","doi":"https://doi.org/10.1109/tip.2024.3371348","title":"Toward Robust Referring Image Segmentation","display_name":"Toward Robust Referring Image Segmentation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392449449","doi":"https://doi.org/10.1109/tip.2024.3371348","pmid":"https://pubmed.ncbi.nlm.nih.gov/38442064"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3371348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3371348","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/A5024765927","display_name":"Jianzong Wu","orcid":"https://orcid.org/0009-0007-4559-7970"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzong Wu","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089900108","display_name":"Xiangtai Li","orcid":"https://orcid.org/0000-0002-0550-8247"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH","CN"],"is_corresponding":false,"raw_author_name":"Xiangtai Li","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Zurich, Switzerland","National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0550-8247","affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445616","display_name":"Xia Li","orcid":"https://orcid.org/0000-0003-2284-1700"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH","CN"],"is_corresponding":false,"raw_author_name":"Xia Li","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Zurich, Switzerland","National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036631624","display_name":"Henghui Ding","orcid":"https://orcid.org/0000-0003-4868-6526"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Henghui Ding","raw_affiliation_strings":["Department of Information Technology and Electrical Engineering, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-4868-6526","affiliations":[{"raw_affiliation_string":"Department of Information Technology and Electrical Engineering, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024097240","display_name":"Yunhai Tong","orcid":"https://orcid.org/0000-0001-8735-2516"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhai Tong","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8735-2516","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["The University of Sydney, Camperdown, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"The University of Sydney, Camperdown, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.6499,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.99208808,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"33","issue":null,"first_page":"1782","last_page":"1794"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9973999857902527,"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":0.8218072652816772},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6894850730895996},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6766703724861145},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6384575963020325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6026949882507324},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5531451106071472},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4859953820705414},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4489455223083496},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44061192870140076},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42910414934158325},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4215799570083618},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3481173515319824},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.334945410490036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8218072652816772},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6894850730895996},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6766703724861145},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6384575963020325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6026949882507324},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5531451106071472},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4859953820705414},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4489455223083496},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44061192870140076},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42910414934158325},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4215799570083618},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3481173515319824},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.334945410490036},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2024.3371348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3371348","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:38442064","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38442064","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":[],"awards":[{"id":"https://openalex.org/G1853729409","display_name":null,"funder_award_id":"2023YFC3807600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":95,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2489434015","https://openalex.org/W2556882396","https://openalex.org/W2748021867","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2962942822","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2964115968","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2967767914","https://openalex.org/W2980088508","https://openalex.org/W2997564896","https://openalex.org/W3000172657","https://openalex.org/W3020827971","https://openalex.org/W3034325957","https://openalex.org/W3034692043","https://openalex.org/W3035097537","https://openalex.org/W3035549667","https://openalex.org/W3043840704","https://openalex.org/W3092462694","https://openalex.org/W3093025045","https://openalex.org/W3096609285","https://openalex.org/W3104844437","https://openalex.org/W3106297436","https://openalex.org/W3108748824","https://openalex.org/W3110440461","https://openalex.org/W3121281282","https://openalex.org/W3136759792","https://openalex.org/W3138516171","https://openalex.org/W3153666347","https://openalex.org/W3159619744","https://openalex.org/W3169367294","https://openalex.org/W3169998662","https://openalex.org/W3172522282","https://openalex.org/W3178075329","https://openalex.org/W3185341429","https://openalex.org/W3187664142","https://openalex.org/W3201770677","https://openalex.org/W3215863079","https://openalex.org/W3215899623","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4225495512","https://openalex.org/W4226024706","https://openalex.org/W4283311214","https://openalex.org/W4283836657","https://openalex.org/W4285301270","https://openalex.org/W4288404646","https://openalex.org/W4290847725","https://openalex.org/W4307504011","https://openalex.org/W4312511177","https://openalex.org/W4312543911","https://openalex.org/W4312585030","https://openalex.org/W4312598093","https://openalex.org/W4312844845","https://openalex.org/W4386066126","https://openalex.org/W4386075493","https://openalex.org/W4386076142","https://openalex.org/W4390190349","https://openalex.org/W4390872914","https://openalex.org/W4390873107","https://openalex.org/W4390873799","https://openalex.org/W4391547487","https://openalex.org/W4401070841","https://openalex.org/W4402187257","https://openalex.org/W6729764063","https://openalex.org/W6740483536","https://openalex.org/W6753695549","https://openalex.org/W6755207826","https://openalex.org/W6757555829","https://openalex.org/W6757817989","https://openalex.org/W6768730002","https://openalex.org/W6774681163","https://openalex.org/W6784094891","https://openalex.org/W6788135285","https://openalex.org/W6790586251","https://openalex.org/W6791353385","https://openalex.org/W6792105337","https://openalex.org/W6796446893","https://openalex.org/W6797399245","https://openalex.org/W6798837711","https://openalex.org/W6804418671","https://openalex.org/W6804533212","https://openalex.org/W6810158684","https://openalex.org/W6810302072","https://openalex.org/W6811002592","https://openalex.org/W6838809002","https://openalex.org/W6839392762","https://openalex.org/W6840684104","https://openalex.org/W6848855029","https://openalex.org/W6851610920"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W4281476908","https://openalex.org/W4304700937","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Referring":[0,88],"Image":[1,89],"Segmentation":[2,90],"(RIS)":[3],"is":[4,43,190],"a":[5,60,63,74,81,133,139,146,181],"fundamental":[6],"vision-language":[7],"task":[8],"that":[9],"outputs":[10],"object":[11],"masks":[12],"based":[13],"on":[14,174],"text":[15,41,102],"descriptions.":[16],"Many":[17],"works":[18],"have":[19],"achieved":[20],"considerable":[21],"progress":[22],"for":[23,69,184],"RIS,":[24,85],"including":[25],"different":[26],"fusion":[27,151],"method":[28],"designs.":[29],"In":[30],"this":[31,77,106],"work,":[32],"we":[33,79,109,137],"explore":[34],"an":[35],"essential":[36],"question,":[37],"\"What":[38],"if":[39],"the":[40,49,55,94,99],"description":[42],"wrong":[44],"or":[45],"misleading?\"":[46],"For":[47],"example,":[48],"described":[50],"objects":[51],"are":[52],"not":[53],"in":[54,132],"image.":[56],"We":[57],"term":[58],"such":[59,73],"sentence":[61,96],"as":[62],"negative":[64,95,120],"sentence.":[65],"However,":[66],"existing":[67,116],"solutions":[68],"RIS":[70,117,176],"cannot":[71],"handle":[72],"setting.":[75],"To":[76,104],"end,":[78],"propose":[80,123,138],"new":[82,107,124,140],"formulation":[83],"of":[84,130],"named":[86],"Robust":[87],"(R-RIS).":[91],"It":[92],"considers":[93],"inputs":[97,131],"besides":[98],"regular":[100],"positive":[101],"inputs.":[103],"facilitate":[105],"task,":[108],"create":[110],"three":[111],"R-RIS":[112,161,178],"datasets":[113,118],"by":[114,163],"augmenting":[115],"with":[119,145],"sentences":[121],"and":[122,149,177],"metrics":[125],"to":[126,159],"evaluate":[127],"both":[128,175,185],"types":[129],"unified":[134],"manner.":[135],"Furthermore,":[136],"transformer-based":[141],"model,":[142],"called":[143],"RefSegformer,":[144],"token-based":[147],"vision":[148],"language":[150],"module.":[152],"Our":[153,168,187],"design":[154],"can":[155],"be":[156],"easily":[157],"extended":[158],"our":[160],"setting":[162],"adding":[164],"extra":[165],"blank":[166],"tokens.":[167],"proposed":[169],"RefSegformer":[170],"achieves":[171],"state-of-the-art":[172],"results":[173],"datasets,":[179],"establishing":[180],"solid":[182],"baseline":[183],"settings.":[186],"project":[188],"page":[189],"at":[191],"https://github.com/jianzongwu/robust-ref-seg.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":31},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}