{"id":"https://openalex.org/W4402915848","doi":"https://doi.org/10.1109/icip51287.2024.10647728","title":"Towards Generalizable Referring Image Segmentation Via Target Prompt And Visual Coherence","display_name":"Towards Generalizable Referring Image Segmentation Via Target Prompt And Visual Coherence","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402915848","doi":"https://doi.org/10.1109/icip51287.2024.10647728"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","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/A5103015234","display_name":"Yajie Liu","orcid":"https://orcid.org/0000-0002-0879-5894"},"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":"Yajie Liu","raw_affiliation_strings":["Beihang University,School of Computer Science and Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059707268","display_name":"Pu Ge","orcid":"https://orcid.org/0000-0002-4444-3159"},"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":"Pu Ge","raw_affiliation_strings":["Hangzhou Innovation Institute Beihang University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Hangzhou Innovation Institute Beihang University,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012939080","display_name":"Haoxiang Ma","orcid":"https://orcid.org/0000-0003-0612-0508"},"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":"Haoxiang Ma","raw_affiliation_strings":["Beihang University,School of Computer Science and Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102099735","display_name":"Shichao Fan","orcid":null},"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":"Shichao Fan","raw_affiliation_strings":["Beihang University,School of Computer Science and Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056847110","display_name":"Qingjie Liu","orcid":"https://orcid.org/0000-0002-5181-6451"},"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":"Qingjie Liu","raw_affiliation_strings":["Beihang University,School of Computer Science and Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073698613","display_name":"Di Huang","orcid":"https://orcid.org/0000-0003-0231-9093"},"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":"Di Huang","raw_affiliation_strings":["Beihang University,School of Computer Science and Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100398953","display_name":"Yunhong Wang","orcid":"https://orcid.org/0000-0001-8001-2703"},"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":"Yunhong Wang","raw_affiliation_strings":["Beihang University,School of Computer Science and Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103015234"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54185247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2599","last_page":"2605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9901000261306763,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9901000261306763,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9865000247955322,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9822999835014343,"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":0.7681008577346802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6602102518081665},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6420831680297852},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6150948405265808},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6110220551490784},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6005711555480957},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07156875729560852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7681008577346802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6602102518081665},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6420831680297852},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6150948405265808},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6110220551490784},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6005711555480957},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07156875729560852},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10647728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2251329024","https://openalex.org/W2489434015","https://openalex.org/W2963109634","https://openalex.org/W2963244312","https://openalex.org/W3035198432","https://openalex.org/W3138516171","https://openalex.org/W3166396011","https://openalex.org/W3198377975","https://openalex.org/W3201770677","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4285192809","https://openalex.org/W4310825192","https://openalex.org/W4312388078","https://openalex.org/W4312458986","https://openalex.org/W4386075493","https://openalex.org/W4386076034","https://openalex.org/W4386076148","https://openalex.org/W4390871886","https://openalex.org/W4402715795","https://openalex.org/W6791353385","https://openalex.org/W6792155083","https://openalex.org/W6847592527"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Referring":[0],"image":[1,10],"segmentation":[2],"(RIS)":[3],"aims":[4],"to":[5,27,68,75,120,127,162],"segment":[6],"objects":[7],"in":[8,90,97,149],"an":[9,81],"conditioning":[11],"on":[12,30,141,175],"free-form":[13],"text":[14,34],"descriptions.":[15],"Despite":[16],"the":[17,57,62,88,98,129,150,155,163],"overwhelming":[18],"progress,":[19],"it":[20],"still":[21],"remains":[22],"challenging":[23],"for":[24],"current":[25],"approaches":[26],"perform":[28],"well":[29],"cases":[31],"with":[32,37,70,80,112],"various":[33],"expressions":[35],"or":[36],"unseen":[38,142],"visual":[39,113,143],"entities,":[40],"limiting":[41],"its":[42,182],"further":[43],"application.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,73,105],"present":[49],"a":[50,77,91,107,116],"novel":[51],"RIS":[52],"approach,":[53],"which":[54,86,138],"substantially":[55],"improves":[56],"generalization":[58],"ability":[59],"by":[60],"addressing":[61],"two":[63],"dilemmas":[64],"mentioned":[65],"above.":[66],"Specially,":[67],"deal":[69],"unconstrained":[71],"texts,":[72],"propose":[74],"boost":[76],"given":[78],"expression":[79,89],"explicit":[82],"and":[83,124,133,154,170,178],"crucial":[84],"prompt,":[85],"complements":[87],"unified":[92],"context,":[93],"facilitating":[94],"target":[95,131],"capturing":[96],"presence":[99],"of":[100],"linguistic":[101],"style":[102],"changes.":[103],"Furthermore,":[104],"introduce":[106],"multi-modal":[108],"fusion":[109],"aggregation":[110],"module":[111],"guidance":[114],"from":[115],"powerful":[117],"pretrained":[118],"model":[119],"leverage":[121],"spatial":[122],"relations":[123],"pixel":[125],"coherences":[126],"handle":[128],"incomplete":[130],"masks":[132],"false":[134],"positive":[135],"irregular":[136],"clumps":[137],"often":[139],"appear":[140],"entities.":[144],"Extensive":[145],"experiments":[146],"are":[147],"conducted":[148],"zero-shot":[151],"cross-dataset":[152],"settings":[153],"proposed":[156],"approach":[157],"achieves":[158],"consistent":[159],"gains":[160],"compared":[161],"state-of-the-art,":[164],"e.g.,":[165],"$4.15":[166],"\\%$,":[167,169],"$5.45":[168],"$4.64":[171],"\\%$":[172],"mIoU":[173],"increase":[174],"RefCOCO,":[176],"RefCOCO+":[177],"ReferIt":[179],"respectively,":[180],"demonstrating":[181],"effectiveness.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}