{"id":"https://openalex.org/W4381744284","doi":"https://doi.org/10.1109/cscwd57460.2023.10152851","title":"Cross-Modal Fusing Vision-Language Network for Referring Image Segmentation","display_name":"Cross-Modal Fusing Vision-Language Network for Referring Image Segmentation","publication_year":2023,"publication_date":"2023-05-24","ids":{"openalex":"https://openalex.org/W4381744284","doi":"https://doi.org/10.1109/cscwd57460.2023.10152851"},"language":"en","primary_location":{"id":"doi:10.1109/cscwd57460.2023.10152851","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cscwd57460.2023.10152851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","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/A5100660064","display_name":"Yu Zhao","orcid":"https://orcid.org/0000-0002-8454-0025"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Zhao","raw_affiliation_strings":["Inner Mongolia University,Department of Computer Science,Huhhot,China,010021"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,Department of Computer Science,Huhhot,China,010021","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101960931","display_name":"Wei Wu","orcid":"https://orcid.org/0000-0002-2694-6086"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wu","raw_affiliation_strings":["Inner Mongolia University,Department of Computer Science,Huhhot,China,010021"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,Department of Computer Science,Huhhot,China,010021","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071638388","display_name":"Yue Guo","orcid":"https://orcid.org/0000-0003-4290-7228"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Guo","raw_affiliation_strings":["Inner Mongolia University,Department of Computer Science,Huhhot,China,010021"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,Department of Computer Science,Huhhot,China,010021","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100660064"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":0.123,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.38576144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1861","last_page":"1866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9922000169754028,"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":0.9739999771118164,"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":0.8012086153030396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7343693971633911},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6250742673873901},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5684988498687744},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5313684940338135},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.51463782787323},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5085426568984985},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4925263822078705},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46870821714401245},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.45560353994369507},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41241946816444397},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3988630175590515},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3862530589103699},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09177586436271667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8012086153030396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7343693971633911},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6250742673873901},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5684988498687744},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5313684940338135},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.51463782787323},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5085426568984985},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4925263822078705},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46870821714401245},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.45560353994369507},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41241946816444397},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3988630175590515},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3862530589103699},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09177586436271667},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cscwd57460.2023.10152851","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cscwd57460.2023.10152851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2383812217","https://openalex.org/W2326515389","https://openalex.org/W2491005386","https://openalex.org/W2380370605"],"abstract_inverted_index":{"Reference":[0],"Image":[1],"Segmentation":[2],"(RIS)":[3],"is":[4],"a":[5],"challenging":[6],"task,":[7],"swhich":[8],"aims":[9],"to":[10,24,63,71],"match":[11],"the":[12,26,61,99],"foreground":[13],"mask":[14],"of":[15,101],"segmented":[16],"entities":[17],"with":[18],"natural":[19],"language":[20,50],"expressions.":[21],"In":[22],"order":[23],"solve":[25],"RIS":[27],"problem,":[28],"we":[29],"propose":[30],"two":[31],"modules:":[32],"Cross-Modal":[33],"Fusing":[34],"Vision-Language":[35],"(CMFVL)":[36],"module,":[37],"Vision":[38],"and":[39,49,58,76,81],"Language":[40],"Sequence":[41],"Generation":[42],"(VLSG)":[43],"module.":[44],"VLSG":[45,86],"receives":[46],"visual":[47],"features":[48,73,80],"features,":[51],"generates":[52],"feature":[53,82],"sequences":[54,62,83],"through":[55,74],"attention":[56,70],"mechanism,":[57],"then":[59,77],"sends":[60],"CMFVL.":[64],"CMFVL":[65],"module":[66],"first":[67],"establishes":[68],"global":[69],"vision":[72,79],"Transformer":[75,88],"inputs":[78],"generated":[84],"by":[85],"into":[87],"for":[89],"context":[90],"information":[91],"interaction.":[92],"Experiments":[93],"on":[94],"three":[95],"benchmark":[96],"datasets":[97],"confirm":[98],"effectiveness":[100],"our":[102],"method.":[103]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}