{"id":"https://openalex.org/W4408611571","doi":"https://doi.org/10.1109/icaiic64266.2025.10920758","title":"CRESO: CLIP-Based Referring Expression Segmentation for Object using Text Prompt","display_name":"CRESO: CLIP-Based Referring Expression Segmentation for Object using Text Prompt","publication_year":2025,"publication_date":"2025-02-18","ids":{"openalex":"https://openalex.org/W4408611571","doi":"https://doi.org/10.1109/icaiic64266.2025.10920758"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic64266.2025.10920758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic64266.2025.10920758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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/A5100611849","display_name":"Subin Park","orcid":"https://orcid.org/0000-0001-8944-1002"},"institutions":[{"id":"https://openalex.org/I28777354","display_name":"Sejong University","ror":"https://ror.org/00aft1q37","country_code":"KR","type":"education","lineage":["https://openalex.org/I28777354"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Subin Park","raw_affiliation_strings":["Sejong University,Department of Artifical Intelligence,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Sejong University,Department of Artifical Intelligence,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I28777354"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009734606","display_name":"Zhegao Piao","orcid":"https://orcid.org/0000-0001-9932-482X"},"institutions":[{"id":"https://openalex.org/I28777354","display_name":"Sejong University","ror":"https://ror.org/00aft1q37","country_code":"KR","type":"education","lineage":["https://openalex.org/I28777354"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Zhegao Piao","raw_affiliation_strings":["Engineering Sejong University,Department of Computer,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Engineering Sejong University,Department of Computer,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I28777354"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022731366","display_name":"Yeong Hyeon Gu","orcid":"https://orcid.org/0000-0002-0002-9386"},"institutions":[{"id":"https://openalex.org/I28777354","display_name":"Sejong University","ror":"https://ror.org/00aft1q37","country_code":"KR","type":"education","lineage":["https://openalex.org/I28777354"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeong Hyeon Gu","raw_affiliation_strings":["Sejong University,Department of Artifical Intelligence,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Sejong University,Department of Artifical Intelligence,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I28777354"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100611849"],"corresponding_institution_ids":["https://openalex.org/I28777354"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02530478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"0974","last_page":"0979"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10028","display_name":"Topic Modeling","score":0.9959999918937683,"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/T12031","display_name":"Speech and dialogue systems","score":0.9728000164031982,"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/computer-science","display_name":"Computer science","score":0.7168864607810974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6332618594169617},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6043751835823059},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5869693756103516},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5439720749855042},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47353336215019226},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4361712336540222},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4233323037624359},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3281761109828949},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1275651454925537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7168864607810974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6332618594169617},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6043751835823059},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5869693756103516},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5439720749855042},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47353336215019226},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4361712336540222},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4233323037624359},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3281761109828949},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1275651454925537}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic64266.2025.10920758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic64266.2025.10920758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2072498467","https://openalex.org/W2760103357","https://openalex.org/W2886247548","https://openalex.org/W3094502228","https://openalex.org/W3138516171","https://openalex.org/W3139633126","https://openalex.org/W4312420092","https://openalex.org/W4318147428","https://openalex.org/W4388099806","https://openalex.org/W4390190073","https://openalex.org/W4390889782","https://openalex.org/W4393146352","https://openalex.org/W4393149172","https://openalex.org/W4403067223","https://openalex.org/W6765753173","https://openalex.org/W6791353385","https://openalex.org/W6858561505","https://openalex.org/W6874325552"],"related_works":["https://openalex.org/W2392243736","https://openalex.org/W86652014","https://openalex.org/W4379231730","https://openalex.org/W2328518092","https://openalex.org/W4389858081","https://openalex.org/W3101249758","https://openalex.org/W2382079200","https://openalex.org/W2737719445","https://openalex.org/W3129895999","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Text-based":[0],"image":[1,12,33,77,102,193],"segmentation":[2,78,111,134,147,194],"is":[3],"the":[4,20,50,65,84,97,117,146,159,165,181,184],"task":[5],"of":[6,22,148,183],"segmenting":[7],"specific":[8],"objects":[9,40,129,149],"in":[10,41,76],"an":[11,131],"based":[13,112],"on":[14,113,158],"user-provided":[15],"text":[16,30,60,105,114,197],"prompts.":[17,198],"To":[18],"improve":[19],"performance":[21],"existing":[23],"models,":[24],"this":[25,46],"paper":[26,179],"emphasizes":[27],"accurately":[28],"embedding":[29],"conditions":[31],"into":[32],"features":[34,103],"and":[35,92,138,153,175],"effectively":[36,188],"capturing":[37],"interactions":[38],"between":[39,128],"complex":[42,137],"visual":[43],"scenes.":[44],"In":[45],"paper,":[47],"we":[48],"propose":[49],"CRESO":[51,71,166,185],"(CLIP-Based":[52],"Referring":[53],"Expression":[54],"Segmentation":[55],"for":[56,136,187],"Objects)":[57],"model":[58,72,167,186],"using":[59,104],"prompt":[61],"which":[62],"builds":[63],"upon":[64],"state-of-the-art":[66],"CLIPSeg":[67],"model.":[68],"Our":[69],"proposed":[70],"achieves":[73],"superior":[74],"accuracy":[75,135],"by":[79,196],"leveraging":[80],"three":[81],"key":[82],"methods:":[83],"Feature-wise":[85],"Linear":[86],"Modulation":[87],"(FiLM)":[88],"Layer,":[89,91],"Transformer":[90,118],"multi-scale":[93,142],"feature":[94,143],"fusion.":[95],"Specifically,":[96],"FiLM":[98],"Layer":[99,119],"adjusts":[100],"fine-grained":[101],"embeddings":[106],"to":[107,124],"enable":[108],"precise":[109],"object":[110],"conditions,":[115],"while":[116],"utilizes":[120],"a":[121],"self-attention":[122],"mechanism":[123],"learn":[125],"contextual":[126],"relationships":[127],"within":[130],"image,":[132],"enhancing":[133],"overlapping":[139],"structures.":[140,155],"Furthermore,":[141],"fusion":[144],"enables":[145],"with":[150],"diverse":[151,172],"sizes":[152],"intricate":[154],"Experimental":[156],"results":[157],"OCID-":[160],"VLG":[161],"dataset":[162],"demonstrate":[163],"that":[164],"outperforms":[168],"competitive":[169],"baseline":[170],"across":[171],"evaluation":[173],"metrics":[174],"precision":[176],"thresholds.":[177],"This":[178],"highlights":[180],"potential":[182],"addressing":[189],"applications":[190],"requiring":[191],"accurate":[192],"guided":[195]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}